critiques of case study

• How to Cite
• Language & Lit
• Rhyme & Rhythm
• The Rewrite
• Search Glass

How to Write a Critique for a Case Analysis

Law, science, psychology, medicine, business and education -- these fields all use case studies to glean quantifiable data from anecdotal situations both in the classroom and professional world. A case analysis provides a review and interpretation, also known as an assessment, of the study results to draw conclusions and solutions that can be applied on a broader basis. It’s the job of the critique to investigate and evaluate the case analysis findings.

Case Details Overview

A critique of a case analysis must first delineate the details of the case study for readability and clarity. This includes all of the factual data produced by the original case study, such as the dates the study was conducted, significant statistical data and the impact of variables. The case overview may also need to address whether the case study data is qualitative or quantitative, which involves noting whether the information is mathematically measurable. The case overview should be a brief synopsis of the case study designed to provide information needed to understand the critique, not a full explanation.

Unbiased Interpretation of Analysis

A critique must also detail the findings of the case analysis using impartial language. Whether your critique questions or validates the analysis, calls the findings into question or simply suggests alternative viewpoints, the conclusions of the case analysis under evaluation must first be presented objectively. This means employing the use of objective language to avoid making personal, judgmental or emotive statements in the paragraphs presenting the findings.

Thesis Rationale

The thesis statement for a critique must address the fundamental issues being raised or questions being asked about the case analysis. Unlike pure analysis, a critique is influenced by personal opinions and beliefs, and the thesis statement should indicate the author’s rationale. The thesis must provide the critique writer’s position statement clearly and concisely. The thesis should also identify the intent of the critique, such as whether it aims to validate or question the case analysis.

Point and Counterpoint

Support for the opinions presented in the thesis statement are provided by counterpoints that address the points made in the case analysis. It’s important to provide a counterargument for all of the major arguments and findings in a case study analysis to prove the validity of your thesis statement. Critiques that gloss over or ignore significant data may be considered invalid for failing to address the full analysis.

Validation or Dissension

A critique is typically either a dissension or validation of the case study analysis, and it should avoid presenting new information from other sources, such as data from other case studies not addressed by the case analysis. In some instances, a critique may present new thoughts or ideas in the form of alternative interpretations of the original case study that the case analysis did not cover.

• Kansas State University: Criticism and Critical Analysis
• Nova Southeastern University: Introduction to Case Study
• Hobart and William Smith Colleges: Writing a Critique (Critical Analysis)
• The University of Adelaide: Objective Language

A former art instructor, high school counselor and party planner, Christine Bartsch writes fashion, travel, interior design, education and entertainment content. Bartsch earned a Bachelor of Fine Arts in communications/psychology/fine arts from Wisconsin Lutheran College and a creative writing Master of Fine Arts from Spalding University. She's written scripts for film/television productions and worked as the senior writer at a video game company.

Organizing Your Social Sciences Research Assignments

• Annotated Bibliography
• Analyzing a Scholarly Journal Article
• Group Presentations
• Dealing with Nervousness
• Using Visual Aids
• Grading Someone Else's Paper
• Types of Structured Group Activities
• Group Project Survival Skills
• Leading a Class Discussion
• Multiple Book Review Essay
• Reviewing Collected Works
• Writing a Case Analysis Paper
• Writing a Case Study
• About Informed Consent
• Writing Field Notes
• Writing a Policy Memo
• Writing a Reflective Paper
• Writing a Research Proposal
• Generative AI and Writing
• Acknowledgments

A case study research paper examines a person, place, event, condition, phenomenon, or other type of subject of analysis in order to extrapolate  key themes and results that help predict future trends, illuminate previously hidden issues that can be applied to practice, and/or provide a means for understanding an important research problem with greater clarity. A case study research paper usually examines a single subject of analysis, but case study papers can also be designed as a comparative investigation that shows relationships between two or more subjects. The methods used to study a case can rest within a quantitative, qualitative, or mixed-method investigative paradigm.

Case Studies. Writing@CSU. Colorado State University; Mills, Albert J. , Gabrielle Durepos, and Eiden Wiebe, editors. Encyclopedia of Case Study Research . Thousand Oaks, CA: SAGE Publications, 2010 ; “What is a Case Study?” In Swanborn, Peter G. Case Study Research: What, Why and How? London: SAGE, 2010.

How to Approach Writing a Case Study Research Paper

General information about how to choose a topic to investigate can be found under the " Choosing a Research Problem " tab in the Organizing Your Social Sciences Research Paper writing guide. Review this page because it may help you identify a subject of analysis that can be investigated using a case study design.

However, identifying a case to investigate involves more than choosing the research problem . A case study encompasses a problem contextualized around the application of in-depth analysis, interpretation, and discussion, often resulting in specific recommendations for action or for improving existing conditions. As Seawright and Gerring note, practical considerations such as time and access to information can influence case selection, but these issues should not be the sole factors used in describing the methodological justification for identifying a particular case to study. Given this, selecting a case includes considering the following:

• The case represents an unusual or atypical example of a research problem that requires more in-depth analysis? Cases often represent a topic that rests on the fringes of prior investigations because the case may provide new ways of understanding the research problem. For example, if the research problem is to identify strategies to improve policies that support girl's access to secondary education in predominantly Muslim nations, you could consider using Azerbaijan as a case study rather than selecting a more obvious nation in the Middle East. Doing so may reveal important new insights into recommending how governments in other predominantly Muslim nations can formulate policies that support improved access to education for girls.
• The case provides important insight or illuminate a previously hidden problem? In-depth analysis of a case can be based on the hypothesis that the case study will reveal trends or issues that have not been exposed in prior research or will reveal new and important implications for practice. For example, anecdotal evidence may suggest drug use among homeless veterans is related to their patterns of travel throughout the day. Assuming prior studies have not looked at individual travel choices as a way to study access to illicit drug use, a case study that observes a homeless veteran could reveal how issues of personal mobility choices facilitate regular access to illicit drugs. Note that it is important to conduct a thorough literature review to ensure that your assumption about the need to reveal new insights or previously hidden problems is valid and evidence-based.
• The case challenges and offers a counter-point to prevailing assumptions? Over time, research on any given topic can fall into a trap of developing assumptions based on outdated studies that are still applied to new or changing conditions or the idea that something should simply be accepted as "common sense," even though the issue has not been thoroughly tested in current practice. A case study analysis may offer an opportunity to gather evidence that challenges prevailing assumptions about a research problem and provide a new set of recommendations applied to practice that have not been tested previously. For example, perhaps there has been a long practice among scholars to apply a particular theory in explaining the relationship between two subjects of analysis. Your case could challenge this assumption by applying an innovative theoretical framework [perhaps borrowed from another discipline] to explore whether this approach offers new ways of understanding the research problem. Taking a contrarian stance is one of the most important ways that new knowledge and understanding develops from existing literature.
• The case provides an opportunity to pursue action leading to the resolution of a problem? Another way to think about choosing a case to study is to consider how the results from investigating a particular case may result in findings that reveal ways in which to resolve an existing or emerging problem. For example, studying the case of an unforeseen incident, such as a fatal accident at a railroad crossing, can reveal hidden issues that could be applied to preventative measures that contribute to reducing the chance of accidents in the future. In this example, a case study investigating the accident could lead to a better understanding of where to strategically locate additional signals at other railroad crossings so as to better warn drivers of an approaching train, particularly when visibility is hindered by heavy rain, fog, or at night.
• The case offers a new direction in future research? A case study can be used as a tool for an exploratory investigation that highlights the need for further research about the problem. A case can be used when there are few studies that help predict an outcome or that establish a clear understanding about how best to proceed in addressing a problem. For example, after conducting a thorough literature review [very important!], you discover that little research exists showing the ways in which women contribute to promoting water conservation in rural communities of east central Africa. A case study of how women contribute to saving water in a rural village of Uganda can lay the foundation for understanding the need for more thorough research that documents how women in their roles as cooks and family caregivers think about water as a valuable resource within their community. This example of a case study could also point to the need for scholars to build new theoretical frameworks around the topic [e.g., applying feminist theories of work and family to the issue of water conservation].

Eisenhardt, Kathleen M. “Building Theories from Case Study Research.” Academy of Management Review 14 (October 1989): 532-550; Emmel, Nick. Sampling and Choosing Cases in Qualitative Research: A Realist Approach . Thousand Oaks, CA: SAGE Publications, 2013; Gerring, John. “What Is a Case Study and What Is It Good for?” American Political Science Review 98 (May 2004): 341-354; Mills, Albert J. , Gabrielle Durepos, and Eiden Wiebe, editors. Encyclopedia of Case Study Research . Thousand Oaks, CA: SAGE Publications, 2010; Seawright, Jason and John Gerring. "Case Selection Techniques in Case Study Research." Political Research Quarterly 61 (June 2008): 294-308.

Structure and Writing Style

The purpose of a paper in the social sciences designed around a case study is to thoroughly investigate a subject of analysis in order to reveal a new understanding about the research problem and, in so doing, contributing new knowledge to what is already known from previous studies. In applied social sciences disciplines [e.g., education, social work, public administration, etc.], case studies may also be used to reveal best practices, highlight key programs, or investigate interesting aspects of professional work.

In general, the structure of a case study research paper is not all that different from a standard college-level research paper. However, there are subtle differences you should be aware of. Here are the key elements to organizing and writing a case study research paper.

I.  Introduction

As with any research paper, your introduction should serve as a roadmap for your readers to ascertain the scope and purpose of your study . The introduction to a case study research paper, however, should not only describe the research problem and its significance, but you should also succinctly describe why the case is being used and how it relates to addressing the problem. The two elements should be linked. With this in mind, a good introduction answers these four questions:

• What is being studied? Describe the research problem and describe the subject of analysis [the case] you have chosen to address the problem. Explain how they are linked and what elements of the case will help to expand knowledge and understanding about the problem.
• Why is this topic important to investigate? Describe the significance of the research problem and state why a case study design and the subject of analysis that the paper is designed around is appropriate in addressing the problem.
• What did we know about this topic before I did this study? Provide background that helps lead the reader into the more in-depth literature review to follow. If applicable, summarize prior case study research applied to the research problem and why it fails to adequately address the problem. Describe why your case will be useful. If no prior case studies have been used to address the research problem, explain why you have selected this subject of analysis.
• How will this study advance new knowledge or new ways of understanding? Explain why your case study will be suitable in helping to expand knowledge and understanding about the research problem.

Each of these questions should be addressed in no more than a few paragraphs. Exceptions to this can be when you are addressing a complex research problem or subject of analysis that requires more in-depth background information.

II.  Literature Review

The literature review for a case study research paper is generally structured the same as it is for any college-level research paper. The difference, however, is that the literature review is focused on providing background information and  enabling historical interpretation of the subject of analysis in relation to the research problem the case is intended to address . This includes synthesizing studies that help to:

• Place relevant works in the context of their contribution to understanding the case study being investigated . This would involve summarizing studies that have used a similar subject of analysis to investigate the research problem. If there is literature using the same or a very similar case to study, you need to explain why duplicating past research is important [e.g., conditions have changed; prior studies were conducted long ago, etc.].
• Describe the relationship each work has to the others under consideration that informs the reader why this case is applicable . Your literature review should include a description of any works that support using the case to investigate the research problem and the underlying research questions.
• Identify new ways to interpret prior research using the case study . If applicable, review any research that has examined the research problem using a different research design. Explain how your use of a case study design may reveal new knowledge or a new perspective or that can redirect research in an important new direction.
• Resolve conflicts amongst seemingly contradictory previous studies . This refers to synthesizing any literature that points to unresolved issues of concern about the research problem and describing how the subject of analysis that forms the case study can help resolve these existing contradictions.
• Point the way in fulfilling a need for additional research . Your review should examine any literature that lays a foundation for understanding why your case study design and the subject of analysis around which you have designed your study may reveal a new way of approaching the research problem or offer a perspective that points to the need for additional research.
• Expose any gaps that exist in the literature that the case study could help to fill . Summarize any literature that not only shows how your subject of analysis contributes to understanding the research problem, but how your case contributes to a new way of understanding the problem that prior research has failed to do.
• Locate your own research within the context of existing literature [very important!] . Collectively, your literature review should always place your case study within the larger domain of prior research about the problem. The overarching purpose of reviewing pertinent literature in a case study paper is to demonstrate that you have thoroughly identified and synthesized prior studies in relation to explaining the relevance of the case in addressing the research problem.

III.  Method

In this section, you explain why you selected a particular case [i.e., subject of analysis] and the strategy you used to identify and ultimately decide that your case was appropriate in addressing the research problem. The way you describe the methods used varies depending on the type of subject of analysis that constitutes your case study.

If your subject of analysis is an incident or event . In the social and behavioral sciences, the event or incident that represents the case to be studied is usually bounded by time and place, with a clear beginning and end and with an identifiable location or position relative to its surroundings. The subject of analysis can be a rare or critical event or it can focus on a typical or regular event. The purpose of studying a rare event is to illuminate new ways of thinking about the broader research problem or to test a hypothesis. Critical incident case studies must describe the method by which you identified the event and explain the process by which you determined the validity of this case to inform broader perspectives about the research problem or to reveal new findings. However, the event does not have to be a rare or uniquely significant to support new thinking about the research problem or to challenge an existing hypothesis. For example, Walo, Bull, and Breen conducted a case study to identify and evaluate the direct and indirect economic benefits and costs of a local sports event in the City of Lismore, New South Wales, Australia. The purpose of their study was to provide new insights from measuring the impact of a typical local sports event that prior studies could not measure well because they focused on large "mega-events." Whether the event is rare or not, the methods section should include an explanation of the following characteristics of the event: a) when did it take place; b) what were the underlying circumstances leading to the event; and, c) what were the consequences of the event in relation to the research problem.

If your subject of analysis is a person. Explain why you selected this particular individual to be studied and describe what experiences they have had that provide an opportunity to advance new understandings about the research problem. Mention any background about this person which might help the reader understand the significance of their experiences that make them worthy of study. This includes describing the relationships this person has had with other people, institutions, and/or events that support using them as the subject for a case study research paper. It is particularly important to differentiate the person as the subject of analysis from others and to succinctly explain how the person relates to examining the research problem [e.g., why is one politician in a particular local election used to show an increase in voter turnout from any other candidate running in the election]. Note that these issues apply to a specific group of people used as a case study unit of analysis [e.g., a classroom of students].

If your subject of analysis is a place. In general, a case study that investigates a place suggests a subject of analysis that is unique or special in some way and that this uniqueness can be used to build new understanding or knowledge about the research problem. A case study of a place must not only describe its various attributes relevant to the research problem [e.g., physical, social, historical, cultural, economic, political], but you must state the method by which you determined that this place will illuminate new understandings about the research problem. It is also important to articulate why a particular place as the case for study is being used if similar places also exist [i.e., if you are studying patterns of homeless encampments of veterans in open spaces, explain why you are studying Echo Park in Los Angeles rather than Griffith Park?]. If applicable, describe what type of human activity involving this place makes it a good choice to study [e.g., prior research suggests Echo Park has more homeless veterans].

If your subject of analysis is a phenomenon. A phenomenon refers to a fact, occurrence, or circumstance that can be studied or observed but with the cause or explanation to be in question. In this sense, a phenomenon that forms your subject of analysis can encompass anything that can be observed or presumed to exist but is not fully understood. In the social and behavioral sciences, the case usually focuses on human interaction within a complex physical, social, economic, cultural, or political system. For example, the phenomenon could be the observation that many vehicles used by ISIS fighters are small trucks with English language advertisements on them. The research problem could be that ISIS fighters are difficult to combat because they are highly mobile. The research questions could be how and by what means are these vehicles used by ISIS being supplied to the militants and how might supply lines to these vehicles be cut off? How might knowing the suppliers of these trucks reveal larger networks of collaborators and financial support? A case study of a phenomenon most often encompasses an in-depth analysis of a cause and effect that is grounded in an interactive relationship between people and their environment in some way.

NOTE:   The choice of the case or set of cases to study cannot appear random. Evidence that supports the method by which you identified and chose your subject of analysis should clearly support investigation of the research problem and linked to key findings from your literature review. Be sure to cite any studies that helped you determine that the case you chose was appropriate for examining the problem.

IV.  Discussion

The main elements of your discussion section are generally the same as any research paper, but centered around interpreting and drawing conclusions about the key findings from your analysis of the case study. Note that a general social sciences research paper may contain a separate section to report findings. However, in a paper designed around a case study, it is common to combine a description of the results with the discussion about their implications. The objectives of your discussion section should include the following:

Reiterate the Research Problem/State the Major Findings Briefly reiterate the research problem you are investigating and explain why the subject of analysis around which you designed the case study were used. You should then describe the findings revealed from your study of the case using direct, declarative, and succinct proclamation of the study results. Highlight any findings that were unexpected or especially profound.

Explain the Meaning of the Findings and Why They are Important Systematically explain the meaning of your case study findings and why you believe they are important. Begin this part of the section by repeating what you consider to be your most important or surprising finding first, then systematically review each finding. Be sure to thoroughly extrapolate what your analysis of the case can tell the reader about situations or conditions beyond the actual case that was studied while, at the same time, being careful not to misconstrue or conflate a finding that undermines the external validity of your conclusions.

Relate the Findings to Similar Studies No study in the social sciences is so novel or possesses such a restricted focus that it has absolutely no relation to previously published research. The discussion section should relate your case study results to those found in other studies, particularly if questions raised from prior studies served as the motivation for choosing your subject of analysis. This is important because comparing and contrasting the findings of other studies helps support the overall importance of your results and it highlights how and in what ways your case study design and the subject of analysis differs from prior research about the topic.

Consider Alternative Explanations of the Findings Remember that the purpose of social science research is to discover and not to prove. When writing the discussion section, you should carefully consider all possible explanations revealed by the case study results, rather than just those that fit your hypothesis or prior assumptions and biases. Be alert to what the in-depth analysis of the case may reveal about the research problem, including offering a contrarian perspective to what scholars have stated in prior research if that is how the findings can be interpreted from your case.

Acknowledge the Study's Limitations You can state the study's limitations in the conclusion section of your paper but describing the limitations of your subject of analysis in the discussion section provides an opportunity to identify the limitations and explain why they are not significant. This part of the discussion section should also note any unanswered questions or issues your case study could not address. More detailed information about how to document any limitations to your research can be found here .

Suggest Areas for Further Research Although your case study may offer important insights about the research problem, there are likely additional questions related to the problem that remain unanswered or findings that unexpectedly revealed themselves as a result of your in-depth analysis of the case. Be sure that the recommendations for further research are linked to the research problem and that you explain why your recommendations are valid in other contexts and based on the original assumptions of your study.

V.  Conclusion

As with any research paper, you should summarize your conclusion in clear, simple language; emphasize how the findings from your case study differs from or supports prior research and why. Do not simply reiterate the discussion section. Provide a synthesis of key findings presented in the paper to show how these converge to address the research problem. If you haven't already done so in the discussion section, be sure to document the limitations of your case study and any need for further research.

The function of your paper's conclusion is to: 1) reiterate the main argument supported by the findings from your case study; 2) state clearly the context, background, and necessity of pursuing the research problem using a case study design in relation to an issue, controversy, or a gap found from reviewing the literature; and, 3) provide a place to persuasively and succinctly restate the significance of your research problem, given that the reader has now been presented with in-depth information about the topic.

Consider the following points to help ensure your conclusion is appropriate:

• If the argument or purpose of your paper is complex, you may need to summarize these points for your reader.
• If prior to your conclusion, you have not yet explained the significance of your findings or if you are proceeding inductively, use the conclusion of your paper to describe your main points and explain their significance.
• Move from a detailed to a general level of consideration of the case study's findings that returns the topic to the context provided by the introduction or within a new context that emerges from your case study findings.

Note that, depending on the discipline you are writing in or the preferences of your professor, the concluding paragraph may contain your final reflections on the evidence presented as it applies to practice or on the essay's central research problem. However, the nature of being introspective about the subject of analysis you have investigated will depend on whether you are explicitly asked to express your observations in this way.

Problems to Avoid

Overgeneralization One of the goals of a case study is to lay a foundation for understanding broader trends and issues applied to similar circumstances. However, be careful when drawing conclusions from your case study. They must be evidence-based and grounded in the results of the study; otherwise, it is merely speculation. Looking at a prior example, it would be incorrect to state that a factor in improving girls access to education in Azerbaijan and the policy implications this may have for improving access in other Muslim nations is due to girls access to social media if there is no documentary evidence from your case study to indicate this. There may be anecdotal evidence that retention rates were better for girls who were engaged with social media, but this observation would only point to the need for further research and would not be a definitive finding if this was not a part of your original research agenda.

Failure to Document Limitations No case is going to reveal all that needs to be understood about a research problem. Therefore, just as you have to clearly state the limitations of a general research study , you must describe the specific limitations inherent in the subject of analysis. For example, the case of studying how women conceptualize the need for water conservation in a village in Uganda could have limited application in other cultural contexts or in areas where fresh water from rivers or lakes is plentiful and, therefore, conservation is understood more in terms of managing access rather than preserving access to a scarce resource.

Failure to Extrapolate All Possible Implications Just as you don't want to over-generalize from your case study findings, you also have to be thorough in the consideration of all possible outcomes or recommendations derived from your findings. If you do not, your reader may question the validity of your analysis, particularly if you failed to document an obvious outcome from your case study research. For example, in the case of studying the accident at the railroad crossing to evaluate where and what types of warning signals should be located, you failed to take into consideration speed limit signage as well as warning signals. When designing your case study, be sure you have thoroughly addressed all aspects of the problem and do not leave gaps in your analysis that leave the reader questioning the results.

Case Studies. Writing@CSU. Colorado State University; Gerring, John. Case Study Research: Principles and Practices . New York: Cambridge University Press, 2007; Merriam, Sharan B. Qualitative Research and Case Study Applications in Education . Rev. ed. San Francisco, CA: Jossey-Bass, 1998; Miller, Lisa L. “The Use of Case Studies in Law and Social Science Research.” Annual Review of Law and Social Science 14 (2018): TBD; Mills, Albert J., Gabrielle Durepos, and Eiden Wiebe, editors. Encyclopedia of Case Study Research . Thousand Oaks, CA: SAGE Publications, 2010; Putney, LeAnn Grogan. "Case Study." In Encyclopedia of Research Design , Neil J. Salkind, editor. (Thousand Oaks, CA: SAGE Publications, 2010), pp. 116-120; Simons, Helen. Case Study Research in Practice . London: SAGE Publications, 2009;  Kratochwill,  Thomas R. and Joel R. Levin, editors. Single-Case Research Design and Analysis: New Development for Psychology and Education .  Hilldsale, NJ: Lawrence Erlbaum Associates, 1992; Swanborn, Peter G. Case Study Research: What, Why and How? London : SAGE, 2010; Yin, Robert K. Case Study Research: Design and Methods . 6th edition. Los Angeles, CA, SAGE Publications, 2014; Walo, Maree, Adrian Bull, and Helen Breen. “Achieving Economic Benefits at Local Events: A Case Study of a Local Sports Event.” Festival Management and Event Tourism 4 (1996): 95-106.

Writing Tip

At Least Five Misconceptions about Case Study Research

Social science case studies are often perceived as limited in their ability to create new knowledge because they are not randomly selected and findings cannot be generalized to larger populations. Flyvbjerg examines five misunderstandings about case study research and systematically "corrects" each one. To quote, these are:

Misunderstanding 1 :  General, theoretical [context-independent] knowledge is more valuable than concrete, practical [context-dependent] knowledge. Misunderstanding 2 :  One cannot generalize on the basis of an individual case; therefore, the case study cannot contribute to scientific development. Misunderstanding 3 :  The case study is most useful for generating hypotheses; that is, in the first stage of a total research process, whereas other methods are more suitable for hypotheses testing and theory building. Misunderstanding 4 :  The case study contains a bias toward verification, that is, a tendency to confirm the researcher’s preconceived notions. Misunderstanding 5 :  It is often difficult to summarize and develop general propositions and theories on the basis of specific case studies [p. 221].

While writing your paper, think introspectively about how you addressed these misconceptions because to do so can help you strengthen the validity and reliability of your research by clarifying issues of case selection, the testing and challenging of existing assumptions, the interpretation of key findings, and the summation of case outcomes. Think of a case study research paper as a complete, in-depth narrative about the specific properties and key characteristics of your subject of analysis applied to the research problem.

Flyvbjerg, Bent. “Five Misunderstandings About Case-Study Research.” Qualitative Inquiry 12 (April 2006): 219-245.

• << Previous: Writing a Case Analysis Paper
• Next: Writing a Field Report >>
• Last Updated: Mar 6, 2024 1:00 PM
• URL: https://libguides.usc.edu/writingguide/assignments

How to write a case study — examples, templates, and tools

It’s a marketer’s job to communicate the effectiveness of a product or service to potential and current customers to convince them to buy and keep business moving. One of the best methods for doing this is to share success stories that are relatable to prospects and customers based on their pain points, experiences, and overall needs.

That’s where case studies come in. Case studies are an essential part of a content marketing plan. These in-depth stories of customer experiences are some of the most effective at demonstrating the value of a product or service. Yet many marketers don’t use them, whether because of their regimented formats or the process of customer involvement and approval.

A case study is a powerful tool for showcasing your hard work and the success your customer achieved. But writing a great case study can be difficult if you’ve never done it before or if it’s been a while. This guide will show you how to write an effective case study and provide real-world examples and templates that will keep readers engaged and support your business.

In this article, you’ll learn:

What is a case study?

How to write a case study, case study templates, case study examples, case study tools.

A case study is the detailed story of a customer’s experience with a product or service that demonstrates their success and often includes measurable outcomes. Case studies are used in a range of fields and for various reasons, from business to academic research. They’re especially impactful in marketing as brands work to convince and convert consumers with relatable, real-world stories of actual customer experiences.

The best case studies tell the story of a customer’s success, including the steps they took, the results they achieved, and the support they received from a brand along the way. To write a great case study, you need to:

• Celebrate the customer and make them — not a product or service — the star of the story.
• Craft the story with specific audiences or target segments in mind so that the story of one customer will be viewed as relatable and actionable for another customer.
• Write copy that is easy to read and engaging so that readers will gain the insights and messages intended.
• Follow a standardized format that includes all of the essentials a potential customer would find interesting and useful.
• Support all of the claims for success made in the story with data in the forms of hard numbers and customer statements.

Case studies are a type of review but more in depth, aiming to show — rather than just tell — the positive experiences that customers have with a brand. Notably, 89% of consumers read reviews before deciding to buy, and 79% view case study content as part of their purchasing process. When it comes to B2B sales, 52% of buyers rank case studies as an important part of their evaluation process.

Telling a brand story through the experience of a tried-and-true customer matters. The story is relatable to potential new customers as they imagine themselves in the shoes of the company or individual featured in the case study. Showcasing previous customers can help new ones see themselves engaging with your brand in the ways that are most meaningful to them.

Besides sharing the perspective of another customer, case studies stand out from other content marketing forms because they are based on evidence. Whether pulling from client testimonials or data-driven results, case studies tend to have more impact on new business because the story contains information that is both objective (data) and subjective (customer experience) — and the brand doesn’t sound too self-promotional.

Case studies are unique in that there’s a fairly standardized format for telling a customer’s story. But that doesn’t mean there isn’t room for creativity. It’s all about making sure that teams are clear on the goals for the case study — along with strategies for supporting content and channels — and understanding how the story fits within the framework of the company’s overall marketing goals.

Here are the basic steps to writing a good case study.

1. Identify your goal

Start by defining exactly who your case study will be designed to help. Case studies are about specific instances where a company works with a customer to achieve a goal. Identify which customers are likely to have these goals, as well as other needs the story should cover to appeal to them.

The answer is often found in one of the buyer personas that have been constructed as part of your larger marketing strategy. This can include anything from new leads generated by the marketing team to long-term customers that are being pressed for cross-sell opportunities. In all of these cases, demonstrating value through a relatable customer success story can be part of the solution to conversion.

2. Choose your client or subject

Who you highlight matters. Case studies tie brands together that might otherwise not cross paths. A writer will want to ensure that the highlighted customer aligns with their own company’s brand identity and offerings. Look for a customer with positive name recognition who has had great success with a product or service and is willing to be an advocate.

The client should also match up with the identified target audience. Whichever company or individual is selected should be a reflection of other potential customers who can see themselves in similar circumstances, having the same problems and possible solutions.

Some of the most compelling case studies feature customers who:

• Switch from one product or service to another while naming competitors that missed the mark.
• Experience measurable results that are relatable to others in a specific industry.
• Represent well-known brands and recognizable names that are likely to compel action.
• Advocate for a product or service as a champion and are well-versed in its advantages.

Whoever or whatever customer is selected, marketers must ensure they have the permission of the company involved before getting started. Some brands have strict review and approval procedures for any official marketing or promotional materials that include their name. Acquiring those approvals in advance will prevent any miscommunication or wasted effort if there is an issue with their legal or compliance teams.

3. Conduct research and compile data

Substantiating the claims made in a case study — either by the marketing team or customers themselves — adds validity to the story. To do this, include data and feedback from the client that defines what success looks like. This can be anything from demonstrating return on investment (ROI) to a specific metric the customer was striving to improve. Case studies should prove how an outcome was achieved and show tangible results that indicate to the customer that your solution is the right one.

This step could also include customer interviews. Make sure that the people being interviewed are key stakeholders in the purchase decision or deployment and use of the product or service that is being highlighted. Content writers should work off a set list of questions prepared in advance. It can be helpful to share these with the interviewees beforehand so they have time to consider and craft their responses. One of the best interview tactics to keep in mind is to ask questions where yes and no are not natural answers. This way, your subject will provide more open-ended responses that produce more meaningful content.

4. Choose the right format

There are a number of different ways to format a case study. Depending on what you hope to achieve, one style will be better than another. However, there are some common elements to include, such as:

• An engaging headline
• A subject and customer introduction
• The unique challenge or challenges the customer faced
• The solution the customer used to solve the problem
• The results achieved
• Data and statistics to back up claims of success
• A strong call to action (CTA) to engage with the vendor

It’s also important to note that while case studies are traditionally written as stories, they don’t have to be in a written format. Some companies choose to get more creative with their case studies and produce multimedia content, depending on their audience and objectives. Case study formats can include traditional print stories, interactive web or social content, data-heavy infographics, professionally shot videos, podcasts, and more.

5. Write your case study

We’ll go into more detail later about how exactly to write a case study, including templates and examples. Generally speaking, though, there are a few things to keep in mind when writing your case study.

• Be clear and concise. Readers want to get to the point of the story quickly and easily, and they’ll be looking to see themselves reflected in the story right from the start.
• Provide a big picture. Always make sure to explain who the client is, their goals, and how they achieved success in a short introduction to engage the reader.
• Construct a clear narrative. Stick to the story from the perspective of the customer and what they needed to solve instead of just listing product features or benefits.
• Leverage graphics. Incorporating infographics, charts, and sidebars can be a more engaging and eye-catching way to share key statistics and data in readable ways.
• Offer the right amount of detail. Most case studies are one or two pages with clear sections that a reader can skim to find the information most important to them.
• Include data to support claims. Show real results — both facts and figures and customer quotes — to demonstrate credibility and prove the solution works.

6. Promote your story

Marketers have a number of options for distribution of a freshly minted case study. Many brands choose to publish case studies on their website and post them on social media. This can help support SEO and organic content strategies while also boosting company credibility and trust as visitors see that other businesses have used the product or service.

Marketers are always looking for quality content they can use for lead generation. Consider offering a case study as gated content behind a form on a landing page or as an offer in an email message. One great way to do this is to summarize the content and tease the full story available for download after the user takes an action.

Sales teams can also leverage case studies, so be sure they are aware that the assets exist once they’re published. Especially when it comes to larger B2B sales, companies often ask for examples of similar customer challenges that have been solved.

Now that you’ve learned a bit about case studies and what they should include, you may be wondering how to start creating great customer story content. Here are a couple of templates you can use to structure your case study.

Template 1 — Challenge-solution-result format

• Start with an engaging title. This should be fewer than 70 characters long for SEO best practices. One of the best ways to approach the title is to include the customer’s name and a hint at the challenge they overcame in the end.
• Create an introduction. Lead with an explanation as to who the customer is, the need they had, and the opportunity they found with a specific product or solution. Writers can also suggest the success the customer experienced with the solution they chose.
• Present the challenge. This should be several paragraphs long and explain the problem the customer faced and the issues they were trying to solve. Details should tie into the company’s products and services naturally. This section needs to be the most relatable to the reader so they can picture themselves in a similar situation.
• Share the solution. Explain which product or service offered was the ideal fit for the customer and why. Feel free to delve into their experience setting up, purchasing, and onboarding the solution.
• Explain the results. Demonstrate the impact of the solution they chose by backing up their positive experience with data. Fill in with customer quotes and tangible, measurable results that show the effect of their choice.
• Ask for action. Include a CTA at the end of the case study that invites readers to reach out for more information, try a demo, or learn more — to nurture them further in the marketing pipeline. What you ask of the reader should tie directly into the goals that were established for the case study in the first place.

Template 2 — Data-driven format

• Start with an engaging title. Be sure to include a statistic or data point in the first 70 characters. Again, it’s best to include the customer’s name as part of the title.
• Create an overview. Share the customer’s background and a short version of the challenge they faced. Present the reason a particular product or service was chosen, and feel free to include quotes from the customer about their selection process.
• Present data point 1. Isolate the first metric that the customer used to define success and explain how the product or solution helped to achieve this goal. Provide data points and quotes to substantiate the claim that success was achieved.
• Present data point 2. Isolate the second metric that the customer used to define success and explain what the product or solution did to achieve this goal. Provide data points and quotes to substantiate the claim that success was achieved.
• Present data point 3. Isolate the final metric that the customer used to define success and explain what the product or solution did to achieve this goal. Provide data points and quotes to substantiate the claim that success was achieved.
• Summarize the results. Reiterate the fact that the customer was able to achieve success thanks to a specific product or service. Include quotes and statements that reflect customer satisfaction and suggest they plan to continue using the solution.
• Ask for action. Include a CTA at the end of the case study that asks readers to reach out for more information, try a demo, or learn more — to further nurture them in the marketing pipeline. Again, remember that this is where marketers can look to convert their content into action with the customer.

While templates are helpful, seeing a case study in action can also be a great way to learn. Here are some examples of how Adobe customers have experienced success.

Juniper Networks

One example is the Adobe and Juniper Networks case study , which puts the reader in the customer’s shoes. The beginning of the story quickly orients the reader so that they know exactly who the article is about and what they were trying to achieve. Solutions are outlined in a way that shows Adobe Experience Manager is the best choice and a natural fit for the customer. Along the way, quotes from the client are incorporated to help add validity to the statements. The results in the case study are conveyed with clear evidence of scale and volume using tangible data.

The story of Lenovo’s journey with Adobe is one that spans years of planning, implementation, and rollout. The Lenovo case study does a great job of consolidating all of this into a relatable journey that other enterprise organizations can see themselves taking, despite the project size. This case study also features descriptive headers and compelling visual elements that engage the reader and strengthen the content.

Tata Consulting

When it comes to using data to show customer results, this case study does an excellent job of conveying details and numbers in an easy-to-digest manner. Bullet points at the start break up the content while also helping the reader understand exactly what the case study will be about. Tata Consulting used Adobe to deliver elevated, engaging content experiences for a large telecommunications client of its own — an objective that’s relatable for a lot of companies.

Case studies are a vital tool for any marketing team as they enable you to demonstrate the value of your company’s products and services to others. They help marketers do their job and add credibility to a brand trying to promote its solutions by using the experiences and stories of real customers.

When you’re ready to get started with a case study:

• Think about a few goals you’d like to accomplish with your content.
• Make a list of successful clients that would be strong candidates for a case study.
• Reach out to the client to get their approval and conduct an interview.
• Gather the data to present an engaging and effective customer story.

Adobe can help

There are several Adobe products that can help you craft compelling case studies. Adobe Experience Platform helps you collect data and deliver great customer experiences across every channel. Once you’ve created your case studies, Experience Platform will help you deliver the right information to the right customer at the right time for maximum impact.

To learn more, watch the Adobe Experience Platform story .

Keep in mind that the best case studies are backed by data. That’s where Adobe Real-Time Customer Data Platform and Adobe Analytics come into play. With Real-Time CDP, you can gather the data you need to build a great case study and target specific customers to deliver the content to the right audience at the perfect moment.

Watch the Real-Time CDP overview video to learn more.

Finally, Adobe Analytics turns real-time data into real-time insights. It helps your business collect and synthesize data from multiple platforms to make more informed decisions and create the best case study possible.

Request a demo to learn more about Adobe Analytics.

https://business.adobe.com/blog/perspectives/b2b-ecommerce-10-case-studies-inspire-you

https://business.adobe.com/blog/basics/business-case

https://business.adobe.com/blog/basics/what-is-real-time-analytics

• Open access
• Published: 26 April 2024

Clinician and staff experiences with frustrated patients during an electronic health record transition: a qualitative case study

• Sherry L. Ball 1 ,
• Bo Kim 2 , 3 ,
• Sarah L. Cutrona 4 , 5 ,
• Brianne K. Molloy-Paolillo 4 ,
• Ellen Ahlness 6 ,
• Megan Moldestad 6 ,
• George Sayre 6 , 7 &
• Seppo T. Rinne 2 , 8  

BMC Health Services Research volume  24 , Article number:  535 ( 2024 ) Cite this article

Metrics details

Electronic health record (EHR) transitions are known to be highly disruptive, can drastically impact clinician and staff experiences, and may influence patients’ experiences using the electronic patient portal. Clinicians and staff can gain insights into patient experiences and be influenced by what they see and hear from patients. Through the lens of an emergency preparedness framework, we examined clinician and staff reactions to and perceptions of their patients’ experiences with the portal during an EHR transition at the Department of Veterans Affairs (VA).

This qualitative case study was situated within a larger multi-methods evaluation of the EHR transition. We conducted a total of 122 interviews with 30 clinicians and staff across disciplines at the initial VA EHR transition site before, immediately after, and up to 12 months after go-live (September 2020-November 2021). Interview transcripts were coded using a priori and emergent codes. The coded text segments relevant to patient experience and clinician interactions with patients were extracted and analyzed to identify themes. For each theme, recommendations were defined based on each stage of an emergency preparedness framework (mitigate, prepare, respond, recover).

In post-go-live interviews participants expressed concerns about the reliability of communicating with their patients via secure messaging within the new EHR portal. Participants felt ill-equipped to field patients’ questions and frustrations navigating the new portal. Participants learned that patients experienced difficulties learning to use and accessing the portal; when unsuccessful, some had difficulties obtaining medication refills via the portal and used the call center as an alternative. However, long telephone wait times provoked patients to walk into the clinic for care, often frustrated and without an appointment. Patients needing increased in-person attention heightened participants’ daily workload and their concern for patients’ well-being. Recommendations for each theme fit within a stage of the emergency preparedness framework.

Conclusions

Application of an emergency preparedness framework to EHR transitions could help address the concerns raised by the participants, (1) mitigating disruptions by identifying at-risk patients before the transition, (2) preparing end-users by disseminating patient-centered informational resources, (3) responding by building capacity for disrupted services, and (4) recovering by monitoring integrity of the new portal function.

Peer Review reports

Electronic health record (EHR) transitions present significant challenges for healthcare clinicians and staff. These transitions require adjustments in care delivery and may threaten care quality and value. It is critical that healthcare organizations undergoing these changes learn from others who have undergone similar transitions [ 1 , 2 ]. However, the current literature lacks adequate guidance on navigating EHR transitions, especially as they relate to how clinicians and staff interact with patients [ 3 ].

Embedded within EHRs, patient portals facilitate complete, accurate, timely, and unambiguous exchange of information between patients and healthcare workers [ 4 , 5 ]. These portals have become indispensable for completing routine out-of-office-visit tasks, such as medication refills, communicating laboratory results, and addressing patient questions [ 6 ]. In 2003, the VA launched their version of a patient portal, myHealtheVet [ 7 ] and by 2017 69% of Veterans enrolled in healthcare at the VA had registered to access the patient portal [ 8 ]. Similar to other electronic portals, this system allows Veterans to review test results, see upcoming appointments, and communicate privately and securely with their healthcare providers.

EHR transitions can introduce disruptions to patient portal communication that may compromise portal reliability, impacting patient and clinician satisfaction, patients’ active involvement in self-management, and ultimately health outcomes [ 9 ]. During an EHR transition, patients can expect reductions in access to care even when clinician capacity and IT support are increased. Patients will likely need for more assistance navigating the patient portal including and using the portal to communicate with their providers [ 10 ]. Staff must be prepared and understand how the changes in the EHR will affect patients and safeguards must be in place to monitor systems for potential risks to patient safety. Building the capacity to respond to emerging system glitches and identified changes must be included in any transition plan. Although portal disruptions are likely to occur when a new EHR is implemented, we know little about how these disruptions impact healthcare workers’ interactions and care delivery to patients [ 11 , 12 ].

Due to an urgency to raise awareness and promote resolution of these patient portal issues,, we utilized existing data from the first EHR transition site for the Department of Veterans Affairs (VA)’s enterprise-wide transition. We focused on end users’ responses to the question “How Veterans were affected by the transition?”. We used qualitative methods to begin to understand how provider and patient interactions were affected during and by the EHR transition. We explored the impact of the EHR transition on patients through healthcare workers’ vicarious and direct experiences with patients. Due to the high level of disruption in care delivery we draw on insights from an emergency preparedness framework [ 13 ] to generate a set of recommendations to improve healthcare workers’ experiences during EHR transitions. The emergency preparedness framework includes 4 phases of an iterative cycle that include: (1) building capacity to mitigate issues, (2) preparing for the inevitable onset of issues, (3) responding to issues as they emerge, and (4) strategies to recover from any damage incurred.

In early 2020, the VA embarked on an EHR transition from a homegrown, legacy EHR system, developed by VA clinicians and used since the 1990s, to a new commercial system by the Oracle-Cerner Corporation. The primary objectives of this transition were to standardize care and improve interoperability between VA Medical Centers nationwide and the Department of Defense (DoD). Spanning over a decade, this transition plan is scheduled to roll out to all VA medical centers and outpatient clinics.

In this manuscript, we present data from the Mann-Grandstaff VA Medical Center in Spokane, WA, VA’s first EHR transition site. The study uses qualitative methods with clinician and staff interviews as part of a larger multi-method evaluation of the EHR transition. Our overarching goal is to identify and share recommendations to improve VA’s EHR transition efforts; rather than be guided by a theoretical framework our study design including the interview guides [ 14 , 15 ] were based primarily on what was being experienced. An experienced team of ten qualitative methodologists and analysts conducted the study.

This evaluation was designated as non-research/quality improvement work by the VA Bedford Healthcare System Institutional Review Board deeming it exempt from needing an informed consent. Study materials, including interview guides with verbal consent procedures, were reviewed and approved by labor unions and by the VA Bedford Healthcare System Institutional Review Board; all methods were carried out in accordance with local and national VA guidelines and regulations.

Interview guides and an outline of the data collection plans were reviewed and approved by relevant national unions before beginning recruitment.

Recruitment

Recruitment began in July 2020, before the first site implemented the new EHR. Prior to collecting data, we met with site leadership to get buy-in and support for the study, understand local context, determine how the site was approaching the transition, and to obtain the names of clinicians and staff for potential interviews. All potential participants were invited by email to participate in a one-hour voluntary interview conducted on Microsoft Teams® about their experiences with this transition; we used snowball sampling during interviews to expand the pool of interviewees. Verbal permission for audio recording of interviews was obtained immediately prior to the interview. Interview participants were informed that they could skip any questions, pause or stop the recording, and stop the interview at any time and were invited to ask questions before beginning the interview.

Most participants were interviewed at multiple timepoints; these included pre-implementation interviews, brief check-ins, and post-implementation interviews (Table  1 ). At the end of the pre-implementation interview, participants were invited to participate in 3–4 additional, shorter (15–20 min), check-in interviews where information about any changes in the transition process, context, or experience could be discussed. Most initial interviewees, in addition to three new participants, participated in post-implementation interviews (35–60 min; approximately 2–3 months and 10–12 months after the implementation) to reflect on the entire transition process.

Data collection

Experienced qualitative interviewers included PhD trained qualitative methodologist and masters level qualitative analysts (JB, SB, AC, EK, MM, GS) conducted individual interviews with clinicians and staff, aligning to a semi-structured interview guide with follow-up probes using the participant’s words to elicit rich responses grounded in the data [ 16 ]. The guide was designed to inform ongoing efforts to improve the rollout of the new EHR. Six main categories were covered in our interview guides, including (1) attitudes toward the new software, (2) information communicated about the transition, (3) training and education, (4) resources, (5) prior experience with EHRs, and (6) prior experiences with EHR transitions. After piloting the interview guide with a clinician, initial interviews were completed between September and October 2020 and averaged  ∼  45 min in duration. Two-month and one-year post-implementation interview guides included an additional question, “Has the Cerner transition affected Vets?”; data presented here largely draw from responses to this question. Check-ins (October 2020– December 2020) took  ∼  15 min; two-month post-implementation interviews (December 2020– January 2021) and one-year post-implementation interviews (October 2020 - November 2021) took  ∼  45 min. Audio recordings of all interviews were professionally transcribed. To ensure consistency and relationship building, participants were scheduled with the same interviewer for the initial and subsequent interviews whenever feasible (i.e., check-ins and post-implementation interviews). Immediately following each interview, interviewers completed a debrief form where highlights and general reflections were noted.

Throughout the data collection process, interviewers met weekly with the entire qualitative team and the project principal investigators to discuss the recruitment process, interview guide development, and reflections on data collection. To provide timely feedback to leadership within the VA, a matrix analysis [ 17 ] was conducted concurrently with data collection using the following domains: training, roles, barriers, and facilitators. Based on these domains, the team developed categories and subcategories, which formed the foundation of an extensive codebook.

Data analysis

All interviewers also coded the data. We used inductive and deductive content analysis [ 18 ]. Interview transcripts were coded in ATLAS.ti qualitative data analysis software (version 9). A priori codes and categories (based on the overall larger project aims and interview guide questions) and emergent codes and categories were developed to capture concepts that did not fit existing codes or categories [ 18 ]. Codes related to patient experience and clinician interactions with patients were extracted and analyzed using qualitative content analysis to identify themes [ 18 ]. Themes were organized according to their fit within the discrete stages of an emergency preparedness framework to generate recommendations for future rollout. In total, we examined data from 111 interviews with 24 VA clinicians and staff (excluding the initial 11 stakeholder meetings (from the 122 total interviews) that were primarily for stakeholder engagement). We focused on participants’ responses related to their experiences interacting with patients during the EHR transition.

Exemplar quotes primarily came from participants’ responses to the question, “Has the Cerner transition affected Vets?” and addressed issues stemming from use of the patient portal. This included both clinicians’ direct experiences with the portal and indirect experiences when they heard from patients about disruptions when using the portal. We identified four themes related to clinicians’ and staff members’ reported experiences: (1) stress associated with the unreliability of routine portal functions and inaccurate migrated information; (2) concern about patients’ ability to learn to use a new portal (especially older patients and special populations); (3) frustration with apparent inadequate dissemination of patient informational materials along with their own lack of time and resources to educate patients on use of the new portal; and (4) burden of additional tasks on top of their daily workload when patients needed increased in-person attention due to issues with the portal.

Stress associated with the unreliability of routine portal functions and inaccurate migrated information

One participant described the portal changes as, “It’s our biggest stress, it’s the patients’ biggest stress… the vets are definitely frustrated; the clinicians are; so I would hope that would mean that behind the scenes somebody is working on it” (P5, check-in).

Participants expressed significant frustration when they encountered veterans who were suddenly unable to communicate with them using routine secure messaging. These experiences left them wondering whether messages sent to patients were received.

Those that use our secure messaging, which has now changed to My VA Health, or whatever it’s called, [have] difficulty navigating that. Some are able to get in and send the message. When we reply to them, they may or may not get the reply. Which I’ve actually asked one of our patients, ‘Did you get the reply that we took care of this?’ And he was like, ‘No, I did not (P11, 2-months post)

Participants learned that some patients were unable to send secure messages to their care team because the portal contained inaccurate or outdated appointment and primary site information.

I’ve heard people say that the appointments aren’t accurate in there… veterans who have said, ‘yeah, it shows I’m registered,’ and when they go into the new messaging system, it says they are part of a VA that they haven’t gone to in years, and that’s the only area they can message to, they can’t message to the [site] VA, even though that’s where they’ve actively being seen for a while now. (P20, 2-months post)

After the EHR transition, participants noted that obtaining medications through the portal, which was once a routine task, became unreliable. They expressed concern around patients’ ability to obtain their medications through the portal, primarily due to challenges with portal usability and incomplete migration of medication lists from the former to the new EHR.

I think it’s been negative, unfortunately. I try to stay optimistic when I talk to [patients], but they all seem to be all having continued difficulty with their medications, trying to properly reorder and get medications seems to still be a real hassle for them. (P17, one-year post) …the medications, their med list just didn’t transfer over into that list [preventing their ability to refill their medications]. (P13, 2-months post)

Concern about patients’ ability to learn to use a new portal

Clinicians and staff expressed concerns around veterans’ ability to access, learn, and navigate a new portal system. Clinicians noted that even veterans who were adept at using the prior electronic portal or other technologies also faced difficulties using the new portal.

They can’t figure out [the new portal], 99% of them that used to use our [old] portal, the electronic secure messaging or emailing between the team, they just can’t use [the new one]. It’s not functioning. (P13, one-year post) Apparently, there’s a link they have to click on to make the new format work for them, and that’s been confusing for them. But I still am having a lot of them tell me, I had somebody recently, who’s very tech savvy, and he couldn’t figure it out, just how to message us. I know they’re still really struggling with that. (P5, 2-months post) And it does seem like the My Vet [my VA Health, new portal], that used to be MyHealtheVet [prior portal], logging on and getting onto that still remains really challenging for a large number of veterans. Like they’re still just unable to do it. So, I do think that, I mean I want to say that there’s positive things, but really, I struggle (P17, one-year post)

Participants recognized difficulties with the new system and expressed empathy for the veterans struggling to access the portal.

I think that a lot of us, individually, that work here, I think we have more compassion for our veterans, because they’re coming in and they can’t even get onto their portal website. (P24, one-year post)

Participants acknowledged that learning a new system may be especially difficult for older veterans or those with less technology experience.

But, you know, veterans, the general population of them are older, in general. So, their technologic skills are limited, and they got used to a system and now they have to change to a new one. (P13, 2-months post) So, for our more elderly veterans who barely turn on the computer, they’re not getting to this new portal. (P8, check in) And you know, I do keep in mind that this is a group of people who aren’t always technologically advanced, so small things, when it’s not normal to them, stymie them.(P13, one-year post)

Concerns were heightened for veterans who were more dependent on the portal as a key element in their care due to specific challenges. One participant pointed out that there may be populations of patients with special circumstances who depend more heavily on the prior portal, MyHealtheVet.

I have veterans from [specific region], that’s the way they communicate. Hearing impaired people can’t hear on the phone, the robocall thing, it doesn’t work, so they use MyHealtheVet. Well, if that goes away, how is that being communicated to the veteran? Ok? (P18, Check-in)

Frustration with inadequate dissemination of information to veterans about EHR transition and use of new portal

Participants were concerned about poor information dissemination to patients about how to access the new portal. During medical encounters, participants often heard from patients about their frustrations accessing the new portal. Participants noted that they could only give their patients a phone number to call for help using the new system but otherwise lacked the knowledge and the time to help them resolve new portal issues. Some clinicians specifically mentioned feeling ill-equipped to handle their patients’ needs for assistance with the new portal. These experiences exacerbated clinician stress during the transition.

Our veterans were using the MyHealtheVet messaging portal, and when our new system went up, it transitioned to My VA Health, but that wasn’t really communicated to the veterans very well. So, what happened was they would go into their MyHealtheVet like they had been doing for all of these years, to go in and request their medications, and when they pulled it up it’d show that they were assigned to a clinician in [a different state], that they have no active medications. Everything was just messed up. And they didn’t know why because there was no alert or notification that things would be changing. (P8, check in) I field all-day frustration from the veterans. And I love my job, I’m not leaving here even as frustrated as I am, because I’m here for them, not to, I’m here to serve the veterans and I have to advocate for them, and I know it will get better, it can’t stay like this. But I constantly field their frustrations.… So, I give them the 1-800 number to a Cerner help desk that helps with that, and I’ve had multiple [instances of] feedback that it didn’t help. (P13, one-year post) And [the patients are] frequently asking me things about their medication [within the portal], when, you know, I can’t help them with that. So, I have to send them back up to the front desk to try to figure out their medications. (P17, one-year post)

Veteran frustration and the burden of additional tasks due to issues with the portal

Clinicians reported that veterans expressed frustration with alternatives to the portal, including long call center wait times. Some veterans chose to walk into the clinic without an appointment rather than wait on the phone. Clinicians noted an increase in walk-ins by frustrated veterans, which placed added workload on clinics that were not staffed to handle the increase in walk-ins.

It’s been kind of clunky also with trying to get that [new portal] transitioned. And then that’s created more walk-ins here, because one, the vets get frustrated with the phone part of it, and then MyHealtheVet (prior portal) not [working], so they end up walking [into the clinic without an appointment]. (P19, check-in) In terms of messages, they can’t necessarily find the clinician they want to message. We had a veteran who came in recently who wanted to talk to their Rheumatologist, and it’s like, yeah, I typed in their name, and nothing came up. So, they have to try calling or coming in. (P20, 2-months post)

In summary, participants described the new patient portal as a source of stress for both themselves and their patients.

In addition to their own direct experience using a new EHR to communicate with their patients, clinicians and staff can be affected by perceptions of their patients’ experiences during an EHR transition [ 19 ]. At this first VA site to transition to the new EHR, clinicians and staff shared their concerns about their patients’ experiences using the portal. They were particularly troubled by unreliability of the secure messaging system and challenges patients faced learning to use the new system without proper instruction. Moreover, clinicians were alarmed to hear about patients having to make in-person visits– especially unplanned (i.e., walk in) ones– due to challenges with the new portal. Each of these issues needs to be addressed to ensure veteran satisfaction. However, the only solution participants could offer to frustrated patients was the telephone number to the help desk, leaving them with no clear knowledge of a solution strategy or a timeline for resolution of the issues.

We propose applying emergency preparedness actions to future EHR rollouts: mitigate, prepare, respond, and recover (Fig.  1 ) [ 13 ]. By applying these actions, patient portal disruptions may be alleviated and patients’ communication with their clinicians and access to care can be maintained. For example, issues stemming from a disruption in the portal may be mitigated by first identifying and understanding which patients typically use the portal and how they use it. Sites can use this information to prepare for the transition by disseminating instructional materials to staff and patients on how to access the new portal, targeting the most common and critical portal uses. Sites can respond to any expected and emerging portal disruptions by increasing access to alternative mechanisms for tasks disrupted by and typically completed within the portal. After the transition, recovery can begin by testing and demonstrating the accuracy and reliability of functions in the new portal. These actions directly address reported clinician concerns and can help maintain patient-clinician communication, and access to care.

The emergency preparedness framework was applied. This framework includes 4 actions: (1) mitigate, (2) prepare, (3) respond, and (4) recover. These actions can be repeated. Recommendations for how each action (1–4) can be applied to a portal transition are included in each blue quadrant of the circle

Sites could mitigate issues by first understanding which patients will be most affected by the transition, such as those who rely heavily on secure messaging. Reliable use of secure messaging within the VA facilitates positive patient-clinician relationships by providing a mechanism for efficient between-visit communication [ 20 , 21 , 22 , 23 ]. During the EHR transition, clinicians and staff became concerned about the well-being of patients from whom they weren’t receiving messages and those who depended on the portal to complete certain tasks. Since secure messaging is often initiated by patients to clinicians [ 23 ], clinicians will likely be unaware that messages are being missed. Understanding how and which patients currently use the portal and anticipating potential portal needs is a first step toward mitigating potential issues.

Despite efforts to inform Veterans of the EHR transition and patient portal [ 24 ] including information sent to a Veteran by email, direct mail, postings on VA websites, and a town hall, our findings agree with those of Fix and colleagues [ 10 ] and suggest that many Veterans were unprepared for the transition. Our findings suggest that end users heard that more is needed to improve the dissemination of knowledge about the transition and how to navigate the new patient portal to both VA employees and the patients they serve.

Preparations for the transition should prioritize providing VA clinicians and staff with updated information and resources on how to access and use the new portal [ 25 ]. VA clinicians deliver quality care to veterans and many VA employees are proud to serve the nation’s veterans and willing to go the extra mile to support their patients’ needs [ 26 ]. In this study, participants expressed feeling unprepared to assist or even respond to their patients’ questions and concerns about using the new portal. This unpreparedness contributed to increased clinician and staff stress, as they felt ill-equipped to help their patients with portal issues. Such experiences can negatively affect the patient-clinician relationship. Preparing clinicians and patients about an upcoming transition, including technical support for clinicians and patients, may help minimize these potential issues [ 10 , 27 ]. Specialized training about an impending transition, along with detailed instructions on how to gain access to the new system, and a dedicated portal helpline may be necessary to help patients better navigate the transition [ 23 , 28 ].

In addition to a dedicated helpline, our recommendations include responding to potential changes in needed veteran services during the transition. In our study, participants observed more veteran walk-ins due to challenges with the patient portal. Health systems need to anticipate and address this demand by expanding access to in-person services and fortifying other communication channels. For example, sites could use nurses to staff a walk-in clinic to handle increases in walk-in traffic and increase call center capacity to handle increases in telephone calls [ 29 ]. Increased use of walk-in clinics have received heightened attention as a promising strategy for meeting healthcare demands during the COVID-19 pandemic [ 30 ] and can potentially be adapted for meeting care-related needs during an EHR transition. These strategies can fill a gap in communication between clinicians and their patients while patients are learning to access and navigate a new electronic portal.

Finally, there is a need for a recovery mechanism to restore confidence in the reliability of the EHR and the well-being of clinicians and staff. Healthcare workers are experiencing unprecedented levels of stress [ 31 ]. A plan must be in place to improve and monitor the accuracy of data migrated, populated, and processed within the new system [ 2 ]. Knowing that portal function is monitored could help ease clinician and staff concerns and mitigate stress related to the transition.

Limitations

This study has several limitations. First, data collection relied on voluntary participation, which may introduce self-selection response bias. Second, this work was completed at one VA medical center that was the first site in the larger enterprise-wide transition, and experiences at other VAs or healthcare systems might differ substantially. Third, we did not interview veterans and relied entirely on secondhand accounts of patient experiences with the patient portal. Future research should include interviews with veterans during the transition and compare veteran and VA employee experiences.

Despite a current delay in the deployment of the new EHR at additional VA medical centers, findings from this study offer timely lessons that can ensure clinicians and staff are equipped to navigate challenges during the transition. The strategies presented in this paper could help maintain patient-clinician communication and improve veteran experience. Guided by the emergency preparedness framework, recommended strategies to address issues presented here include alerting those patients most affected by the EHR transition, being prepared to address patients’ concerns, increasing staffing for the help desk and walk-in care clinics, and monitoring the accuracy and reliability of the portal to provide assurance to healthcare workers that patients’ needs are being met. These strategies can inform change management at other VA medical centers that will soon undergo EHR transition and may have implications for other healthcare systems undergoing patient portal changes. Further work is needed to directly examine the perspectives of veterans using the portals, as well as the perspectives of both staff and patients in the growing number of healthcare systems beyond VA that are preparing for an EHR-to-EHR transition.

Data availability

Deidentified data analyzed for this study are available from the corresponding author on reasonable request.

Abbreviations

Electronic health record

Department of Veterans Affairs

VA Medical Centers

Department of Defense

Huang C, Koppel R, McGreevey JD 3rd, Craven CK, Schreiber R. Transitions from one Electronic Health record to another: challenges, pitfalls, and recommendations. Appl Clin Inf. 2020;11(5):742–54.

Article   Google Scholar  

Penrod LE. Electronic Health Record Transition considerations. PM R. 2017;9(5S):S13–8.

Article   PubMed   Google Scholar  

Cogan AM, Haltom TM, Shimada SL, Davila JA, McGinn BP, Fix GM. Understanding patients’ experiences during transitions from one electronic health record to another: a scoping review. PEC Innov. 2024;4:100258. https://doi.org/10.1016/j.pecinn.2024.100258 . PMID: 38327990; PMCID: PMC10847675.

Article   PubMed   PubMed Central   Google Scholar  

Powell KR. Patient-perceived facilitators of and barriers to Electronic Portal Use: a systematic review. Comput Inf Nurs. 2017;35(11):565–73.

Google Scholar  

Wilson-Stronks A, Lee KK, Cordero CL, et al. One size does not fit all: meeting the Health Care needs of diverse populations. Oakbrook Terrace, IL: The Joint Commission; 2008.

Carini E, Villani L, Pezzullo AM, Gentili A, Barbara A, Ricciardi W, Boccia S. The Impact of Digital Patient Portals on Health outcomes, System Efficiency, and patient attitudes: updated systematic literature review. J Med Internet Res. 2021;23(9):e26189.

Home -. My HealtheVet - My HealtheVet (va.gov).

Nazi KM, Turvey CL, Klein DM, Hogan TP. A decade of veteran voices: examining patient Portal Enhancements through the Lens of user-centered design. J Med Internet Res. 2018;20(7):e10413. https://doi.org/10.2196/10413 .

Tapuria A, Porat T, Kalra D, Dsouza G, Xiaohui S, Curcin V. Impact of patient access to their electronic health record: systematic review. Inf Health Soc Care. 2021;46:2.

Fix GM, Haltom TM, Cogan AM, et al. Understanding patients’ preferences and experiences during an Electronic Health Record Transition. J GEN INTERN MED. 2023. https://doi.org/10.1007/s11606-023-08338-6 .

Monturo C, Brockway C, Ginev A. Electronic Health Record Transition: the patient experience. CIN: Computers Inf Nurs. 2022;40:1.

Tian D, Hoehner CM, Woeltje KF, Luong L, Lane MA. Disrupted and restored patient experience with transition to New Electronic Health Record System. J Patient Exp. 2021;18:8.

Emergency management programs for healthcare facilities. the four phases of emergency management. US Department of Homeland Security website: https://www.hsdl.org/?view&did=765520 . Accessed 28 Aug 2023.

Ahlness EA, Orlander J, Brunner J, Cutrona SL, Kim B, Molloy-Paolillo BK, Rinne ST, Rucci J, Sayre G, Anderson E. Everything’s so Role-Specific: VA Employee Perspectives’ on Electronic Health Record (EHR) transition implications for roles and responsibilities. J Gen Intern Med. 2023;38(Suppl 4):991–8. Epub 2023 Oct 5. PMID: 37798577; PMCID: PMC10593626.

Rucci JM, Ball S, Brunner J, Moldestad M, Cutrona SL, Sayre G, Rinne S. Like one long battle: employee perspectives of the simultaneous impact of COVID-19 and an Electronic Health Record Transition. J Gen Intern Med. 2023;38(Suppl 4):1040–8. https://doi.org/10.1007/s11606-023-08284-3 . Epub 2023 Oct 5. PMID: 37798583; PMCID: PMC10593661.

Sayre G, Young J. Beyond open-ended questions: purposeful interview guide development to elicit rich, trustworthy data [videorecording]. Seattle (WA): VA Health Services Research & Development HSR&D Cyberseminars; 2018.

Averill JB. Matrix analysis as a complementary analytic strategy in qualitative inquiry. Qual Health Res. 2002;12:6855–66.

Elo S, Kyngäs H. The qualitative content analysis process. J Adv Nurs. 2008;62:1107–15.

Haun JN, Lind JD, Shimada SL, Simon SR. Evaluating Secure Messaging from the veteran perspective: informing the adoption and sustained use of a patient-driven communication platform. Ann Anthropol Pract. 2013;372:57–74.

Kittler AF, Carlson GL, Harris C, Lippincott M, Pizziferri L, Volk LA, et al. Primary care physician attitudes toward using a secure web-based portal designed to facilitate electronic communication with patients. Inf Prim Care. 2004;123:129–38.

Shimada SL, Petrakis BA, Rothendler JA, Zirkle M, Zhao S, Feng H, Fix GM, Ozkaynak M, Martin T, Johnson SA, Tulu B, Gordon HS, Simon SR, Woods SS. An analysis of patient-provider secure messaging at two Veterans Health Administration medical centers: message content and resolution through secure messaging. J Am Med Inf Assoc. 2017;24:5.

Jha AK, Perlin JB, Kizer KW, Dudley RA. Effect of the transformation of the Veterans Affairs Health Care System on the quality of care. N Engl J Med. 2003;348:22.

McAlearney AS, Walker DM, Gaughan A, Moffatt-Bruce S, Huerta TR. Helping patients be better patients: a qualitative study of perceptions about Inpatient Portal Use. Telemed J E Health. 2020;26:9.

https://www.myhealth.va.gov/mhv-portal-web/transitioning-to-my-va-health-learn-more .

Beagley L. Educating patients: understanding barriers, learning styles, and teaching techniques. J Perianesth Nurs. 2011;26:5.

Moldestad M, Stryczek KC, Haverhals L, Kenney R, Lee M, Ball S, et al. Competing demands: Scheduling challenges in being veteran-centric in the setting of Health System initiatives to Improve Access. Mil Med. 2021;186:11–2.

Adusumalli J, Bhagra A, Vitek S, Clark SD, Chon TY. Stress management in staff supporting electronic health record transitions: a novel approach. Explore (NY). 2021;17:6.

Heponiemi T, Gluschkoff K, Vehko T, Kaihlanen AM, Saranto K, Nissinen S, et al. Electronic Health Record implementations and Insufficient Training Endanger nurses’ Well-being: cross-sectional survey study. J Med Internet Res. 2021;23:12e27096.

Laurant M, van der Biezen M, Wijers N, Watananirun K, Kontopantelis E, van Vught AJ. Nurses as substitutes for doctors in primary care. Cochrane Database Syst Rev. 201;7(7):CD001271.

Elnahal S, Kadakia KT, Gondi S, How, U.S. Health systems Can Build Capacity to Handle Demand Surges. Harvard Business Review. 2021. https://hbr.org/2021/10/how-u-s-health-systems-can-build-capacity-to-handle-demand-surges/ Accessed 25 Nov 2022.

George RE, Lowe WA. Well-being and uncertainty in health care practice. Clin Teach. 2019;16:4.

Download references

Acknowledgments

We acknowledge and thank members of the EMPIRIC Evaluation qualitative and supporting team for their contributions to this work including Ellen Ahlness, PhD, Julian Brunner, PhD, Adena Cohen-Bearak, MPH, M.Ed, Leah Cubanski, BA, Christine Firestone, Bo Kim, PhD, Megan Moldestad, MS, and Rachel Smith. We greatly appreciate the staff at the Mann-Grandstaff VA Medical Center and associated community-based outpatient clinics for generously sharing of their time and experiences participating in this study during this challenging time.

The “EHRM Partnership Integrating Rapid Cycle Evaluation to Improve Cerner Implementation (EMPIRIC)” (PEC 20–168) work was supported by funding from the US Department of Veterans Affairs, Veterans Health Administration, Health Services Research & Development Quality Enhancement Research Initiative (QUERI) (PEC 20–168). The findings and conclusions in this article are those of the authors and do not necessarily reflect the views of the Veterans Health Administration, Veterans Affairs, or any participating health agency or funder.

Author information

Authors and affiliations.

VA Northeast Ohio Healthcare System, 10701 East Blvd., Research Service 151, 44106, Cleveland, OH, USA

Sherry L. Ball

Center for Healthcare Organization and Implementation Research, VA Boston Healthcare System, Boston, MA, USA

Bo Kim & Seppo T. Rinne

Department of Psychiatry, Harvard Medical School, Boston, MA, USA

Center for Healthcare Organization and Implementation Research, VA Bedford Healthcare System, Bedford, MA, USA

Sarah L. Cutrona & Brianne K. Molloy-Paolillo

Division of Health Informatics & Implementation Science, Department of Population and Quantitative Health Sciences, University of Massachusetts Chan Medical School, Worcester, MA, USA

Sarah L. Cutrona

Seattle-Denver Center of Innovation for Veteran-Centered and Value-Driven Care, VHA Puget Sound Health Care System, Seattle, WA, USA

Ellen Ahlness, Megan Moldestad & George Sayre

University of Washington School of Public Health, Seattle, WA, USA

George Sayre

Geisel School of Medicine at Dartmouth, Hannover, NH, USA

Seppo T. Rinne

You can also search for this author in PubMed   Google Scholar

Contributions

S.R. designed the larger study. G.S. was the qualitative methodologist who led the qualitative team. S.B., E.A., and M.M. created the interview guides and completed the interviews; Data analysis, data interpretation, and the initial manuscript draft were completed by S.B. and B.K. S.C. and B.M. worked with the qualitative team to finalize the analysis and edit and finalize the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Sherry L. Ball .

Ethics declarations

Ethics approval and consent to participate.

This evaluation was designated as non-research/quality improvement by the VA Bedford Healthcare System Institutional Review Board. All methods were carried out in accordance with local and national VA guidelines and regulations for quality improvement activities. This study included virtual interviews with participants via MS Teams. Employees volunteered to participate in interviews and verbal consent was obtained to record interviews. Study materials, including interview guides with verbal consent procedures, were reviewed and approved by labor unions and determined as non-research by the VA Bedford Healthcare System Institutional Review Board.

Consent for publication

Not applicable.

The findings and conclusions in this paper are those of the authors and do not necessarily represent the official position of the Department of Veterans Affairs.

Prior presentations

Ball S, Kim B, Moldestad M, Molloy-Paolillo B, Cubanski L, Cutrona S, Sayre G, and Rinne S. (2022, June). Electronic Health Record Transition: Providers’ Experiences with Frustrated Patients. Poster presentation at the 2022 AcademyHealth Annual Research Meeting. June 2022.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Ball, S.L., Kim, B., Cutrona, S.L. et al. Clinician and staff experiences with frustrated patients during an electronic health record transition: a qualitative case study. BMC Health Serv Res 24 , 535 (2024). https://doi.org/10.1186/s12913-024-10974-5

Download citation

Received : 29 August 2023

Accepted : 09 April 2024

Published : 26 April 2024

DOI : https://doi.org/10.1186/s12913-024-10974-5

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• EHR transition
• Patient experience
• Clinician experience
• Qualitative analysis

BMC Health Services Research

ISSN: 1472-6963

• General enquiries: [email protected]

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• BMC Med Res Methodol

The case study approach

Sarah crowe.

1 Division of Primary Care, The University of Nottingham, Nottingham, UK

Kathrin Cresswell

2 Centre for Population Health Sciences, The University of Edinburgh, Edinburgh, UK

Ann Robertson

3 School of Health in Social Science, The University of Edinburgh, Edinburgh, UK

Anthony Avery

Aziz sheikh.

The case study approach allows in-depth, multi-faceted explorations of complex issues in their real-life settings. The value of the case study approach is well recognised in the fields of business, law and policy, but somewhat less so in health services research. Based on our experiences of conducting several health-related case studies, we reflect on the different types of case study design, the specific research questions this approach can help answer, the data sources that tend to be used, and the particular advantages and disadvantages of employing this methodological approach. The paper concludes with key pointers to aid those designing and appraising proposals for conducting case study research, and a checklist to help readers assess the quality of case study reports.

Introduction

The case study approach is particularly useful to employ when there is a need to obtain an in-depth appreciation of an issue, event or phenomenon of interest, in its natural real-life context. Our aim in writing this piece is to provide insights into when to consider employing this approach and an overview of key methodological considerations in relation to the design, planning, analysis, interpretation and reporting of case studies.

The illustrative 'grand round', 'case report' and 'case series' have a long tradition in clinical practice and research. Presenting detailed critiques, typically of one or more patients, aims to provide insights into aspects of the clinical case and, in doing so, illustrate broader lessons that may be learnt. In research, the conceptually-related case study approach can be used, for example, to describe in detail a patient's episode of care, explore professional attitudes to and experiences of a new policy initiative or service development or more generally to 'investigate contemporary phenomena within its real-life context' [ 1 ]. Based on our experiences of conducting a range of case studies, we reflect on when to consider using this approach, discuss the key steps involved and illustrate, with examples, some of the practical challenges of attaining an in-depth understanding of a 'case' as an integrated whole. In keeping with previously published work, we acknowledge the importance of theory to underpin the design, selection, conduct and interpretation of case studies[ 2 ]. In so doing, we make passing reference to the different epistemological approaches used in case study research by key theoreticians and methodologists in this field of enquiry.

This paper is structured around the following main questions: What is a case study? What are case studies used for? How are case studies conducted? What are the potential pitfalls and how can these be avoided? We draw in particular on four of our own recently published examples of case studies (see Tables ​ Tables1, 1 , ​ ,2, 2 , ​ ,3 3 and ​ and4) 4 ) and those of others to illustrate our discussion[ 3 - 7 ].

Example of a case study investigating the reasons for differences in recruitment rates of minority ethnic people in asthma research[ 3 ]

Example of a case study investigating the process of planning and implementing a service in Primary Care Organisations[ 4 ]

Example of a case study investigating the introduction of the electronic health records[ 5 ]

Example of a case study investigating the formal and informal ways students learn about patient safety[ 6 ]

What is a case study?

A case study is a research approach that is used to generate an in-depth, multi-faceted understanding of a complex issue in its real-life context. It is an established research design that is used extensively in a wide variety of disciplines, particularly in the social sciences. A case study can be defined in a variety of ways (Table ​ (Table5), 5 ), the central tenet being the need to explore an event or phenomenon in depth and in its natural context. It is for this reason sometimes referred to as a "naturalistic" design; this is in contrast to an "experimental" design (such as a randomised controlled trial) in which the investigator seeks to exert control over and manipulate the variable(s) of interest.

Definitions of a case study

Stake's work has been particularly influential in defining the case study approach to scientific enquiry. He has helpfully characterised three main types of case study: intrinsic , instrumental and collective [ 8 ]. An intrinsic case study is typically undertaken to learn about a unique phenomenon. The researcher should define the uniqueness of the phenomenon, which distinguishes it from all others. In contrast, the instrumental case study uses a particular case (some of which may be better than others) to gain a broader appreciation of an issue or phenomenon. The collective case study involves studying multiple cases simultaneously or sequentially in an attempt to generate a still broader appreciation of a particular issue.

These are however not necessarily mutually exclusive categories. In the first of our examples (Table ​ (Table1), 1 ), we undertook an intrinsic case study to investigate the issue of recruitment of minority ethnic people into the specific context of asthma research studies, but it developed into a instrumental case study through seeking to understand the issue of recruitment of these marginalised populations more generally, generating a number of the findings that are potentially transferable to other disease contexts[ 3 ]. In contrast, the other three examples (see Tables ​ Tables2, 2 , ​ ,3 3 and ​ and4) 4 ) employed collective case study designs to study the introduction of workforce reconfiguration in primary care, the implementation of electronic health records into hospitals, and to understand the ways in which healthcare students learn about patient safety considerations[ 4 - 6 ]. Although our study focusing on the introduction of General Practitioners with Specialist Interests (Table ​ (Table2) 2 ) was explicitly collective in design (four contrasting primary care organisations were studied), is was also instrumental in that this particular professional group was studied as an exemplar of the more general phenomenon of workforce redesign[ 4 ].

What are case studies used for?

According to Yin, case studies can be used to explain, describe or explore events or phenomena in the everyday contexts in which they occur[ 1 ]. These can, for example, help to understand and explain causal links and pathways resulting from a new policy initiative or service development (see Tables ​ Tables2 2 and ​ and3, 3 , for example)[ 1 ]. In contrast to experimental designs, which seek to test a specific hypothesis through deliberately manipulating the environment (like, for example, in a randomised controlled trial giving a new drug to randomly selected individuals and then comparing outcomes with controls),[ 9 ] the case study approach lends itself well to capturing information on more explanatory ' how ', 'what' and ' why ' questions, such as ' how is the intervention being implemented and received on the ground?'. The case study approach can offer additional insights into what gaps exist in its delivery or why one implementation strategy might be chosen over another. This in turn can help develop or refine theory, as shown in our study of the teaching of patient safety in undergraduate curricula (Table ​ (Table4 4 )[ 6 , 10 ]. Key questions to consider when selecting the most appropriate study design are whether it is desirable or indeed possible to undertake a formal experimental investigation in which individuals and/or organisations are allocated to an intervention or control arm? Or whether the wish is to obtain a more naturalistic understanding of an issue? The former is ideally studied using a controlled experimental design, whereas the latter is more appropriately studied using a case study design.

Case studies may be approached in different ways depending on the epistemological standpoint of the researcher, that is, whether they take a critical (questioning one's own and others' assumptions), interpretivist (trying to understand individual and shared social meanings) or positivist approach (orientating towards the criteria of natural sciences, such as focusing on generalisability considerations) (Table ​ (Table6). 6 ). Whilst such a schema can be conceptually helpful, it may be appropriate to draw on more than one approach in any case study, particularly in the context of conducting health services research. Doolin has, for example, noted that in the context of undertaking interpretative case studies, researchers can usefully draw on a critical, reflective perspective which seeks to take into account the wider social and political environment that has shaped the case[ 11 ].

Example of epistemological approaches that may be used in case study research

How are case studies conducted?

Here, we focus on the main stages of research activity when planning and undertaking a case study; the crucial stages are: defining the case; selecting the case(s); collecting and analysing the data; interpreting data; and reporting the findings.

Defining the case

Carefully formulated research question(s), informed by the existing literature and a prior appreciation of the theoretical issues and setting(s), are all important in appropriately and succinctly defining the case[ 8 , 12 ]. Crucially, each case should have a pre-defined boundary which clarifies the nature and time period covered by the case study (i.e. its scope, beginning and end), the relevant social group, organisation or geographical area of interest to the investigator, the types of evidence to be collected, and the priorities for data collection and analysis (see Table ​ Table7 7 )[ 1 ]. A theory driven approach to defining the case may help generate knowledge that is potentially transferable to a range of clinical contexts and behaviours; using theory is also likely to result in a more informed appreciation of, for example, how and why interventions have succeeded or failed[ 13 ].

Example of a checklist for rating a case study proposal[ 8 ]

For example, in our evaluation of the introduction of electronic health records in English hospitals (Table ​ (Table3), 3 ), we defined our cases as the NHS Trusts that were receiving the new technology[ 5 ]. Our focus was on how the technology was being implemented. However, if the primary research interest had been on the social and organisational dimensions of implementation, we might have defined our case differently as a grouping of healthcare professionals (e.g. doctors and/or nurses). The precise beginning and end of the case may however prove difficult to define. Pursuing this same example, when does the process of implementation and adoption of an electronic health record system really begin or end? Such judgements will inevitably be influenced by a range of factors, including the research question, theory of interest, the scope and richness of the gathered data and the resources available to the research team.

Selecting the case(s)

The decision on how to select the case(s) to study is a very important one that merits some reflection. In an intrinsic case study, the case is selected on its own merits[ 8 ]. The case is selected not because it is representative of other cases, but because of its uniqueness, which is of genuine interest to the researchers. This was, for example, the case in our study of the recruitment of minority ethnic participants into asthma research (Table ​ (Table1) 1 ) as our earlier work had demonstrated the marginalisation of minority ethnic people with asthma, despite evidence of disproportionate asthma morbidity[ 14 , 15 ]. In another example of an intrinsic case study, Hellstrom et al.[ 16 ] studied an elderly married couple living with dementia to explore how dementia had impacted on their understanding of home, their everyday life and their relationships.

For an instrumental case study, selecting a "typical" case can work well[ 8 ]. In contrast to the intrinsic case study, the particular case which is chosen is of less importance than selecting a case that allows the researcher to investigate an issue or phenomenon. For example, in order to gain an understanding of doctors' responses to health policy initiatives, Som undertook an instrumental case study interviewing clinicians who had a range of responsibilities for clinical governance in one NHS acute hospital trust[ 17 ]. Sampling a "deviant" or "atypical" case may however prove even more informative, potentially enabling the researcher to identify causal processes, generate hypotheses and develop theory.

In collective or multiple case studies, a number of cases are carefully selected. This offers the advantage of allowing comparisons to be made across several cases and/or replication. Choosing a "typical" case may enable the findings to be generalised to theory (i.e. analytical generalisation) or to test theory by replicating the findings in a second or even a third case (i.e. replication logic)[ 1 ]. Yin suggests two or three literal replications (i.e. predicting similar results) if the theory is straightforward and five or more if the theory is more subtle. However, critics might argue that selecting 'cases' in this way is insufficiently reflexive and ill-suited to the complexities of contemporary healthcare organisations.

The selected case study site(s) should allow the research team access to the group of individuals, the organisation, the processes or whatever else constitutes the chosen unit of analysis for the study. Access is therefore a central consideration; the researcher needs to come to know the case study site(s) well and to work cooperatively with them. Selected cases need to be not only interesting but also hospitable to the inquiry [ 8 ] if they are to be informative and answer the research question(s). Case study sites may also be pre-selected for the researcher, with decisions being influenced by key stakeholders. For example, our selection of case study sites in the evaluation of the implementation and adoption of electronic health record systems (see Table ​ Table3) 3 ) was heavily influenced by NHS Connecting for Health, the government agency that was responsible for overseeing the National Programme for Information Technology (NPfIT)[ 5 ]. This prominent stakeholder had already selected the NHS sites (through a competitive bidding process) to be early adopters of the electronic health record systems and had negotiated contracts that detailed the deployment timelines.

It is also important to consider in advance the likely burden and risks associated with participation for those who (or the site(s) which) comprise the case study. Of particular importance is the obligation for the researcher to think through the ethical implications of the study (e.g. the risk of inadvertently breaching anonymity or confidentiality) and to ensure that potential participants/participating sites are provided with sufficient information to make an informed choice about joining the study. The outcome of providing this information might be that the emotive burden associated with participation, or the organisational disruption associated with supporting the fieldwork, is considered so high that the individuals or sites decide against participation.

In our example of evaluating implementations of electronic health record systems, given the restricted number of early adopter sites available to us, we sought purposively to select a diverse range of implementation cases among those that were available[ 5 ]. We chose a mixture of teaching, non-teaching and Foundation Trust hospitals, and examples of each of the three electronic health record systems procured centrally by the NPfIT. At one recruited site, it quickly became apparent that access was problematic because of competing demands on that organisation. Recognising the importance of full access and co-operative working for generating rich data, the research team decided not to pursue work at that site and instead to focus on other recruited sites.

Collecting the data

In order to develop a thorough understanding of the case, the case study approach usually involves the collection of multiple sources of evidence, using a range of quantitative (e.g. questionnaires, audits and analysis of routinely collected healthcare data) and more commonly qualitative techniques (e.g. interviews, focus groups and observations). The use of multiple sources of data (data triangulation) has been advocated as a way of increasing the internal validity of a study (i.e. the extent to which the method is appropriate to answer the research question)[ 8 , 18 - 21 ]. An underlying assumption is that data collected in different ways should lead to similar conclusions, and approaching the same issue from different angles can help develop a holistic picture of the phenomenon (Table ​ (Table2 2 )[ 4 ].

Brazier and colleagues used a mixed-methods case study approach to investigate the impact of a cancer care programme[ 22 ]. Here, quantitative measures were collected with questionnaires before, and five months after, the start of the intervention which did not yield any statistically significant results. Qualitative interviews with patients however helped provide an insight into potentially beneficial process-related aspects of the programme, such as greater, perceived patient involvement in care. The authors reported how this case study approach provided a number of contextual factors likely to influence the effectiveness of the intervention and which were not likely to have been obtained from quantitative methods alone.

In collective or multiple case studies, data collection needs to be flexible enough to allow a detailed description of each individual case to be developed (e.g. the nature of different cancer care programmes), before considering the emerging similarities and differences in cross-case comparisons (e.g. to explore why one programme is more effective than another). It is important that data sources from different cases are, where possible, broadly comparable for this purpose even though they may vary in nature and depth.

Analysing, interpreting and reporting case studies

Making sense and offering a coherent interpretation of the typically disparate sources of data (whether qualitative alone or together with quantitative) is far from straightforward. Repeated reviewing and sorting of the voluminous and detail-rich data are integral to the process of analysis. In collective case studies, it is helpful to analyse data relating to the individual component cases first, before making comparisons across cases. Attention needs to be paid to variations within each case and, where relevant, the relationship between different causes, effects and outcomes[ 23 ]. Data will need to be organised and coded to allow the key issues, both derived from the literature and emerging from the dataset, to be easily retrieved at a later stage. An initial coding frame can help capture these issues and can be applied systematically to the whole dataset with the aid of a qualitative data analysis software package.

The Framework approach is a practical approach, comprising of five stages (familiarisation; identifying a thematic framework; indexing; charting; mapping and interpretation) , to managing and analysing large datasets particularly if time is limited, as was the case in our study of recruitment of South Asians into asthma research (Table ​ (Table1 1 )[ 3 , 24 ]. Theoretical frameworks may also play an important role in integrating different sources of data and examining emerging themes. For example, we drew on a socio-technical framework to help explain the connections between different elements - technology; people; and the organisational settings within which they worked - in our study of the introduction of electronic health record systems (Table ​ (Table3 3 )[ 5 ]. Our study of patient safety in undergraduate curricula drew on an evaluation-based approach to design and analysis, which emphasised the importance of the academic, organisational and practice contexts through which students learn (Table ​ (Table4 4 )[ 6 ].

Case study findings can have implications both for theory development and theory testing. They may establish, strengthen or weaken historical explanations of a case and, in certain circumstances, allow theoretical (as opposed to statistical) generalisation beyond the particular cases studied[ 12 ]. These theoretical lenses should not, however, constitute a strait-jacket and the cases should not be "forced to fit" the particular theoretical framework that is being employed.

When reporting findings, it is important to provide the reader with enough contextual information to understand the processes that were followed and how the conclusions were reached. In a collective case study, researchers may choose to present the findings from individual cases separately before amalgamating across cases. Care must be taken to ensure the anonymity of both case sites and individual participants (if agreed in advance) by allocating appropriate codes or withholding descriptors. In the example given in Table ​ Table3, 3 , we decided against providing detailed information on the NHS sites and individual participants in order to avoid the risk of inadvertent disclosure of identities[ 5 , 25 ].

What are the potential pitfalls and how can these be avoided?

The case study approach is, as with all research, not without its limitations. When investigating the formal and informal ways undergraduate students learn about patient safety (Table ​ (Table4), 4 ), for example, we rapidly accumulated a large quantity of data. The volume of data, together with the time restrictions in place, impacted on the depth of analysis that was possible within the available resources. This highlights a more general point of the importance of avoiding the temptation to collect as much data as possible; adequate time also needs to be set aside for data analysis and interpretation of what are often highly complex datasets.

Case study research has sometimes been criticised for lacking scientific rigour and providing little basis for generalisation (i.e. producing findings that may be transferable to other settings)[ 1 ]. There are several ways to address these concerns, including: the use of theoretical sampling (i.e. drawing on a particular conceptual framework); respondent validation (i.e. participants checking emerging findings and the researcher's interpretation, and providing an opinion as to whether they feel these are accurate); and transparency throughout the research process (see Table ​ Table8 8 )[ 8 , 18 - 21 , 23 , 26 ]. Transparency can be achieved by describing in detail the steps involved in case selection, data collection, the reasons for the particular methods chosen, and the researcher's background and level of involvement (i.e. being explicit about how the researcher has influenced data collection and interpretation). Seeking potential, alternative explanations, and being explicit about how interpretations and conclusions were reached, help readers to judge the trustworthiness of the case study report. Stake provides a critique checklist for a case study report (Table ​ (Table9 9 )[ 8 ].

Potential pitfalls and mitigating actions when undertaking case study research

Stake's checklist for assessing the quality of a case study report[ 8 ]

Conclusions

The case study approach allows, amongst other things, critical events, interventions, policy developments and programme-based service reforms to be studied in detail in a real-life context. It should therefore be considered when an experimental design is either inappropriate to answer the research questions posed or impossible to undertake. Considering the frequency with which implementations of innovations are now taking place in healthcare settings and how well the case study approach lends itself to in-depth, complex health service research, we believe this approach should be more widely considered by researchers. Though inherently challenging, the research case study can, if carefully conceptualised and thoughtfully undertaken and reported, yield powerful insights into many important aspects of health and healthcare delivery.

Competing interests

The authors declare that they have no competing interests.

Authors' contributions

AS conceived this article. SC, KC and AR wrote this paper with GH, AA and AS all commenting on various drafts. SC and AS are guarantors.

Pre-publication history

The pre-publication history for this paper can be accessed here:

http://www.biomedcentral.com/1471-2288/11/100/prepub

Acknowledgements

We are grateful to the participants and colleagues who contributed to the individual case studies that we have drawn on. This work received no direct funding, but it has been informed by projects funded by Asthma UK, the NHS Service Delivery Organisation, NHS Connecting for Health Evaluation Programme, and Patient Safety Research Portfolio. We would also like to thank the expert reviewers for their insightful and constructive feedback. Our thanks are also due to Dr. Allison Worth who commented on an earlier draft of this manuscript.

• Yin RK. Case study research, design and method. 4. London: Sage Publications Ltd.; 2009. [ Google Scholar ]
• Keen J, Packwood T. Qualitative research; case study evaluation. BMJ. 1995; 311 :444–446. [ PMC free article ] [ PubMed ] [ Google Scholar ]
• Sheikh A, Halani L, Bhopal R, Netuveli G, Partridge M, Car J. et al. Facilitating the Recruitment of Minority Ethnic People into Research: Qualitative Case Study of South Asians and Asthma. PLoS Med. 2009; 6 (10):1–11. [ PMC free article ] [ PubMed ] [ Google Scholar ]
• Pinnock H, Huby G, Powell A, Kielmann T, Price D, Williams S, The process of planning, development and implementation of a General Practitioner with a Special Interest service in Primary Care Organisations in England and Wales: a comparative prospective case study. Report for the National Co-ordinating Centre for NHS Service Delivery and Organisation R&D (NCCSDO) 2008. http://www.sdo.nihr.ac.uk/files/project/99-final-report.pdf
• Robertson A, Cresswell K, Takian A, Petrakaki D, Crowe S, Cornford T. et al. Prospective evaluation of the implementation and adoption of NHS Connecting for Health's national electronic health record in secondary care in England: interim findings. BMJ. 2010; 41 :c4564. [ PMC free article ] [ PubMed ] [ Google Scholar ]
• Pearson P, Steven A, Howe A, Sheikh A, Ashcroft D, Smith P. the Patient Safety Education Study Group. Learning about patient safety: organisational context and culture in the education of healthcare professionals. J Health Serv Res Policy. 2010; 15 :4–10. doi: 10.1258/jhsrp.2009.009052. [ PubMed ] [ CrossRef ] [ Google Scholar ]
• van Harten WH, Casparie TF, Fisscher OA. The evaluation of the introduction of a quality management system: a process-oriented case study in a large rehabilitation hospital. Health Policy. 2002; 60 (1):17–37. doi: 10.1016/S0168-8510(01)00187-7. [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Stake RE. The art of case study research. London: Sage Publications Ltd.; 1995. [ Google Scholar ]
• Sheikh A, Smeeth L, Ashcroft R. Randomised controlled trials in primary care: scope and application. Br J Gen Pract. 2002; 52 (482):746–51. [ PMC free article ] [ PubMed ] [ Google Scholar ]
• King G, Keohane R, Verba S. Designing Social Inquiry. Princeton: Princeton University Press; 1996. [ Google Scholar ]
• Doolin B. Information technology as disciplinary technology: being critical in interpretative research on information systems. Journal of Information Technology. 1998; 13 :301–311. doi: 10.1057/jit.1998.8. [ CrossRef ] [ Google Scholar ]
• George AL, Bennett A. Case studies and theory development in the social sciences. Cambridge, MA: MIT Press; 2005. [ Google Scholar ]
• Eccles M. the Improved Clinical Effectiveness through Behavioural Research Group (ICEBeRG) Designing theoretically-informed implementation interventions. Implementation Science. 2006; 1 :1–8. doi: 10.1186/1748-5908-1-1. [ PMC free article ] [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Netuveli G, Hurwitz B, Levy M, Fletcher M, Barnes G, Durham SR, Sheikh A. Ethnic variations in UK asthma frequency, morbidity, and health-service use: a systematic review and meta-analysis. Lancet. 2005; 365 (9456):312–7. [ PubMed ] [ Google Scholar ]
• Sheikh A, Panesar SS, Lasserson T, Netuveli G. Recruitment of ethnic minorities to asthma studies. Thorax. 2004; 59 (7):634. [ PMC free article ] [ PubMed ] [ Google Scholar ]
• Hellström I, Nolan M, Lundh U. 'We do things together': A case study of 'couplehood' in dementia. Dementia. 2005; 4 :7–22. doi: 10.1177/1471301205049188. [ CrossRef ] [ Google Scholar ]
• Som CV. Nothing seems to have changed, nothing seems to be changing and perhaps nothing will change in the NHS: doctors' response to clinical governance. International Journal of Public Sector Management. 2005; 18 :463–477. doi: 10.1108/09513550510608903. [ CrossRef ] [ Google Scholar ]
• Lincoln Y, Guba E. Naturalistic inquiry. Newbury Park: Sage Publications; 1985. [ Google Scholar ]
• Barbour RS. Checklists for improving rigour in qualitative research: a case of the tail wagging the dog? BMJ. 2001; 322 :1115–1117. doi: 10.1136/bmj.322.7294.1115. [ PMC free article ] [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Mays N, Pope C. Qualitative research in health care: Assessing quality in qualitative research. BMJ. 2000; 320 :50–52. doi: 10.1136/bmj.320.7226.50. [ PMC free article ] [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Mason J. Qualitative researching. London: Sage; 2002. [ Google Scholar ]
• Brazier A, Cooke K, Moravan V. Using Mixed Methods for Evaluating an Integrative Approach to Cancer Care: A Case Study. Integr Cancer Ther. 2008; 7 :5–17. doi: 10.1177/1534735407313395. [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Miles MB, Huberman M. Qualitative data analysis: an expanded sourcebook. 2. CA: Sage Publications Inc.; 1994. [ Google Scholar ]
• Pope C, Ziebland S, Mays N. Analysing qualitative data. Qualitative research in health care. BMJ. 2000; 320 :114–116. doi: 10.1136/bmj.320.7227.114. [ PMC free article ] [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Cresswell KM, Worth A, Sheikh A. Actor-Network Theory and its role in understanding the implementation of information technology developments in healthcare. BMC Med Inform Decis Mak. 2010; 10 (1):67. doi: 10.1186/1472-6947-10-67. [ PMC free article ] [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Malterud K. Qualitative research: standards, challenges, and guidelines. Lancet. 2001; 358 :483–488. doi: 10.1016/S0140-6736(01)05627-6. [ PubMed ] [ CrossRef ] [ Google Scholar ]
• Yin R. Case study research: design and methods. 2. Thousand Oaks, CA: Sage Publishing; 1994. [ Google Scholar ]
• Yin R. Enhancing the quality of case studies in health services research. Health Serv Res. 1999; 34 :1209–1224. [ PMC free article ] [ PubMed ] [ Google Scholar ]
• Green J, Thorogood N. Qualitative methods for health research. 2. Los Angeles: Sage; 2009. [ Google Scholar ]
• Howcroft D, Trauth E. Handbook of Critical Information Systems Research, Theory and Application. Cheltenham, UK: Northampton, MA, USA: Edward Elgar; 2005. [ Google Scholar ]
• Blakie N. Approaches to Social Enquiry. Cambridge: Polity Press; 1993. [ Google Scholar ]
• Doolin B. Power and resistance in the implementation of a medical management information system. Info Systems J. 2004; 14 :343–362. doi: 10.1111/j.1365-2575.2004.00176.x. [ CrossRef ] [ Google Scholar ]
• Bloomfield BP, Best A. Management consultants: systems development, power and the translation of problems. Sociological Review. 1992; 40 :533–560. [ Google Scholar ]
• Shanks G, Parr A. Proceedings of the European Conference on Information Systems. Naples; 2003. Positivist, single case study research in information systems: A critical analysis. [ Google Scholar ]

• Share full article

Advertisement

Supported by

David Brooks

The Courage to Follow the Evidence on Transgender Care

By David Brooks

Opinion Columnist

Hilary Cass is the kind of hero the world needs today. She has entered one of the most toxic debates in our culture: how the medical community should respond to the growing numbers of young people who seek gender transition through medical treatments, including puberty blockers and hormone therapies. This month, after more than three years of research, Cass, a pediatrician, produced a report , commissioned by the National Health Service in England, that is remarkable for its empathy for people on all sides of this issue, for its humility in the face of complex social trends we don’t understand and for its intellectual integrity as we try to figure out which treatments actually work to serve those patients who are in distress. With incredible courage, she shows that careful scholarship can cut through debates that have been marked by vituperation and intimidation and possibly reset them on more rational grounds.

Cass, a past president of Britain’s Royal College of Pediatrics and Child Health, is clear about the mission of her report: “This review is not about defining what it means to be trans, nor is it about undermining the validity of trans identities, challenging the right of people to express themselves or rolling back on people’s rights to health care. It is about what the health care approach should be, and how best to help the growing number of children and young people who are looking for support from the N.H.S. in relation to their gender identity.”

This issue begins with a mystery. For reasons that are not clear, the number of adolescents who have sought to medically change their sex has been skyrocketing in recent years, though the overall number remains very small. For reasons that are also not clear, adolescents who were assigned female at birth are driving this trend, whereas before the late 2000s, it was mostly adolescents who were assigned male at birth who sought these treatments.

Doctors and researchers have proposed various theories to try to explain these trends. One is that greater social acceptance of trans people has enabled people to seek these therapies. Another is that teenagers are being influenced by the popularity of searching and experimenting around identity. A third is that the rise of teen mental health issues may be contributing to gender dysphoria. In her report, Cass is skeptical of broad generalizations in the absence of clear evidence; these are individual children and adolescents who take their own routes to who they are.

Some activists and medical practitioners on the left have come to see the surge in requests for medical transitioning as a piece of the new civil rights issue of our time — offering recognition to people of all gender identities. Transition through medical interventions was embraced by providers in the United States and Europe after a pair of small Dutch studies showed that such treatment improved patients’ well-being. But a 2022 Reuters investigation found that some American clinics were quite aggressive with treatment: None of the 18 U.S. clinics that Reuters looked at performed long assessments on their patients, and some prescribed puberty blockers on the first visit.

Unfortunately, some researchers who questioned the Dutch approach were viciously attacked. This year, Sallie Baxendale, a professor of clinical neuropsychology at the University College London, published a review of studies looking at the impact of puberty blockers on brain development and concluded that “critical questions” about the therapy remain unanswered. She was immediately attacked. She recently told The Guardian, “I’ve been accused of being an anti-trans activist, and that now comes up on Google and is never going to go away.”

As Cass writes in her report, “The toxicity of the debate is exceptional.” She continues, “There are few other areas of health care where professionals are so afraid to openly discuss their views, where people are vilified on social media and where name-calling echoes the worst bullying behavior.”

Cass focused on Britain, but her description of the intellectual and political climate is just as applicable to the U.S., where brutality on the left has been matched by brutality on the right, with crude legislation that doesn’t acknowledge the well-being of the young people in question. In 24 states Republicans have passed laws banning these therapies, sometimes threatening doctors with prison time if they prescribe the treatment they think is best for their patients.

The battle lines on this issue are an extreme case, but they are not unfamiliar. On issue after issue, zealous minorities bully and intimidate the reasonable majority. Often, those who see nuance decide it’s best to just keep their heads down. The rage-filled minority rules.

Cass showed enormous courage in walking into this maelstrom. She did it in the face of practitioners who refused to cooperate and thus denied her information that could have helped inform her report. As an editorial in The BMJ puts it, “Despite encouragement from N.H.S. England,” the “necessary cooperation” was not forthcoming. “Professionals withholding data from a national inquiry seems hard to imagine, but it is what happened.”

Cass’s report does not contain even a hint of rancor, just a generous open-mindedness and empathy for all involved. Time and again in her report, she returns to the young people and the parents directly involved, on all sides of the issue. She clearly spent a lot of time meeting with them. She writes, “One of the great pleasures of the review has been getting to meet and talk to so many interesting people.”

The report’s greatest strength is its epistemic humility. Cass is continually asking, “What do we really know?” She is carefully examining the various studies — which are high quality, which are not. She is down in the academic weeds.

She notes that the quality of the research in this field is poor. The current treatments are “built on shaky foundations,” she writes in The BMJ. Practitioners have raced ahead with therapies when we don’t know what the effects will be. As Cass tells The BMJ, “I can’t think of another area of pediatric care where we give young people a potentially irreversible treatment and have no idea what happens to them in adulthood.”

She writes in her report, “The option to provide masculinizing/feminizing hormones from age 16 is available, but the review would recommend extreme caution.” She does not issue a blanket, one-size-fits-all recommendation, but her core conclusion is this: “For most young people, a medical pathway will not be the best way to manage their gender-related distress.” She realizes that this conclusion will not please many of the young people she has come to know, but this is where the evidence has taken her.

You can agree or disagree with this or that part of the report, and maybe the evidence will look different in 10 years, but I ask you to examine the integrity with which Cass did her work in such a treacherous environment.

In 1877 a British philosopher and mathematician named William Kingdon Clifford published an essay called “ The Ethics of Belief .” In it he argued that if a shipowner ignored evidence that his craft had problems and sent the ship to sea having convinced himself it was safe, then of course we would blame him if the ship went down and all aboard were lost. To have a belief is to bear responsibility, and one thus has a moral responsibility to dig arduously into the evidence, avoid ideological thinking and take into account self-serving biases. “It is wrong always, everywhere, and for anyone, to believe anything upon insufficient evidence,” Clifford wrote. A belief, he continued, is a public possession. If too many people believe things without evidence, “the danger to society is not merely that it should believe wrong things, though that is great enough; but that it should become credulous, and lose the habit of testing things and inquiring into them; for then it must sink back into savagery.”

Since the Trump years, this habit of not consulting the evidence has become the underlying crisis in so many realms. People segregate into intellectually cohesive teams, which are always dumber than intellectually diverse teams. Issues are settled by intimidation, not evidence. Our natural human tendency is to be too confident in our knowledge, too quick to ignore contrary evidence. But these days it has become acceptable to luxuriate in those epistemic shortcomings, not to struggle against them. See, for example, the modern Republican Party.

Recently it’s been encouraging to see cases in which the evidence has won out. Many universities have acknowledged that the SAT is a better predictor of college success than high school grades and have reinstated it. Some corporations have come to understand that while diversity, equity and inclusion are essential goals, the current programs often empirically fail to serve those goals and need to be reformed. I’m hoping that Hilary Cass is modeling a kind of behavior that will be replicated across academia, in the other professions and across the body politic more generally and thus save us from spiraling into an epistemological doom loop.

The Times is committed to publishing a diversity of letters to the editor. We’d like to hear what you think about this or any of our articles. Here are some tips . And here’s our email: [email protected] .

Follow the New York Times Opinion section on Facebook , Instagram , TikTok , WhatsApp , X and Threads .

David Brooks has been a columnist with The Times since 2003. He is the author, most recently,  of “How to Know a Person: The Art of Seeing Others Deeply and Being Deeply Seen.” @ nytdavidbrooks

• Search Menu
• Volume 2024, Issue 4, April 2024
• Bariatric Surgery
• Breast Surgery
• Cardiothoracic Surgery
• Colorectal Surgery
• Colorectal Surgery, Upper GI Surgery
• Gynaecology
• Hepatobiliary Surgery
• Interventional Radiology
• Neurosurgery
• Ophthalmology
• Oral and Maxillofacial Surgery
• Otorhinolaryngology - Head & Neck Surgery
• Paediatric Surgery
• Plastic Surgery
• Transplant Surgery
• Trauma & Orthopaedic Surgery
• Upper GI Surgery
• Vascular Surgery
• Author Guidelines
• Submission Site
• Open Access
• Reasons to Submit
• About Journal of Surgical Case Reports
• Editorial Board
• Advertising and Corporate Services
• Journals Career Network
• Self-Archiving Policy
• Journals on Oxford Academic
• Books on Oxford Academic

Article Contents

Introduction, case report, conflict of interest statement, data availability, consent for publication.

• < Previous

Exploring a rare case of juvenile psammomatoid ossifying fibroma in the ethmoid: a case study and review

• Article contents
• Figures & tables
• Supplementary Data

Taha Yassine Aaboudech, Hafsa El Ouazzani, Habiba Kadiri, Leila Essakalli, Ayoub Bouteyine, Hanae Benadbdenbi, Naji Rguieg, Nadia Cherradi, Exploring a rare case of juvenile psammomatoid ossifying fibroma in the ethmoid: a case study and review, Journal of Surgical Case Reports , Volume 2024, Issue 4, April 2024, rjae242, https://doi.org/10.1093/jscr/rjae242

• Permissions Icon Permissions

Juvenile ossifying fibroma (JOF) and its variants, including juvenile psammomatoid ossifying fibroma (JPOF), represent rare yet clinically significant benign fibro-osseous lesions that primarily occur in children and young adolescents. They can be found in diverse anatomical sites such as the jaw, nasal cavity, paranasal sinuses, and orbit. JOF exhibits an aggressive nature, necessitating early radiological detection and surgical intervention. Similarly, JPOF, with a locally malignant potential, requires surgical removal, typically conducted through endoscopic approaches. We report a case of a 5-year-old girl with JPOF arising in the ethmoid, revealed by recurrent epistaxis and proptosis. The text emphasizes the importance of early diagnosis through histopathology as a diagnostic tool and underscores the need for appropriate management.

Juvenile ossifying fibroma (JOF) is a rare condition primarily observed in children and adolescents. This benign fibro-osseous tumor commonly occurs within the sinonasal region. Its distinctions from the conventional ossifying fibroma lie in the age of onset, anatomical site, locally aggressive behavior, and a notable propensity for recurrence. Clinical manifestations vary based on the tumor’s location, potentially presenting as nasal obstruction, facial swelling, or proptosis. The World Health Organization (WHO) classifies JOF into two main subtypes: juvenile trabecular ossifying fibroma and juvenile psammomatoid ossifying fibroma (JPOF) [ 1 ]. The psammomatoid subtype is a rare, benign tumor found in the head and neck region, often affecting children and young adults. It tends to develop in areas such as the nasal cavity, paranasal sinuses, or the orbit. Although typically non-cancerous, it may display locally aggressive behavior, potentially damaging nearby structures. Surgical removal is the preferred treatment, with either endoscopic or external approaches being considered, with a preference for the latter. Due to the risk of significant bleeding during surgery, precautions to secure blood products beforehand are essential [ 2 ].

This article outlines a case of JPOF diagnosed in a child.

A 5-year-old girl presented with progressive right eye proptosis and recurrent epistaxis over the past 6 months, along with a history of nasal obstruction persisting for several months. During the examination, non-axial proptosis was observed, and both extraocular movements and visual acuity were found to be intact.

Flexible nasofibroscopy revealed a protrusion filling the right nasal fossa, closely approaching the nasal septum. Computed tomography (CT) and magnetic resonance imaging scans indicated a well-defined osteolytic lesion with a peripheral sclerotic rind, measuring 4.1 × 3.8 × 3.7 cm and originating from the right ethmoid, expanding into the ipsilateral nasal cavity, orbit, and maxillary sinus ( Fig. 1 ).

CT showing an expansible, well-demarcated, osteolytic lesion with a peripheral sclerotic rind on the right side of the ethmoid bone, expanding into the ipsilateral nasal cavity, orbit, and maxillary sinus; (A) coronal CT scan; (B) axial CT scan.

Upon admission to the Ear, Nose, and Throat department, the patient underwent an initial Frozen Section procedure. The sample was promptly sent to the pathology laboratory for histological analysis. The findings indicated the presence of a benign mesenchymal tumor accompanied by roughly round-shaped calcifications. Given the potential for further complications, total tumor removal was deemed necessary to both prevent complications and establish a definitive histological diagnosis.

The pathology laboratory received a white to reddish fragmented tumor with an elastic to hard consistency. Histological examination disclosed a proliferation of spindle-shaped or ovoid cells with vesicular nuclei and rare mitotic figures. Cells were arranged in sheets, with numerous rounded purplish formations corresponding to psammomatous body-type calcifications. A few giant cells were also observed. The stroma of the tumor was fibrous and collagenous. No necrosis was found ( Fig. 2 ).

H&E staining of the pathological specimen at different magnifications shows a benign fibro-osseous proliferation characterized by a large number of spherical basophilic calcified entities with no osteoblastic rimming resembling psammoma bodies (arrowheads), within a fibroblastic stroma of uniform stellate or spindle-shaped cells; (A and B) low power magnifications; (C) x20 power magnification; (D) high power (x40) magnification.

Immunohistochemical studies were conducted, revealing that the tumor cells did not express Cytokeratin, CD34, S100, smooth and striatal muscle markers, MDM2, progesterone receptor (PR), or epithelial membrane antigen (EMA). Vimentin was diffusely expressed, with a very low ki67 proliferation index estimated at 4% ( Fig. 3 ).

Immunostaining reveals that the tumor tissue is (A) diffusely positive for Vimentin in the stromal component; (B) low Ki-67 proliferation index; (C and D) negative staining for EMA and CD34.

This case illustrates a typical clinical history, radiographic appearance, and classic histological findings of JPOF presented in the ethmoid.

JPOF predominantly affects younger individuals, with reported average ages ranging from 16 to 33 years. However, Malek’s review of 86 JPOF cases revealed an age range from 3 to 49 years, with a mean age of 17.7 years and a slight male predominance (1.2:1) [ 3–5 ]. This tumor is typically found in the nasal cavity, paranasal sinuses, orbits, or the fronto-ethmoid complex, with an exceedingly rare occurrence in the base or vault of the skull [ 6 ]. The primary clinical presentation often involves bony expansion, which is frequently observed. This expansion can manifest through a range of symptoms including proptosis, nasal obstruction, headaches, facial swelling, pain, and recurring sinus infections [ 7 ]. Additionally, it may exhibit an aggressive clinical course [ 8 ].

Radiologically, ossifying fibroma typically appears as a mass with a distinct border, unlike fibrous dysplasia. Moreover, ossifying fibroma lacks ground-glass opacity and instead exhibits a mixed density resembling both compact bone and fibrous tissue [ 9 ].While the appearance of the lesion on imaging might offer diagnostic insights, distinguishing it can be challenging due to its resemblances to other osteo-fibroid lesions within the facial skeleton [ 10 ].

Histologically, JPOF is characterized by a large number of spherical calcified entities with no osteoblastic rimming. Some of these calcifications have psammoma-like concentric lamellae with basophilic cores and an eosinophilic osteoid rim. The surrounding fibrous stroma is composed of loosely to densely collagenized tissue that contains a dense proliferation of fibroblast-like, spindle-shaped cells with hyperchromatic nuclei [ 11 ].

JPOF must be distinguished from other fibro-osseous lesions such as fibrous dysplasia, osteoblastoma, low-grade central osteosarcoma, and primary aneurysmal bone cyst. Additionally, it is important to consider intraosseous cavernous hemangioma and eosinophilic granuloma due to their similarities in radiological and histological features [ 6 , 12 ]. Misdiagnosis may occur with extracranial meningioma featuring psammoma bodies, which typically tests positive for EMA, unlike JPOF [ 7 ]. JPOF typically does not express S100 and CD34 [ 7 ].

Despite its benign and slow growth, this subtype exhibits local malignancy with a tendency to infiltrate surrounding structures. Therefore, accurate diagnosis is crucial, and treatment should involve complete tumor removal. Incomplete or partial resection is associated with a heightened recurrence risk [ 2 ].

Our report underscores the rarity of JPOF, focusing on its clinical, radiological, and primarily histological aspects. Despite its uncommon occurrence, JPOF poses diagnostic and management challenges due to its potential aggressiveness and recurrence. Histopathological examination remains pivotal for confirming the diagnosis, highlighting the importance of thorough evaluation and appropriate management guided by histological findings.

None declared.

No external funding sources were obtained for this submission.

No new data were generated or analyzed in support of this research.

Written informed consent for publication of their clinical details and/or clinical images was obtained from the patient.

El-Naggar AK , Chan JKC , Grandis JR , et al.  World Health Organization Classification of Tumours , 4th edn. Lyon, France : International Agency for Research on Cancer, 2017 , 251 – 2 .

Google Scholar

Google Preview

Kuźmińska M , Gotlib T , Niemczyk K . Juvenile psammomatoid ossifying fibroma–case report . Polski Przegląd Otorynolaryngologiczny 2021 ; 10 : 57 – 61 .

Chrcanovic BR , Gomez RS . Juvenile ossifying fibroma of the jaws and paranasal sinuses: a systematic review of the cases reported in the literature . Int J Oral Maxillofac Surg 2020 ; 49 : 28 – 37 .

Sarode SC , Sarode GS , Waknis P , et al.  Juvenile psammomatoid ossifying fibroma: a review . Oral Oncol 2011 ; 47 : 1110 – 6 .

Makek M . In: Karger S (ed). Clinical pathology of fibro-osteo-cemental lesions of the cranio-facial skeleton and jaw bones . Basel : Switzerland , 1983 , 128 – 227 .

López CB , Zabala AB , Bareño EU . Cranial juvenile psammomatoid ossifying fibroma: case report . J Neurosurg Pediatr 2016 ; 17 : 318 – 23 .

Wenig BM , Vinh TN , Smirniotopoulos JG , et al.  Aggressive psammomatoid ossifying fibromas of the sinonasal region: a clinicopathologic study of a distinct group of fibro-osseous lesions . Cancer 1995 ; 76 : 1155 – 65 .

Brademann G , Werner JA , Jänig U , et al.  Cemento-ossifying fibroma of the petromastoid region: case report and review of the literature . J Laryngol Otol 1997 ; 111 : 152 – 5 .

Sontakke SA , Karjodkar FR , Umarji HR . Computed tomographic features of fibrous dysplasia of maxillofacial region . Imaging Sci Dent 2011 ; 41 : 23 – 8 .

Bertrand B , Eloy P , Cornelis JP , et al.  Juvenile aggressive cemento-ossifying fibroma: case report and review of the literature . Laryngoscope 1993 ; 103 : 1385 – 90 .

Owosho AA , Hughes MA , Prasad JL , et al.  Psammomatoid and trabecular juvenile ossifying fibroma: two distinct radiologic entities . Oral Surg Oral Med Oral Pathol Oral Radiol 2014 ; 118 : 732 – 8 .

Nakajima R , Saito N , Uchino A , et al.  Juvenile psammomatoid ossifying fibroma with visual disturbance: a case report with imaging features . J Neuroimaging 2013 ; 23 : 137 – 40 .

Email alerts

Citing articles via, affiliations.

• Online ISSN 2042-8812
• Copyright © 2024 Oxford University Press and JSCR Publishing Ltd
• About Oxford Academic
• Publish journals with us
• University press partners
• What we publish
• New features  
• Open access
• Institutional account management
• Rights and permissions
• Get help with access
• Accessibility
• Advertising
• Media enquiries
• Oxford University Press
• Oxford Languages
• University of Oxford

Oxford University Press is a department of the University of Oxford. It furthers the University's objective of excellence in research, scholarship, and education by publishing worldwide

• Copyright © 2024 Oxford University Press
• Cookie settings
• Cookie policy
• Privacy policy
• Legal notice

This Feature Is Available To Subscribers Only

Sign In or Create an Account

This PDF is available to Subscribers Only

For full access to this pdf, sign in to an existing account, or purchase an annual subscription.

• Open access
• Published: 22 April 2024

The influence of maternal prepregnancy weight and gestational weight gain on the umbilical cord blood metabolome: a case–control study

• Xianxian Yuan   ORCID: orcid.org/0000-0001-8762-8471 1 ,
• Yuru Ma 1 ,
• Jia Wang 2 ,
• Yan Zhao 1 ,
• Wei Zheng 1 ,
• Ruihua Yang 1 ,
• Lirui Zhang 1 ,
• Xin Yan 1 &
• Guanghui Li   ORCID: orcid.org/0000-0003-2290-1515 1  

BMC Pregnancy and Childbirth volume  24 , Article number:  297 ( 2024 ) Cite this article

107 Accesses

Metrics details

Maternal overweight/obesity and excessive gestational weight gain (GWG) are frequently reported to be risk factors for obesity and other metabolic disorders in offspring. Cord blood metabolites provide information on fetal nutritional and metabolic health and could provide an early window of detection of potential health issues among newborns. The aim of the study was to explore the impact of maternal prepregnancy overweight/obesity and excessive GWG on cord blood metabolic profiles.

A case control study including 33 pairs of mothers with prepregnancy overweight/obesity and their neonates, 30 pairs of mothers with excessive GWG and their neonates, and 32 control mother-neonate pairs. Untargeted metabolomic profiling of umbilical cord blood samples were performed using UHPLC‒MS/MS.

Forty-six metabolites exhibited a significant increase and 60 metabolites exhibited a significant reduction in umbilical cord blood from overweight and obese mothers compared with mothers with normal body weight. Steroid hormone biosynthesis and neuroactive ligand‒receptor interactions were the two top-ranking pathways enriched with these metabolites ( P  = 0.01 and 0.03, respectively). Compared with mothers with normal GWG, in mothers with excessive GWG, the levels of 63 metabolites were increased and those of 46 metabolites were decreased in umbilical cord blood. Biosynthesis of unsaturated fatty acids was the most altered pathway enriched with these metabolites ( P  < 0.01).

Conclusions

Prepregnancy overweight and obesity affected the fetal steroid hormone biosynthesis pathway, while excessive GWG affected fetal fatty acid metabolism. This emphasizes the importance of preconception weight loss and maintaining an appropriate GWG, which are beneficial for the long-term metabolic health of offspring.

Peer Review reports

The obesity epidemic is an important public health problem in developed and developing countries [ 1 ] and is associated with the emergence of chronic noncommunicable diseases, including type 2 diabetes mellitus (T2DM), hypertension, cardiovascular disease, nonalcoholic fatty liver disease (NAFLD), and cancer [ 2 , 3 , 4 ]. Maternal obesity is the most common metabolic disturbance in pregnancy, and the prevalence of obesity among women of childbearing age is 7.1% ~ 31.9% in some countries [ 5 ]. In China, the prevalence of overweight and obesity has also increased rapidly in the past four decades. Based on Chinese criteria, the latest national prevalence estimates for 2015–2019 were 34.3% for overweight and 16.4% for obesity in adults (≥ 18 years of age) [ 6 ].

Increasing evidence implicates overnutrition in utero as a major determinant of the health of offspring during childhood and adulthood, which is compatible with the developmental origins of health and disease (DOHaD) framework [ 7 ]. Maternal obesity and excessive gestational weight gain (GWG) are important risk factors for several adverse maternal outcomes, including gestational diabetes and hypertensive disorders, fetal death, and preterm birth [ 8 , 9 , 10 ]. More importantly, they have negative implications for offspring, both perinatally and later in life. Evidence from cohort studies focusing on offspring development confirms the relationship between maternal obesity/excessive GWG and offspring obesity programming [ 11 , 12 , 13 ]. Currently, there is no unified mechanism to explain the adverse outcomes associated with maternal obesity and excessive GWG, which may be the independent and interactive effects of the obese maternal phenotype itself and the diet associated with this phenotype. In addition to genetic and environmental factors, metabolic programming may also lead to the intergenerational transmission of obesity through epigenetic mechanisms.

Metabolomics, which reflects the metabolic phenotype of human subjects and animals, is the profiling of metabolites in biofluids, cells and tissues using high-throughput platforms, such as mass spectrometry. It has unique potential in identifying biomarkers for predicting occurrence, severity, and progression of diseases, as well as exploring underlying mechanistic abnormalities [ 14 , 15 ]. Umbilical cord metabolites can provide information about fetal nutritional and metabolic health, and may provide an early window for detection of potential health issues in newborns [ 16 ]. Previous studies have reported differences in umbilical cord metabolite profiles associated with maternal obesity [ 17 , 18 ]. However, the results were inconsistent due to differences in sample sizes, ethnicity and region, and mass spectrometry. In addition, most studies have not considered the difference in the effects of prepregnancy body mass index (BMI) and GWG on cord blood metabolites.

To investigate the relationship between early metabolic programming and the increased incidence of metabolic diseases in offspring, we studied the associations between elevated prepregnancy BMI/excessive GWG and umbilical cord metabolic profiles. Another purpose of this study was to explore whether there were differences in the effects of prepregnancy overweight/obesity and excessive GWG on cord blood metabolites.

Study population

This was a hospital-based, case control study that included singleton pregnant women who received prenatal care and delivered vaginally at Beijing Obstetrics and Gynecology Hospital, Capital Medical University, from January 2022 to March 2022. We selected 33 pregnant women with a prepregnancy BMI ≥ 24.0 kg/m 2 regardless of their gestational weight gain as the overweight/obese group, 30 pregnant women with a prepregnancy BMI of 18.5–23.9 kg/m 2 and a GWG > 14.0 kg as the excessive GWG group, and 32 pregnant women with a BMI of 18.5–23.9 kg/m 2 and a GWG of 8.0–14.0 kg as the control group. The ages of the three groups were matched (± 1.0 years), and the prepregnancy BMIs of the excessive GWG and control groups were matched (± 1.0 kg/m 2 ).

The inclusion criteria were women with singleton pregnancies, those aged between 20 and 45 years, those with full-term delivery (gestational age ≥ 37 weeks), those with a prepregnancy BMI ≥ 18.5 kg/m 2 , those without prepregnancy diabetes mellitus (DM) or hypertension, and those without gestational diabetes mellitus (GDM). The exclusion criteria were women with multiple pregnancies, those less than 20 years or more than 45 years old, those with a prepregnancy BMI < 18.5 kg/m 2 , those with prepregnancy DM, hypertension or GDM, and those without cord blood samples.

We classified pregnant women into BMI categories based on Chinese guidelines [ 19 ]: normal weight (prepregnancy BMI 18.5–23.9 kg/m 2 ), overweight (prepregnancy BMI 24.0–27.9 kg/m 2 ), and obese (prepregnancy BMI ≥ 28.0 kg/m 2 ). GWG guideline concordance was defined by the 2021 Chinese Nutrition Society recommendations according to prepregnancy BMI. The upper limits of GWG for normal weight, overweight, and obesity were 14.0 kg, 11.0 kg, and 9.0 kg, respectively.

Ethical approval and written informed consent were obtained from all participants. The study has been performed according to the Declaration of Helsinki, and the procedures have been approved by the ethics committees of Beijing Obstetrics and Gynecology Hospital, Capital Medical University (2021-KY-037).

Sample and data collection

Maternal and neonatal clinical data were collected from the electronic medical records system of Beijing Obstetrics and Gynecology Hospital. Maternal clinical characteristics included age, height, prepregnancy and predelivery weight, education level, smoking and drinking status during pregnancy, parity, conception method, comorbidities and complications of pregnancy, family history of DM and hypertension, gestational age, mode of delivery, and biochemical results during pregnancy. Prepregnancy BMI was calculated as prepregnancy weight in kilograms divided by the square of height in meters. GWG was determined by subtracting the prepregnancy weight in kilograms from the predelivery weight in kilograms. GDM was defined using the IAPDSG’s diagnostic criteria at 24 to 28 +6  weeks gestation and the fasting glucose and 1- and 2-h glucose concentrations at the time of the oral glucose tolerance test (OGTT). Neonatal clinical characteristics included sex, birth weight and length. Macrosomia was defined as a birth weight of 4,000 g or more [ 20 ]. Low birth weight (LBW) was defined as a birth weight less than 2,500 g [ 21 ].

Umbilical cord blood samples were obtained by trained midwives after clamping the cord at delivery. Whole blood samples were collected in EDTA tubes, refrigerated for < 24 h, and centrifuged at 2,000 r.p.m. at 4 ℃ for 10 min. Plasma aliquots were stored at -80 ℃ until shipment on dry ice to Novogene, Inc. (Beijing, China) for untargeted metabolomic analysis.

Untargeted metabolomic analyses

Ultrahigh-performance liquid chromatography tandem mass spectrometry (UHPLC‒MS/MS) analyses were performed using a Vanquish UHPLC system (Thermo Fisher, Germany) coupled with an Orbitrap Q Exactive™ HF mass spectrometer (Thermo Fisher, Germany) at Novogene Co., Ltd. (Beijing, China). Detailed descriptions of the sample preparation, mass spectrometry and automated metabolite identification procedures are described in the Supplementary materials .

Statistical analysis

Clinical data statistical analysis.

Quantitative data are shown as the mean ± standard deviation (SD) or median (interquartile range), and categorical data are presented as percentages. The Mann‒Whitney U test, chi-square test, and general linear repeated-measures model were used to assess the differences between the control and study groups when appropriate. A P value < 0.05 was considered statistically significant. All analyses were performed using Statistical Package of Social Sciences version 25.0 (SPSS 25.0) for Windows (SPSS Inc).

Umbilical cord metabolome statistical analysis

These metabolites were annotated using the Human Metabolome Database (HMDB) ( https://hmdb.ca/metabolites ), LIPIDMaps database ( http://www.lipidmaps.org/ ), and Kyoto Encylopaedia of Genes and Genomes (KEGG) database ( https://www.genome.jp/kegg/pathway.html ). Principal component analysis (PCA) and partial least-squares discriminant analysis (PLS-DA) were performed at metaX. We applied univariate analysis ( T test) to calculate the statistical significance ( P value). Metabolites with a variable importance for the projection (VIP) > 1, a P value < 0.05 and a fold change (FC) ≥ 2 or FC ≤ 0.5 were considered to be differential metabolites. A false discovery rate (FDR) control was implemented to correct for multiple comparisons. The q -value in the FDR control was defined as the FDR analog of the P -value. In this study, the q -value was set at 0.2. For clustering heatmaps, the data were normalized using z scores of the intensity areas of differential metabolites and were plotted by the Pheatmap package in R language.

The correlations among differential metabolites were analyzed by cor () in R language (method = Pearson). Statistically significant correlations among differential metabolites were calculated by cor.mtest () in R language. A P value < 0.05 was considered statistically significant, and correlation plots were plotted by the corrplot package in R language. The functions of these metabolites and metabolic pathways were studied using the KEGG database. The metabolic pathway enrichment analysis of differential metabolites was performed when the ratio was satisfied by x/n > y/N, and the metabolic pathway was considered significantly enriched when P  < 0.05.

Demographic characteristics of study participants

The demographic and clinical characteristics of the three population groups enrolled in the study are summarized in Table  1 . Mothers had no significant difference regarding their ages or gestational ages. Compared to the mothers in the excessive GWG and control groups, those in the prepregnancy overweight/obesity group had a significantly higher prepregnancy BMI (25.6 (24.5, 27.2) kg/m 2 ). However, there was no significant difference in prepregnancy BMI between mothers in the excessive GWG group (20.3 ± 1.2 kg/m 2 ) and mothers in the control group (20.6 ± 1.5 kg/m 2 ). Mothers in the excessive GWG group had the highest GWG (17.0 (15.5, 19.1) kg) among the three groups. The mean GWG of the mothers in the prepregnancy overweight/obesity group was 12.9 ± 3.8 kg, which was similar to that of the control group (11.8 ± 1.5 kg). It was noteworthy that among the 33 prepregnancy overweight/obese pregnant women, 20 of them had appropriate GWG, 1 had insufficient GWG, and 12 had excessive GWG. The proportion of mothers who underwent invitro fertilization and embryo transfer (IVF-ET) in the prepregnancy overweight/obesity group (15.2%) was significantly higher than that in the excessive GWG and control groups. There were no statistically significant differences in the proportions of pregnancy outcomes among the three groups, including preeclampsia, premature rupture of membranes, postpartum hemorrhage, macrosomia, and LBW. The babies in the three groups showed no significant difference regarding their birth weights or lengths.

The biochemical parameters of the mothers during pregnancy are shown in Table  2 . The levels of triglyceride (TG) and uric acid (UA) of mothers in the prepregnancy overweight/obesity group were significantly higher than those of the mothers in the excessive GWG and control groups in the first trimester. However, there was no significant difference in the blood glucose and lipid levels in the second and third trimesters of pregnancy among the three groups.

PCA and PLS-DA analysis of cord blood metabolites

Functional and taxonomic annotations of the identified metabolites included the HMDB classification annotations, LIPID MAPS classification annotations, and KEGG pathway annotations. Those cord blood metabolites included lipids and lipid-like molecules, organic acids and their derivatives, and organoheterocyclic compounds, which were mainly involved in metabolism. To better understand the structure of the cord blood metabolome in cases versus controls, we used unsupervised PCA to identify metabolites contributing the most to observed differences in the dataset. PCA did not clearly separate the three groups. We next used PLS-DA to identify metabolites that were predictive of case versus control status. PLS-DA clearly distinguished the cases from the controls (Fig.  1 ), the prepregnancy overweight/obesity group vs. the control group (R2Y = 0.82, Q2Y = 0.37; R2Y = 0.77, Q2Y = 0.13, respectively) (Fig.  1 A), and the excessive GWG group vs. the control group (R2Y = 0.76, Q2Y = 0.16; R2Y = 0.81, Q2Y = 0.41) (Fig.  1 B).

PLS-DA of identified cord blood metabolites. A the prepregnancy overweight/obesity group vs. the control group; B the excessive GWG group vs. the control group. (a) PLS-DA score. The horizontal coordinates are the score of the sample on the first principal component; the longitudinal coordinates are the score of the sample on the second principal component; R2Y represents the interpretation rate of the model, and Q2Y is used to evaluate the predictive ability of the PLS-DA model, and when R2Y is greater than Q2Y, it means that the model is well established. (b) PLS-DA valid. Horizontal coordinates represent the correlation between randomly grouped Y and the original group Y, and vertical coordinates represent the scores of R2 and Q2. (1) POS, positive metabolites; (2) NEG, negative metabolites

Maternal prepregnancy overweight/obesity

Screening differential metabolites according to a PLS-DA VIP > 1.0, a FC > 1.2 or < 0.833 and a P value < 0.05, a total of 106 cord blood metabolites (77 positive metabolites and 29 negative metabolites) differed between the prepregnancy overweight/obesity group and the control group. Compared with those in the control group, the levels of 46 metabolites (19 positive metabolites and 27 negative metabolites) were increased in the prepregnancy overweight/obesity group, among which octopamine was the metabolite with the largest increase, followed by (2S)-4-Oxo-2-phenyl-3,4-dihydro-2H-chromen-7-yl beta-D-glucopyranoside, N-tetradecanamide, stearamide, and methanandamide (Fig.  2 A). Compared with the control group, in the prepregnancy overweight/obesity group, there were 60 metabolites (58 positive metabolites and 2 negative metabolites) with reduced concentrations, among which senecionine was the metabolite with the largest decrease, followed by 3-(methylsulfonyl)-2H-chromen-2-one, methyl EudesMate, cuminaldehyde, and 2-(tert-butyl)-1,3-thiazolane-4-carboxylic acid (Fig.  2 A).

Stem plots of differential cord blood metabolites. A the prepregnancy overweight/obesity group vs. the control group; B the excessive GWG group vs. the control group. (1) positive metabolites; (2) negative metabolites. Notes: The color of the dot in the stem plots represents the upward and lower adjustment, the blue represents downward, and the red represents upward. The length of the rod represents the size of log2 (FC), and the size of the dot represents the size of the VIP value

A hierarchical analysis of the two groups of differential metabolites obtained was carried out, and the difference in metabolic expression patterns between the two groups and within the same comparison was obtained, which is shown in Fig.  3 . KEGG pathway analysis of differential cord blood metabolites associated with the prepregnancy overweight/obesity group versus the control group is shown in Table  3 and Fig.  4 A. The metabolite enrichment analysis revealed that steroid hormone biosynthesis ( P value = 0.01) and neuroactive ligand‒receptor interactions ( P value = 0.03) were the two pathways that were most altered between the prepregnancy overweight/obesity group and the control group. 19 metabolites were distributed in the pathway of steroid hormone biosynthesis, and 4 metabolites were distributed in the pathway of neuroactive ligand‒receptor interactions. In the steroid hormone biosynthesis pathway, the levels of corticosterone, 11-deoxycortisol, cortisol, testosterone, and 7α-hydroxytestosterone were decreased in the prepregnancy overweight/obesity group relative to those in the control group. In the neuroactive ligand‒receptor interaction pathway, the level of cortisol was decreased and the levels of trace amines were increased in the prepregnancy overweight/obesity group relative to the control group.

Clustering heat maps of differential cord blood metabolites of the three groups. A positive metabolites; B negative metabolites. Notes: Longitudinal clustering of samples and trans-verse clustering of metabolites. The shorter the clustering branches, the higher the similarity. Through horizontal comparison, we can see the relationship between groups of metabolite content clustering

KEGG enrichment scatterplots (a) and net (b) of differential cord blood metabolites. A the prepregnancy overweight/obesity group vs. the control group; B the excessive GWG group vs. the control group. (1) positive metabolites; (2) negative metabolites. Notes: (a) The horizontal co-ordinates in the figure are x/y (the number of differential metabolites in the corresponding metabolic pathway/the total number of total metabolites identified in this pathway). The value represents the enrichment degree of differential metabolites in the pathway. The color of the point rep-resents the P -value of the hypergeometric test, and the size of the point represents the number of differential metabolites in the corresponding pathway. (b) The red dot represents a metabolic pathway, the yellow dot represents a substance-related regulatory enzyme information, the green dot represents the background substance of a metabolic pathway, the purple dot represents the molecular module information of a class of substances, the blue dot represents a substance chemical reaction, and the green square represents the differential substance obtained by this comparison

Maternal excessive GWG

A total of 109 cord blood metabolites (52 positive metabolites and 57 negative metabolites) differed between the excessive GWG group and the control group. Compared with the control group, in the excessive GWG group, there were 63 metabolites (15 positive metabolites and 48 negative metabolites) with increased concentrations, among which 2-thio-acetyl MAGE was the metabolite with the largest increase, followed by PC (7:0/8:0), lysopc 16:2 (2 N isomer), MGMG (18:2), and thromboxane B2 (Fig.  2 B). Compared with the levels in the control group, the levels of 46 metabolites (37 positive metabolites and 9 negative metabolites) in the excessive GWG group were reduced, among which hippuric acid had the largest decrease, followed by 8-hydroxyquinoline, gamithromycin, 2-phenylglycine, and cefmetazole (Fig.  2 B).

A hierarchical analysis of differential metabolites obtained in the two groups was carried out, and the difference in metabolic expression patterns between the two groups and within the same comparison was obtained, which is shown in Fig.  3 . KEGG pathway analysis of the cord blood metabolites associated with the excessive GWG group versus the control group is shown in Table  4 and Fig.  4 B. The metabolite enrichment analysis revealed that biosynthesis of unsaturated fatty acids was the most altered pathway between the excessive GWG and control groups ( P value < 0.01). There were 13 metabolites distributed in the enriched pathway. The levels of docosapentaenoic acid (DPA), docosahexaenoic acid (DHA), arachidonic acid, adrenic acid, palmitic acid, stearic acid, behenic acid, lignoceric acid, and erucic acid were increased in the excessive GWG group relative to those in the control group.

Our present study found that both maternal prepregnancy overweight/obesity and excessive GWG could affect umbilical cord blood metabolites, and they had different effects on these metabolites. Regardless of their gestational weight gain, the umbilical cord blood of prepregnancy overweight and obese mothers had 46 metabolites increased and 60 metabolites decreased compared with the umbilical cord blood of mothers with normal body weight and appropriate GWG. Steroid hormone biosynthesis and neuroactive ligand‒receptor interactions were the two top-ranking pathways enriched with these metabolites. Compared with mothers with normal prepregnancy BMI and appropriate GWG, in mothers with normal prepregnancy BMI but excessive GWG, the levels of 63 metabolites were increased and those of 46 metabolites were decreased in umbilical cord blood. Biosynthesis of unsaturated fatty acids was the most altered pathway enriched with these metabolites.

There were many differential metabolites in the cord blood between the prepregnancy overweight/obesity group and the control group and between the excessive GWG group and the control group. However, the roles of most of these differential metabolites are unknown. The levels of stearamide and methanandamide were increased in the prepregnancy overweight/obesity group. Stearamide, also known as octadecanamide or kemamide S, belongs to the class of organic compounds known as carboximidic acids. Stearamide, which is increased in the serum of patients with hepatic cirrhosis and sepsis, may be associated with the systemic inflammatory state [ 22 , 23 ]. Methanandamide is a stable analog of anandamide that participates in energy balance mainly by activating cannabinoid receptors. Methanandamide dose-dependently inhibits and excites tension-sensitive gastric vagal afferents (GVAs), which play a role in appetite regulation [ 24 ]. In mice fed a high-fat diet, only an inhibitory effect of methanandamide was observed, and GVA responses to tension were dampened [ 24 , 25 ]. These changes may contribute to the development and/or maintenance of obesity. Moreover, methanandamide can produce dose-related hypothermia and attenuate cocaine-induced hyperthermia by a cannabinoid 1-dopamine D2 receptor mechanism [ 26 ].

Metabolomic pathway analysis of the cord blood metabolite features in the prepregnancy overweight and obesity group identified two filtered significant pathways: steroid hormone biosynthesis and neuroactive ligand‒receptor interaction pathways. In the steroid hormone biosynthesis pathway, the levels of several glucocorticoids (including corticosterone, 11-deoxycortisol, cortisol, testosterone, and 7α-hydroxytestosterone) were decreased in the prepregnancy overweight/obesity group. In addition to the physiological role of glucocorticoids in the healthy neuroendocrine development and maturation of fetuses and babies, glucocorticoids are essential to human health by regulating different physiological events in mature organs and tissues, such as glucose metabolism, lipid biosynthesis and distribution, food intake, thermogenesis, and mood and learning patterns [ 27 ]. Glucocorticoids have been considered as a link between adverse early-life conditions and the development of metabolic disorders in later life [ 28 , 29 , 30 ]. However, there is still much controversy regarding the role of maternal obesity in the fetal–steroid hormone biosynthesis pathway. Studies of maternal obesity animal models showed that corticosterone and cortisol levels were increased in the offspring of obese mothers [ 31 , 32 ]. A study reported by Satu M Kumpulainen et al. showed that young adults born to mothers with higher early pregnancy BMIs show lower average levels of diurnal cortisol, especially in the morning [ 33 ]. Laura I. Stirrat et al. found that increased maternal BMI was associated with lower maternal cortisol, corticosterone, and 11-dehydrocorticosterone levels. However, there were no associations between maternal BMI and glucocorticoid levels in the cord blood [ 34 ]. The differences in the study protocols of these previous studies may explain the mixed findings, such as cortisol measured from peripheral blood, cord blood or saliva; variation in measurement time points; the number of samples. Although the effect of maternal obesity on fetal steroid hormone levels is controversial, dysregulation of glucocorticoids may be a plausible mechanism by which maternal obesity can increase the risk of metabolic disorders and mental health disorders in offspring.

The effect of excessive GWG on umbilical cord blood metabolites is different from that of maternal overweight and obesity. Compared with the control group, in the excessive GWG group, the level of thromboxane B2 was increased and the level of hippuric acid was decreased. Thromboxane B2, which is important in the platelet release reaction, is a stable, physiologically active compound formed in vivo from prostaglandin endoperoxides. Hippuric acid is an acyl glycine formed from the conjugation of benzoic acid with glycine. Several studies have confirmed that both thromboxane B2 and hippuric acid levels are associated with diet. Dietary fatty acids affect platelet thromboxane production [ 35 , 36 , 37 ]. In our study, several fatty acids (e.g., palmitic acid, stearic acid, behenic acid, and lignoceric acid) in the excessive GWG group were also increased, which may have led to the increase in thromboxane B2 levels. Hippuric acid can be detected after the consumption of whole grains and anthocyanin-rich bilberries [ 38 , 39 ]. A healthy diet intervention increased the signals for hippuric acid to incorporate polyunsaturated fatty acids [ 38 ], and the low level of hippuric acid was associated with lower fruit-vegetable intakes [ 39 ]. Maternal overnutrition and unhealthy dietary patterns are the main reasons for excessive GWG [ 40 , 41 ]. Therefore, we speculated that the differences in thromboxane B2 and hippuric acid between the excessive GWG and control groups were associated with maternal diet during pregnancy. The effect of these differential metabolites on the long-term metabolic health of offspring after birth needs further study.

Metabolomic pathway analysis of the cord blood metabolite features in the excessive GWG group identified that biosynthesis of unsaturated fatty acids was the filtered significant pathway. The levels of several fatty acids in this pathway were increased in the excessive GWG group, including long-chain saturated fatty acids (e.g., palmitic acid (C 16:0), stearic acid (C 18:0), behenic acid (C 22:0), and lignoceric acid (C 23:0)), monounsaturated fatty acids (erucic acid), and polyunsaturated fatty acids (e.g., DPA, DHA, arachidonic acid, and adrenic acid). Because perinatal fatty acid status can be influenced by maternal dietary modifications or supplementation [ 42 ], we speculated that maternal diet during pregnancy caused the difference in umbilical cord blood fatty acids between the excessive GWG and control groups. A large body of evidence from mechanistic studies supports the potential of fatty acids to influence later obesity. However, the possible mechanisms and observed relationships are complex and related to the types and patterns of fatty acids [ 43 , 44 ]. Maternal dietary fatty acids have been found to induce hypothalamic inflammation, cause epigenetic changes, and alter the mechanisms of energy control in offspring [ 43 ]. Evidence from cell culture and rodent studies showed that polyunsaturated fatty acids might serve several complex roles in fetuses, including the stimulation and/or inhibition regulation of adipocyte differentiation [ 44 ]. The questions of whether lower n-6 long-chain polyunsaturated fatty acid levels or higher n-3 long-chain polyunsaturated fatty acid levels are of more relevance and whether the long-term effects differ with different offspring ages remain [ 44 ]. Although there is a biologically plausible case for the relevance of perinatal fatty acid status in later obesity risk, available data in humans suggest that the influence of achievable modification of perinatal n-3/n-6 status is not sufficient to influence offspring obesity risk in the general population [ 45 ]. Further studies seem justified to clarify the reasons.

The advantage of our present study is that we simultaneously analyzed the effects of prepregnancy overweight/obesity and excessive GWG on cord blood metabolites and explored their differences. In addition, to exclude the effect of hyperglycemia on cord blood metabolites, both women with prepregnancy diabetes mellitus and gestational diabetes mellitus were excluded from our study. The limitation of our study is that it was a single-center study with a small sample, especially in the prepregnancy overweight/obesity group. In the future, we can expand the sample size and conduct a subgroup analysis of the prepregnancy overweight/obesity group and analyze the differences in the effects of different degrees of obesity on cord blood metabolites. The prepregnancy overweight/obesity group can be further divided into an appropriate GWG group and an excessive GWG group, and the differences in the effects of these two groups on umbilical cord blood metabolites can be analyzed. Moreover, the dietary pattern of the pregnant woman could affect the production of cord blood metabolites. We did not investigate the dietary patterns of the mothers in this study, which is another limitation of this study. In future studies, we should investigate maternal dietary patterns as a very important confounding variable.

In conclusion, our present study confirmed that both prepregnancy overweight/obesity and excessive GWG could affect umbilical cord blood metabolites, and they had different effects on these metabolites. Prepregnancy overweight and obesity affected the fetal steroid hormone biosynthesis pathway, while normal prepregnancy body weight but excessive GWG affected fetal fatty acid metabolism. This emphasizes the importance of preconception weight loss and maintaining an appropriate GWG, which are beneficial for the long-term metabolic health of offspring.

Availability of data and materials

Data sets generated during the current study are not publicly available but will be available from the corresponding author at a reasonable request. Responses to the request for the raw data will be judged by a committee including XXY and GHL.

Abbreviations

Excessive gestational weight gain

Ultrahigh-performance liquid chromatography tandem mass spectrometry

Type 2 diabetes mellitus

Nonalcoholic fatty liver disease

The developmental origins of health and disease

Body mass index

Diabetes mellitus

Gestational diabetes mellitus

Oral glucose tolerance test

Low birth weight

Standard deviation

The Human Metabolome Database

Kyoto Encylopaedia of Genes and Genomes

Principal component analysis

Partial least-squares discriminant analysis

Importance for the projection

Fold change

Invitro fertilization and embryo transfer

Triglyceride

Docosapentaenoic acid

Docosahexaenoic acid

Gastric vagal afferents

Collaborators GBDO, Afshin A, Forouzanfar MH, Reitsma MB, Sur P, Estep K, Lee A, Marczak L, Mokdad AH, Moradi-Lakeh M, et al. Health effects of overweight and obesity in 195 countries over 25 years. N Engl J Med. 2017;377(1):13–27.

Article   Google Scholar  

Bjerregaard LG, Jensen BW, Angquist L, Osler M, Sorensen TIA, Baker JL. Change in overweight from childhood to early adulthood and risk of type 2 diabetes. N Engl J Med. 2018;378(14):1302–12.

Article   PubMed   Google Scholar  

Sharma V, Coleman S, Nixon J, Sharples L, Hamilton-Shield J, Rutter H, Bryant M. A systematic review and meta-analysis estimating the population prevalence of comorbidities in children and adolescents aged 5 to 18 years. Obes Rev. 2019;20(10):1341–9.

Article   PubMed   PubMed Central   Google Scholar  

Llewellyn A, Simmonds M, Owen CG, Woolacott N. Childhood obesity as a predictor of morbidity in adulthood: a systematic review and meta-analysis. Obes Rev. 2016;17(1):56–67.

Article   CAS   PubMed   Google Scholar  

Poston L, Caleyachetty R, Cnattingius S, Corvalan C, Uauy R, Herring S, Gillman MW. Preconceptional and maternal obesity: epidemiology and health consequences. Lancet Diabetes Endocrinol. 2016;4(12):1025–36.

Pan XF, Wang L, Pan A. Epidemiology and determinants of obesity in China. Lancet Diabetes Endocrinol. 2021;9(6):373–92.

Barker DJ. The developmental origins of adult disease. J Am Coll Nutr. 2004;23(6 Suppl):588S-595S.

LifeCycle Project-Maternal O, Childhood Outcomes Study G, Voerman E, Santos S, Inskip H, Amiano P, Barros H, Charles MA, Chatzi L, Chrousos GP, et al. Association of gestational weight gain with adverse maternal and infant outcomes. JAMA. 2019;321(17):1702–15.

Aune D, Saugstad OD, Henriksen T, Tonstad S. Maternal body mass index and the risk of fetal death, stillbirth, and infant death: a systematic review and meta-analysis. JAMA. 2014;311(15):1536–46.

Ukah UV, Bayrampour H, Sabr Y, Razaz N, Chan WS, Lim KI, Lisonkova S. Association between gestational weight gain and severe adverse birth outcomes in Washington State, US: a population-based retrospective cohort study, 2004–2013. PLoS Med. 2019;16(12):e1003009.

Starling AP, Brinton JT, Glueck DH, Shapiro AL, Harrod CS, Lynch AM, Siega-Riz AM, Dabelea D. Associations of maternal BMI and gestational weight gain with neonatal adiposity in the Healthy Start study. Am J Clin Nutr. 2015;101(2):302–9.

Voerman E, Santos S, Patro Golab B, Amiano P, Ballester F, Barros H, Bergstrom A, Charles MA, Chatzi L, Chevrier C, et al. Maternal body mass index, gestational weight gain, and the risk of overweight and obesity across childhood: an individual participant data meta-analysis. PLoS Med. 2019;16(2):e1002744.

Heslehurst N, Vieira R, Akhter Z, Bailey H, Slack E, Ngongalah L, Pemu A, Rankin J. The association between maternal body mass index and child obesity: a systematic review and meta-analysis. PLoS Med. 2019;16(6):e1002817.

Newgard CB. Metabolomics and metabolic diseases: where do we stand? Cell Metab. 2017;25(1):43–56.

Johnson CH, Ivanisevic J, Siuzdak G. Metabolomics: beyond biomarkers and towards mechanisms. Nat Rev Mol Cell Biol. 2016;17(7):451–9.

Article   CAS   PubMed   PubMed Central   Google Scholar  

Hivert MF, Perng W, Watkins SM, Newgard CS, Kenny LC, Kristal BS, Patti ME, Isganaitis E, DeMeo DL, Oken E, et al. Metabolomics in the developmental origins of obesity and its cardiometabolic consequences. J Dev Orig Health Dis. 2015;6(2):65–78.

Schlueter RJ, Al-Akwaa FM, Benny PA, Gurary A, Xie G, Jia W, Chun SJ, Chern I, Garmire LX. Prepregnant obesity of mothers in a multiethnic cohort is associated with cord blood metabolomic changes in offspring. J Proteome Res. 2020;19(4):1361–74.

Shokry E, Marchioro L, Uhl O, Bermudez MG, Garcia-Santos JA, Segura MT, Campoy C, Koletzko B. Impact of maternal BMI and gestational diabetes mellitus on maternal and cord blood metabolome: results from the PREOBE cohort study. Acta Diabetol. 2019;56(4):421–30.

Chen C, Lu FC, Department of Disease Control Ministry of Health PRC. The guidelines for prevention and control of overweight and obesity in Chinese adults. Biomed Environ Sci. 2004;17(Suppl):1–36.

PubMed   Google Scholar  

The American College of Obstetricians and Gynecologists. Macrosomia: ACOG practice bulletin, number 216. Obstet Gynecol. 2020;135(1):e18–e35.

Goldenberg RL, Culhane JF. Low birth weight in the United States. Am J Clin Nutr. 2007;85(2):584S-590S.

Lian JS, Liu W, Hao SR, Guo YZ, Huang HJ, Chen DY, Xie Q, Pan XP, Xu W, Yuan WX, et al. A serum metabonomic study on the difference between alcohol- and HBV-induced liver cirrhosis by ultraperformance liquid chromatography coupled to mass spectrometry plus quadrupole time-of-flight mass spectrometry. Chin Med J (Engl). 2011;124(9):1367–73.

CAS   PubMed   Google Scholar  

Ding W, Xu S, Zhou B, Zhou R, Liu P, Hui X, Long Y, Su L. Dynamic plasma lipidomic analysis revealed cholesterol ester and amides associated with sepsis development in critically Ill patients after cardiovascular surgery with cardiopulmonary bypass. J Pers Med. 2022;12(11):1838.

Christie S, O’Rielly R, Li H, Nunez-Salces M, Wittert GA, Page AJ. Modulatory effect of methanandamide on gastric vagal afferent satiety signals depends on nutritional status. J Physiol. 2020;598(11):2169–82.

Christie S, O’Rielly R, Li H, Wittert GA, Page AJ. High fat diet induced obesity alters endocannabinoid and ghrelin mediated regulation of components of the endocannabinoid system in nodose ganglia. Peptides. 2020;131:170371.

Rasmussen BA, Kim E, Unterwald EM, Rawls SM. Methanandamide attenuates cocaine-induced hyperthermia in rats by a cannabinoid CB1-dopamine D2 receptor mechanism. Brain Res. 2009;1260:7–14.

Facchi JC, Lima TAL, Oliveira LR, Costermani HO, Miranda GDS, de Oliveira JC. Perinatal programming of metabolic diseases: the role of glucocorticoids. Metabolism. 2020;104:154047.

Reynolds RM, Walker BR, Syddall HE, Andrew R, Wood PJ, Whorwood CB, Phillips DI. Altered control of cortisol secretion in adult men with low birth weight and cardiovascular risk factors. J Clin Endocrinol Metab. 2001;86(1):245–50.

Valtat B, Dupuis C, Zenaty D, Singh-Estivalet A, Tronche F, Breant B, Blondeau B. Genetic evidence of the programming of beta cell mass and function by glucocorticoids in mice. Diabetologia. 2011;54(2):350–9.

Jia Y, Li R, Cong R, Yang X, Sun Q, Parvizi N, Zhao R. Maternal low-protein diet affects epigenetic regulation of hepatic mitochondrial DNA transcription in a sex-specific manner in newborn piglets associated with GR binding to its promoter. PLoS ONE. 2013;8(5):e63855.

Rodriguez JS, Rodriguez-Gonzalez GL, Reyes-Castro LA, Ibanez C, Ramirez A, Chavira R, Larrea F, Nathanielsz PW, Zambrano E. Maternal obesity in the rat programs male offspring exploratory, learning and motivation behavior: prevention by dietary intervention pre-gestation or in gestation. Int J Dev Neurosci. 2012;30(2):75–81.

Tuersunjiang N, Odhiambo JF, Long NM, Shasa DR, Nathanielsz PW, Ford SP. Diet reduction to requirements in obese/overfed ewes from early gestation prevents glucose/insulin dysregulation and returns fetal adiposity and organ development to control levels. Am J Physiol Endocrinol Metab. 2013;305(7):E868-878.

Kumpulainen SM, Heinonen K, Kaseva N, Andersson S, Lano A, Reynolds RM, Wolke D, Kajantie E, Eriksson JG, Raikkonen K. Maternal early pregnancy body mass index and diurnal salivary cortisol in young adult offspring. Psychoneuroendocrinology. 2019;104:89–99.

Stirrat LI, Just G, Homer NZM, Andrew R, Norman JE, Reynolds RM. Glucocorticoids are lower at delivery in maternal, but not cord blood of obese pregnancies. Sci Rep. 2017;7(1):10263.

Prisco D, Filippini M, Francalanci I, Paniccia R, Gensini GF, Serneri GG. Effect of n-3 fatty acid ethyl ester supplementation on fatty acid composition of the single platelet phospholipids and on platelet functions. Metabolism. 1995;44(5):562–9.

Kaapa P, Uhari M, Nikkari T, Viinikka L, Ylikorkala O. Dietary fatty acids and platelet thromboxane production in puerperal women and their offspring. Am J Obstet Gynecol. 1986;155(1):146–9.

Teng KT, Chang CY, Kanthimathi MS, Tan AT, Nesaretnam K. Effects of amount and type of dietary fats on postprandial lipemia and thrombogenic markers in individuals with metabolic syndrome. Atherosclerosis. 2015;242(1):281–7.

Hanhineva K, Lankinen MA, Pedret A, Schwab U, Kolehmainen M, Paananen J, de Mello V, Sola R, Lehtonen M, Poutanen K, et al. Nontargeted metabolite profiling discriminates diet-specific biomarkers for consumption of whole grains, fatty fish, and bilberries in a randomized controlled trial. J Nutr. 2015;145(1):7–17.

Brunelli L, Davin A, Sestito G, Mimmi MC, De Simone G, Balducci C, Pansarasa O, Forloni G, Cereda C, Pastorelli R, et al. Plasmatic hippuric acid as a hallmark of frailty in an Italian cohort: the mediation effect of fruit-vegetable intake. J Gerontol A Biol Sci Med Sci. 2021;76(12):2081–9.

Ferreira LB, Lobo CV, Miranda A, Carvalho BDC, Santos LCD. Dietary patterns during pregnancy and gestational weight gain: a systematic review. Rev Bras Ginecol Obstet. 2022;44(5):540–7.

Tielemans MJ, Garcia AH, Peralta Santos A, Bramer WM, Luksa N, Luvizotto MJ, Moreira E, Topi G, de Jonge EA, Visser TL, et al. Macronutrient composition and gestational weight gain: a systematic review. Am J Clin Nutr. 2016;103(1):83–99.

Lewis RM, Wadsack C, Desoye G. Placental fatty acid transfer. Curr Opin Clin Nutr Metab Care. 2018;21(2):78–82.

Cesar HC, Pisani LP. Fatty-acid-mediated hypothalamic inflammation and epigenetic programming. J Nutr Biochem. 2017;42:1–6.

Demmelmair H, Koletzko B. Perinatal polyunsaturated fatty acid status and obesity risk. Nutrients. 2021;13(11):3882.

Hauner H, Brunner S. Early fatty acid exposure and later obesity risk. Curr Opin Clin Nutr Metab Care. 2015;18(2):113–7.

Download references

Acknowledgements

The authors thank the study participants for their involvement and research assistants for their help conducting the study.

This research was funded by the Beijing Natural Science Foundation, grant number 7214231.

Author information

Authors and affiliations.

Division of Endocrinology and Metabolism, Department of Obstetrics, Beijing Obstetrics and Gynecology Hospital, Capital Medical University, Beijing Maternal and Child Health Care Hospital, No. 251, Yaojiayuan Road, Chaoyang District, Beijing, 100026, China

Xianxian Yuan, Yuru Ma, Yan Zhao, Wei Zheng, Ruihua Yang, Lirui Zhang, Xin Yan & Guanghui Li

Department of Obstetrics and Gynecology, The Second Hospital of Jilin University, Changchun, 130041, Jilin, China

You can also search for this author in PubMed   Google Scholar

Contributions

XXY designed the study. XXY, WZ, LRZ and XY analyzed the data. YRM, JW, YZ and RHY took part in data collection and management. XXY wrote the manuscript. XXY and GHL reviewed the manuscript and contributed to manuscript revision. All authors contributed to the article and approved the submitted version. All authors reviewed the manuscript.

Corresponding author

Correspondence to Guanghui Li .

Ethics declarations

Ethics approval and consent to participate.

This study has been performed in accordance with the Declaration of Helsinki and has been approved by the ethics committee of Beijing Obstetrics and Gynecology Hospital, Capital Medical University (2021-KY-037). Informed consent was obtained from all subjects involved in the study to publish this paper. All methods were carried out in accordance with relevant guidelines and regulations in the declaration.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Supplementary material 1., rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Yuan, X., Ma, Y., Wang, J. et al. The influence of maternal prepregnancy weight and gestational weight gain on the umbilical cord blood metabolome: a case–control study. BMC Pregnancy Childbirth 24 , 297 (2024). https://doi.org/10.1186/s12884-024-06507-x

Download citation

Received : 30 September 2023

Accepted : 11 April 2024

Published : 22 April 2024

DOI : https://doi.org/10.1186/s12884-024-06507-x

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Maternal obesity
• Gestational weight gain
• Offspring health
• Metabolites
• Umbilical cord blood

BMC Pregnancy and Childbirth

ISSN: 1471-2393

• Submission enquiries: [email protected]
• General enquiries: [email protected]

• Skip to main content
• Keyboard shortcuts for audio player

• Your Health
• Treatments & Tests
• Health Inc.
• Public Health

Reproductive rights in America

What's at stake as the supreme court hears idaho case about abortion in emergencies.

Selena Simmons-Duffin

The Supreme Court will hear another case about abortion rights on Wednesday. Protestors gathered outside the court last month when the case before the justices involved abortion pills. Tom Brenner for The Washington Post/Getty Images hide caption

The Supreme Court will hear another case about abortion rights on Wednesday. Protestors gathered outside the court last month when the case before the justices involved abortion pills.

In Idaho, when a pregnant patient has complications, abortion is only legal to prevent the woman's death. But a federal law known as EMTALA requires doctors to provide "stabilizing treatment" to patients in the emergency department.

The Biden administration sees that as a direct conflict, which is why the abortion issue is back – yet again – before the Supreme Court on Wednesday.

The case began just a few weeks after the justices overturned Roe v. Wade in 2022, when the federal Justice Department sued Idaho , arguing that the court should declare that "Idaho's law is invalid" when it comes to emergency abortions because the federal emergency care law preempts the state's abortion ban. So far, a district court agreed with the Biden administration, an appeals court panel agreed with Idaho, and the Supreme Court allowed the strict ban to take effect in January when it agreed to hear the case.

Supreme Court allows Idaho abortion ban to be enacted, first such ruling since Dobbs

The case, known as Moyle v. United States (Mike Moyle is the speaker of the Idaho House), has major implications on everything from what emergency care is available in states with abortion bans to how hospitals operate in Idaho. Here's a summary of what's at stake.

1. Idaho physicians warn patients are being harmed

Under Idaho's abortion law , the medical exception only applies when a doctor judges that "the abortion was necessary to prevent the death of the pregnant woman." (There is also an exception to the Idaho abortion ban in cases of rape or incest, only in the first trimester of the pregnancy, if the person files a police report.)

In a filing with the court , a group of 678 physicians in Idaho described cases in which women facing serious pregnancy complications were either sent home from the hospital or had to be transferred out of state for care. "It's been just a few months now that Idaho's law has been in effect – six patients with medical emergencies have already been transferred out of state for [pregnancy] termination," Dr. Jim Souza, chief physician executive of St. Luke's Health System in Idaho, told reporters on a press call last week.

Those delays and transfers can have consequences. For example, Dr. Emily Corrigan described a patient in court filings whose water broke too early, which put her at risk of infection. After two weeks of being dismissed while trying to get care, the patient went to Corrigan's hospital – by that time, she showed signs of infection and had lost so much blood she needed a transfusion. Corrigan added that without receiving an abortion, the patient could have needed a limb amputation or a hysterectomy – in other words, even if she didn't die, she could have faced life-long consequences to her health.

Attorneys for Idaho defend its abortion law, arguing that "every circumstance described by the administration's declarations involved life-threatening circumstances under which Idaho law would allow an abortion."

Ryan Bangert, senior attorney for the Christian legal powerhouse Alliance Defending Freedom, which is providing pro-bono assistance to the state of Idaho, says that "Idaho law does allow for physicians to make those difficult decisions when it's necessary to perform an abortion to save the life of the mother," without waiting for patients to become sicker and sicker.

Still, Dr. Sara Thomson, an OB-GYN in Boise, says difficult calls in the hospital are not hypothetical or even rare. "In my group, we're seeing this happen about every month or every other month where this state law complicates our care," she says. Four patients have sued the state in a separate case arguing that the narrow medical exception harmed them.

"As far as we know, we haven't had a woman die as a consequence of this law, but that is really on the top of our worry list of things that could happen because we know that if we watch as death is approaching and we don't intervene quickly enough, when we decide finally that we're going to intervene to save her life, it may be too late," she says.

2. Hospitals are closing units and struggling to recruit doctors

Labor and delivery departments are expensive for hospitals to operate. Idaho already had a shortage of providers, including OB-GYNS. Hospital administrators now say the Idaho abortion law has led to an exodus of maternal care providers from the state, which has a population of 2 million people.

Three rural hospitals in Idaho have closed their labor-and-delivery units since the abortion law took effect. "We are seeing the expansion of what's called obstetrical deserts here in Idaho," said Brian Whitlock, president and CEO of the Idaho Hospital Association.

Since Idaho's abortion law took effect, nearly one in four OB-GYNs have left the state or retired, according to a report from the Idaho Physician Well-Being Action Collaborative. The report finds the loss of doctors who specialize in high-risk pregnancies is even more extreme – five of nine full time maternal-fetal medicine specialists have left Idaho.

Administrators say they aren't able to recruit new providers to fill those positions. "Since [the abortion law's] enactment, St. Luke's has had markedly fewer applicants for open physician positions, particularly in obstetrics. And several out-of-state candidates have withdrawn their applications upon learning of the challenges of practicing in Idaho, citing [the law's] enactment and fear of criminal penalties," reads an amicus brief from St. Luke's health system in support of the federal government.

"Prior to the abortion decision, we already ranked 50th in number of physicians per capita – we were already a strained state," says Thomson, the doctor in Boise. She's experienced the loss of OB-GYN colleagues first hand. "I had a partner retire right as the laws were changing and her position has remained open – unfilled now for almost two years – so my own personal group has been short-staffed," she says.

ADF's Bangert says he's skeptical of the assertion that the abortion law is responsible for this exodus of doctors from Idaho. "I would be very surprised if Idaho's abortion law is the sole or singular cause of any physician shortage," he says. "I'm very suspicious of any claims of causality."

3. Justices could weigh in on fetal "personhood"

The state of Idaho's brief argues that EMTALA actually requires hospitals "to protect and care for an 'unborn child,'" an argument echoed in friend-of-the-court briefs from the U.S. Conference of Catholic Bishops and a group of states from Indiana to Wyoming that also have restrictive abortion laws. They argue that abortion can't be seen as a stabilizing treatment if one patient dies as a result.

Thomson is also Catholic, and she says the idea that, in an emergency, she is treating two patients – the fetus and the mother – doesn't account for clinical reality. "Of course, as obstetricians we have a passion for caring for both the mother and the baby, but there are clinical situations where the mom's health or life is in jeopardy, and no matter what we do, the baby is going to be lost," she says.

The Idaho abortion law uses the term "unborn child" as opposed to the words "embryo" or "fetus" – language that implies the fetus has the same rights as other people.

Shots - Health News

The science of ivf: what to know about alabama's 'extrauterine children' ruling.

Mary Ziegler , a legal historian at University of California - Davis, who is writing a book on fetal personhood, describes it as the "North Star" of the anti-abortion rights movement. She says this case will be the first time the Supreme Court justices will be considering a statute that uses that language.

"I think we may get clues about the future of bigger conflicts about fetal personhood," she explains, depending on how the justices respond to this idea. "Not just in the context of this statute or emergency medical scenarios, but in the context of the Constitution."

ADF has dismissed the idea that this case is an attempt to expand fetal rights. "This case is, at root, a question about whether or not the federal government can affect a hostile takeover of the practice of medicine in all 50 states by misinterpreting a long-standing federal statute to contain a hidden nationwide abortion mandate," Bangert says.

4. The election looms large

Ziegler suspects the justices will allow Idaho's abortion law to remain as is. "The Supreme Court has let Idaho's law go into effect, which suggests that the court is not convinced by the Biden administration's arguments, at least at this point," she notes.

Trump backed a federal abortion ban as president. Now, he says he wouldn't sign one

Whatever the decision, it will put abortion squarely back in the national spotlight a few months before the November election. "It's a reminder on the political side of things, that Biden and Trump don't really control the terms of the debate on this very important issue," Zielger observes. "They're going to be things put on everybody's radar by other actors, including the Supreme Court."

The justices will hear arguments in the case on Wednesday morning. A decision is expected by late June or early July.

Correction April 23, 2024

An earlier version of this story did not mention the rape and incest exception to Idaho's abortion ban. A person who reports rape or incest to police can end a pregnancy in Idaho in the first trimester.

• Abortion rights
• Supreme Court

• Open access
• Published: 22 April 2024

Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study

• Kannan Sridharan 1 &
• Reginald P. Sequeira 1  

BMC Medical Education volume  24 , Article number:  431 ( 2024 ) Cite this article

424 Accesses

1 Altmetric

Metrics details

Artificial intelligence (AI) tools are designed to create or generate content from their trained parameters using an online conversational interface. AI has opened new avenues in redefining the role boundaries of teachers and learners and has the potential to impact the teaching-learning process.

In this descriptive proof-of- concept cross-sectional study we have explored the application of three generative AI tools on drug treatment of hypertension theme to generate: (1) specific learning outcomes (SLOs); (2) test items (MCQs- A type and case cluster; SAQs; OSPE); (3) test standard-setting parameters for medical students.

Analysis of AI-generated output showed profound homology but divergence in quality and responsiveness to refining search queries. The SLOs identified key domains of antihypertensive pharmacology and therapeutics relevant to stages of the medical program, stated with appropriate action verbs as per Bloom’s taxonomy. Test items often had clinical vignettes aligned with the key domain stated in search queries. Some test items related to A-type MCQs had construction defects, multiple correct answers, and dubious appropriateness to the learner’s stage. ChatGPT generated explanations for test items, this enhancing usefulness to support self-study by learners. Integrated case-cluster items had focused clinical case description vignettes, integration across disciplines, and targeted higher levels of competencies. The response of AI tools on standard-setting varied. Individual questions for each SAQ clinical scenario were mostly open-ended. The AI-generated OSPE test items were appropriate for the learner’s stage and identified relevant pharmacotherapeutic issues. The model answers supplied for both SAQs and OSPEs can aid course instructors in planning classroom lessons, identifying suitable instructional methods, establishing rubrics for grading, and for learners as a study guide. Key lessons learnt for improving AI-generated test item quality are outlined.

Conclusions

AI tools are useful adjuncts to plan instructional methods, identify themes for test blueprinting, generate test items, and guide test standard-setting appropriate to learners’ stage in the medical program. However, experts need to review the content validity of AI-generated output. We expect AIs to influence the medical education landscape to empower learners, and to align competencies with curriculum implementation. AI literacy is an essential competency for health professionals.

Peer Review reports

Artificial intelligence (AI) has great potential to revolutionize the field of medical education from curricular conception to assessment [ 1 ]. AIs used in medical education are mostly generative AI large language models that were developed and validated based on billions to trillions of parameters [ 2 ]. AIs hold promise in the incorporation of history-taking, assessment, diagnosis, and management of various disorders [ 3 ]. While applications of AIs in undergraduate medical training are being explored, huge ethical challenges remain in terms of data collection, maintaining anonymity, consent, and ownership of the provided data [ 4 ]. AIs hold a promising role amongst learners because they can deliver a personalized learning experience by tracking their progress and providing real-time feedback, thereby enhancing their understanding in the areas they are finding difficult [ 5 ]. Consequently, a recent survey has shown that medical students have expressed their interest in acquiring competencies related to the use of AIs in healthcare during their undergraduate medical training [ 6 ].

Pharmacology and Therapeutics (P & T) is a core discipline embedded in the undergraduate medical curriculum, mostly in the pre-clerkship phase. However, the application of therapeutic principles forms one of the key learning objectives during the clerkship phase of the undergraduate medical career. Student assessment in pharmacology & therapeutics (P&T) is with test items such as multiple-choice questions (MCQs), integrated case cluster questions, short answer questions (SAQs), and objective structured practical examination (OSPE) in the undergraduate medical curriculum. It has been argued that AIs possess the ability to communicate an idea more creatively than humans [ 7 ]. It is imperative that with access to billions of trillions of datasets the AI platforms hold promise in playing a crucial role in the conception of various test items related to any of the disciplines in the undergraduate medical curriculum. Additionally, AIs provide an optimized curriculum for a program/course/topic addressing multidimensional problems [ 8 ], although robust evidence for this claim is lacking.

The existing literature has evaluated the knowledge, attitude, and perceptions of adopting AI in medical education. Integration of AIs in medical education is the need of the hour in all health professional education. However, the academic medical fraternity facing challenges in the incorporation of AIs in the medical curriculum due to factors such as inadequate grounding in data analytics, lack of high-quality firm evidence favoring the utility of AIs in medical education, and lack of funding [ 9 ]. Open-access AI platforms are available free to users without any restrictions. Hence, as a proof-of-concept, we chose to explore the utility of three AI platforms to identify specific learning objectives (SLOs) related to pharmacology discipline in the management of hypertension for medical students at different stages of their medical training.

Study design and ethics

The present study is observational, cross-sectional in design, conducted in the Department of Pharmacology & Therapeutics, College of Medicine and Medical Sciences, Arabian Gulf University, Kingdom of Bahrain, between April and August 2023. Ethical Committee approval was not sought given the nature of this study that neither had any interaction with humans, nor collection of any personal data was involved.

Study procedure

We conducted the present study in May-June 2023 with the Poe© chatbot interface created by Quora© that provides access to the following three AI platforms:

Sage Poe [ 10 ]: A generative AI search engine developed by Anthropic © that conceives a response based on the written input provided. Quora has renamed Sage Poe as Assistant © from July 2023 onwards.

Claude-Instant [ 11 ]: A retrieval-based AI search engine developed by Anthropic © that collates a response based on pre-written responses amongst the existing databases.

ChatGPT version 3.5 [ 12 ]: A generative architecture-based AI search engine developed by OpenAI © trained on large and diverse datasets.

We queried the chatbots to generate SLOs, A-type MCQs, integrated case cluster MCQs, integrated SAQs, and OSPE test items in the domain of systemic hypertension related to the P&T discipline. Separate prompts were used to generate outputs for pre-clerkship (preclinical) phase students, and at the time of graduation (before starting residency programs). Additionally, we have also evaluated the ability of these AI platforms to estimate the proportion of students correctly answering these test items. We used the following queries for each of these objectives:

Specific learning objectives

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate specific learning objectives in the pharmacology discipline relevant to undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

A-type MCQs

In the initial query used for A-type of item, we specified the domains (such as the mechanism of action, pharmacokinetics, adverse reactions, and indications) so that a sample of test items generated without any theme-related clutter, shown below:

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase of which 5 MCQs should be related to mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

The MCQs generated with the above search query were not based on clinical vignettes. We queried again to generate MCQs using clinical vignettes specifically because most medical schools have adopted problem-based learning (PBL) in their medical curriculum.

Write 20 single best answer MCQs with 5 choices related to anti-hypertensive drugs for undergraduate medical students during the pre-clerkship phase using a clinical vignette for each MCQ of which 5 MCQs should be related to the mechanism of action, 5 MCQs related to pharmacokinetics, 5 MCQs related to adverse reactions, and 5 MCQs should be related to indications.

We attempted to explore whether AI platforms can provide useful guidance on standard-setting. Hence, we used the following search query.

Can you do a simulation with 100 undergraduate medical students to take the above questions and let me know what percentage of students got each MCQ correct?

Integrated case cluster MCQs

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students during the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette. Please do not include ‘none of the above’ as the choice. (This modified search query was used because test items with ‘None of the above’ option were generated with the previous search query).

Write 20 integrated case cluster MCQs with 2 questions in each cluster with 5 choices for undergraduate medical students at the time of graduation integrating pharmacology and physiology related to systemic hypertension with a case vignette.

Integrated short answer questions

Write a short answer question scenario with difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with moderately difficult questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Write a short answer question scenario with questions based on the theme of a newly diagnosed hypertensive patient for undergraduate medical students at the time of graduation with the main objectives related to the physiology of blood pressure regulation, risk factors for systemic hypertension, pathophysiology of systemic hypertension, pathological changes in the systemic blood vessels in hypertension, pharmacological management, and non-pharmacological treatment of systemic hypertension.

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students during their pre-clerkship phase related to anti-hypertensive drugs?

Can you generate 5 OSPE pharmacology and therapeutics prescription writing exercises containing appropriate instructions for the patients for the assessment of undergraduate medical students at the time of graduation related to anti-hypertensive drugs?

Both authors independently evaluated the AI-generated outputs, and a consensus was reached. We cross-checked the veracity of answers suggested by AIs as per the Joint National Commission Guidelines (JNC-8) and Goodman and Gilman’s The Pharmacological Basis of Therapeutics (2023), a reference textbook [ 13 , 14 ]. Errors in the A-type MCQs were categorized as item construction defects, multiple correct answers, and uncertain appropriateness to the learner’s level. Test items in the integrated case cluster MCQs, SAQs and OSPEs were evaluated with the Preliminary Conceptual Framework for Establishing Content Validity of AI-Generated Test Items based on the following domains: technical accuracy, comprehensiveness, education level, and lack of construction defects (Table  1 ). The responses were categorized as complete and deficient for each domain.

The pre-clerkship phase SLOs identified by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials 1 – 3 , respectively. In general, a broad homology in SLOs generated by the three AI platforms was observed. All AI platforms identified appropriate action verbs as per Bloom’s taxonomy to state the SLO; action verbs such as describe, explain, recognize, discuss, identify, recommend, and interpret are used to state the learning outcome. The specific, measurable, achievable, relevant, time-bound (SMART) SLOs generated by each AI platform slightly varied. All key domains of antihypertensive pharmacology to be achieved during the pre-clerkship (pre-clinical) years were relevant for graduating doctors. The SLOs addressed current JNC Treatment Guidelines recommended classes of antihypertensive drugs, the mechanism of action, pharmacokinetics, adverse effects, indications/contraindications, dosage adjustments, monitoring therapy, and principles of monotherapy and combination therapy.

The SLOs to be achieved by undergraduate medical students at the time of graduation identified by Sage Poe, Claude-Instant, and ChatGPT listed in electronic supplementary materials 4 – 6 , respectively. The identified SLOs emphasize the application of pharmacology knowledge within a clinical context, focusing on competencies needed to function independently in early residency stages. These SLOs go beyond knowledge recall and mechanisms of action to encompass competencies related to clinical problem-solving, rational prescribing, and holistic patient management. The SLOs generated require higher cognitive ability of the learner: action verbs such as demonstrate, apply, evaluate, analyze, develop, justify, recommend, interpret, manage, adjust, educate, refer, design, initiate & titrate were frequently used.

The MCQs for the pre-clerkship phase identified by Sage Poe, Claude-Instant, and ChatGPT listed in the electronic supplementary materials 7 – 9 , respectively, and those identified with the search query based on the clinical vignette in electronic supplementary materials ( 10 – 12 ).

All MCQs generated by the AIs in each of the four domains specified [mechanism of action (MOA); pharmacokinetics; adverse drug reactions (ADRs), and indications for antihypertensive drugs] are quality test items with potential content validity. The test items on MOA generated by Sage Poe included themes such as renin-angiotensin-aldosterone (RAAS) system, beta-adrenergic blockers (BB), calcium channel blockers (CCB), potassium channel openers, and centrally acting antihypertensives; on pharmacokinetics included high oral bioavailability/metabolism in liver [angiotensin receptor blocker (ARB)-losartan], long half-life and renal elimination [angiotensin converting enzyme inhibitors (ACEI)-lisinopril], metabolism by both liver and kidney (beta-blocker (BB)-metoprolol], rapid onset- short duration of action (direct vasodilator-hydralazine), and long-acting transdermal drug delivery (centrally acting-clonidine). Regarding the ADR theme, dry cough, angioedema, and hyperkalemia by ACEIs in susceptible patients, reflex tachycardia by CCB/amlodipine, and orthostatic hypotension by CCB/verapamil addressed. Clinical indications included the drug of choice for hypertensive patients with concomitant comorbidity such as diabetics (ACEI-lisinopril), heart failure and low ejection fraction (BB-carvedilol), hypertensive urgency/emergency (alpha cum beta receptor blocker-labetalol), stroke in patients with history recurrent stroke or transient ischemic attack (ARB-losartan), and preeclampsia (methyldopa).

Almost similar themes under each domain were identified by the Claude-Instant AI platform with few notable exceptions: hydrochlorothiazide (instead of clonidine) in MOA and pharmacokinetics domains, respectively; under the ADR domain ankle edema/ amlodipine, sexual dysfunction and fatigue in male due to alpha-1 receptor blocker; under clinical indications the best initial monotherapy for clinical scenarios such as a 55-year old male with Stage-2 hypertension; a 75-year-old man Stage 1 hypertension; a 35-year-old man with Stage I hypertension working on night shifts; and a 40-year-old man with stage 1 hypertension and hyperlipidemia.

As with Claude-Instant AI, ChatGPT-generated test items on MOA were mostly similar. However, under the pharmacokinetic domain, immediate- and extended-release metoprolol, the effect of food to enhance the oral bioavailability of ramipril, and the highest oral bioavailability of amlodipine compared to other commonly used antihypertensives were the themes identified. Whereas the other ADR themes remained similar, constipation due to verapamil was a new theme addressed. Notably, in this test item, amlodipine was an option that increased the difficulty of this test item because amlodipine therapy is also associated with constipation, albeit to a lesser extent, compared to verapamil. In the clinical indication domain, the case description asking “most commonly used in the treatment of hypertension and heart failure” is controversial because the options listed included losartan, ramipril, and hydrochlorothiazide but the suggested correct answer was ramipril. This is a good example to stress the importance of vetting the AI-generated MCQ by experts for content validity and to assure robust psychometrics. The MCQ on the most used drug in the treatment of “hypertension and diabetic nephropathy” is more explicit as opposed to “hypertension and diabetes” by Claude-Instant because the therapeutic concept of reducing or delaying nephropathy must be distinguished from prevention of nephropathy, although either an ACEI or ARB is the drug of choice for both indications.

It is important to align student assessment to the curriculum; in the PBL curriculum, MCQs with a clinical vignette are preferred. The modification of the query specifying the search to generate MCQs with a clinical vignette on domains specified previously gave appropriate output by all three AI platforms evaluated (Sage Poe; Claude- Instant; Chat GPT). The scenarios generated had a good clinical fidelity and educational fit for the pre-clerkship student perspective.

The errors observed with AI outputs on the A-type MCQs are summarized in Table  2 . No significant pattern was observed except that Claude-Instant© generated test items in a stereotyped format such as the same choices for all test items related to pharmacokinetics and indications, and all the test items in the ADR domain are linked to the mechanisms of action of drugs. This illustrates the importance of reviewing AI-generated test items by content experts for content validity to ensure alignment with evidence-based medicine and up-to-date treatment guidelines.

The test items generated by ChatGPT had the advantage of explanations supplied rendering these more useful for learners to support self-study. The following examples illustrate this assertion: “ A patient with hypertension is started on a medication that works by blocking beta-1 receptors in the heart (metoprolol)”. Metoprolol is a beta blocker that works by blocking beta-1 receptors in the heart, which reduces heart rate and cardiac output, resulting in a decrease in blood pressure. However, this explanation is incomplete because there is no mention of other less important mechanisms, of beta receptor blockers on renin release. Also, these MCQs were mostly recall type: Which of the following medications is known to have a significant first-pass effect? The explanation reads: propranolol is known to have a significant first pass-effect, meaning that a large portion of the drug is metabolized by the liver before it reaches systemic circulation. Losartan, amlodipine, ramipril, and hydrochlorothiazide do not have significant first-pass effect. However, it is also important to extend the explanation further by stating that the first-pass effect of propranolol does not lead to total loss of pharmacological activity because the metabolite hydroxy propranolol also has potent beta-blocking activity. Another MCQ test item had a construction defect: “A patient with hypertension is started on a medication that can cause photosensitivity. Which of the following medications is most likely responsible?” Options included: losartan, amlodipine, ramipril, hydrochlorothiazide, hydrochlorothiazide/triamterene. The explanation states that hydrochlorothiazide (HCTZ) can cause photosensitivity, which is increased sensitivity to sunlight that can cause skin rashes and sunburns. Losartan, amlodipine, ramipril, and HCTZ/triamterene are less likely to cause photosensitivity. However, it is irrational to claim that HCTZ/triamterene, one of the wrong options, is less likely to cause photosensitivity. The difficulty index of such test items is likely unacceptable in high-stake tests to make equitable psychometric decisions.

The responses from Sage Poe, Claude-Instant, and ChatGPT on guidance for standard-setting methods are listed in the electronic supplementary materials 13 – 15 . Sage Poe offered this information with the caveat that “the results of this simulation were purely hypothetical and do not reflect the actual performance of any real students”. The simulation estimates of examinees correctly answering test items ranged from 60 to 90% for the mechanism of action, 65–85% for pharmacokinetics, 60–80% for adverse reactions, and 75–90% for clinical indications of antihypertensives.

In contrast, Claude-Instant admitted that “Performing a full simulation with 100 medical students is beyond the scope of what I can do as an AI assistant. I can generate sample MCQ questions and answers, but I do not have access to a population of medical students to administer the questions. A true simulation that administers questions to real students and analyzes the results would require access to a database of medical students, a platform to deliver the questions, and code to analyze the responses. As an AI assistant, I lack these capabilities. While I cannot perform a full simulation, here are some considerations for administering MCQ questions to medical students: provide details on the purpose and instructions for the test to ensure students understand what is expected out of them; consider including some easier questions in addition to more challenging ones to boost students’ confidence and motivation; avoid ambiguous wording and ensure each question has only one unambiguously correct answer option; when analyzing results, look for questions factors that may have impacted performance, like unclear wording or answer options that are too similar. Focusing on weak questions can help improve future tests; compare performance across different student groups to identify areas where more teaching may be needed; provide detailed answer explanations and review sessions after the test to help students learn from any errors and reinforce correct concepts”. However, ChatGPT offered the simulation result estimates for the 20 MCQ on antihypertensive drugs: mechanism of action ranged from 67 to 92%, pharmacokinetics 63–86%, adverse effects 65–82%, and clinical indications 64–89%. Furthermore, it also stated that “Overall, the performance of the students was quite good, with most questions having a response rate of over 70%. However, there were some questions where the projected correct response rate was rather low, such as Question #5 (Mechanism of Action of Hydrochlorothiazide; see Electronic Supplementary Material 12 ) and Question 18 (Indications for Verapamil; see Electronic Supplementary Material 10 ). This may suggest areas where students need more focused education or review.”

We asked AI assistants to generate 20 integrated case cluster MCQs with 2 test items in each cluster with five options for undergraduate medical students in the pre-clerkship phase integrating pharmacology and physiology related to systemic hypertension with a case vignette and the responses by Sage Poe, Claude-Instant, and ChatGPT are listed in the electronic supplementary materials ( 16 – 18 ). In all instances, the test items generated had focused case descriptions in the form of a clinical vignette, and horizontal integration across the pathophysiology of hypertension and pharmacology of antihypertensive drugs. These test items mostly targeted the ‘knows (knowledge)’ or ‘knows how (competence)’ level on Miller’s pyramid and are suitable for assessing the clinical competence of pre-clerkship medical students, especially in an integrated PBL curriculum. Both the AI assistants generated excellent clinical vignettes and themes; however, most of the cluster MCQs by ChatGPT had “None of the above” as an option, which is often considered a test item construction flaw. Notwithstanding these limitations, case cluster integrated test items are valuable for learners to integrate their knowledge of different basic medical sciences and their application to clinical sciences. This integrated approach can be used for both instructional and student assessment purposes to make the course more meaningful. Indeed, one of the basic tenets of PBL is curriculum integration.

In the next query, we asked AI assistants to write integrated case cluster MCQs with 2 test items in each cluster with 5 options for undergraduate medical students at the time of graduation integrating pharmacology and physiology of hypertension with a case vignette. The responses are listed in the electronic supplementary materials 19 – 21 . Claude-Instant has provided only partial responses to both the queries. Overall, the information provided in case vignettes requires the learner to interpret the clinical information and make therapeutic decisions. Such test items are appropriate for assessing the minimum competency of medical school graduates to start internship or residency programs; these MCQs are generally comparable to test items used in USMLE Part 2. The evaluation of the integrated case cluster test items provided by all the AI platforms is summarized in Table  3 . In general, the AI outputs had at least one construction defect, and did not include all the core sub-topics to a sufficient degree.

When asked to simulate the above-generated test items to 100 undergraduate medical students at the time of graduation and provide a percentage of students who are likely to correctly answer each item, the AI assistant responded:

“ As an AI language model, I cannot simulate the responses of 100 undergraduate medical students likely to obtain the correct answer for each question. However, I can provide some general information about the difficulty level of each question based on the complexity of the concepts being tested and the level of integration between pharmacology and physiology ”.

AI assistant went on to clarify that questions that require knowledge of basic pharmacology principles, such as the mechanism of action of specific drugs, are likely to be easier for students to answer correctly. Test items that require an understanding of the physiological mechanisms underlying hypertension and correlating with symptoms are likely to be more challenging for students. The AI assistant sorted these test items into two categories accordingly. Overall, the difficulty level of the test item is based on the level of integration between pharmacology and pathophysiology. Test items that require an understanding of both pharmacological and physiological mechanisms are likely to be more challenging for students requiring a strong foundation in both pharmacology and physiology concepts to be able to correctly answer integrated case-cluster MCQs.

Short answer questions

The responses to a search query on generating SAQs appropriate to the pre-clerkship phase Sage Poe, Claude-Instant, and ChatGPT generated items are listed in the electronic supplementary materials 22 – 24 for difficult questions and 25–27 for moderately difficult questions.

It is apparent from these case vignette descriptions that the short answer question format varied. Accordingly, the scope for asking individual questions for each scenario is open-ended. In all instances, model answers are supplied which are helpful for the course instructor to plan classroom lessons, identify appropriate instructional methods, and establish rubrics for grading the answer scripts, and as a study guide for students.

We then wanted to see to what extent AI can differentiate the difficulty of the SAQ by replacing the search term “difficult” with “moderately difficult” in the above search prompt: the changes in the revised case scenarios are substantial. Perhaps the context of learning and practice (and the level of the student in the MD/medical program) may determine the difficulty level of SAQ generated. It is worth noting that on changing the search from cardiology to internal medicine rotation in Sage Poe the case description also changed. Thus, it is essential to select an appropriate AI assistant, perhaps by trial and error, to generate quality SAQs. Most of the individual questions tested stand-alone knowledge and did not require students to demonstrate integration.

The responses of Sage Poe, Claude-Instant, and ChatGPT for the search query to generate SAQs at the time of graduation are listed in the electronic supplementary materials 28 – 30 . It is interesting to note how AI assistants considered the stage of the learner while generating the SAQ. The response by Sage Poe is illustrative for comparison. “You are a newly graduated medical student who is working in a hospital” versus “You are a medical student in your pre-clerkship.”

Some questions were retained, deleted, or modified to align with competency appropriate to the context (Electronic Supplementary Materials 28 – 30 ). Overall, the test items at both levels from all AI platforms were technically accurate and thorough addressing the topics related to different disciplines (Table  3 ). The differences in learning objective transition are summarized in Table  4 . A comparison of learning objectives revealed that almost all objectives remained the same except for a few (Table  5 ).

A similar trend was apparent with test items generated by other AI assistants, such as ChatGPT. The contrasting differences in questions are illustrated by the vertical integration of basic sciences and clinical sciences (Table  6 ).

Taken together, these in-depth qualitative comparisons suggest that AI assistants such as Sage Poe and ChatGPT consider the learner’s stage of training in designing test items, learning outcomes, and answers expected from the examinee. It is critical to state the search query explicitly to generate quality output by AI assistants.

The OSPE test items generated by Claude-Instant and ChatGPT appropriate to the pre-clerkship phase (without mentioning “appropriate instructions for the patients”) are listed in the electronic supplementary materials 31 and 32 and with patient instructions on the electronic supplementary materials 33 and 34 . For reasons unknown, Sage Poe did not provide any response to this search query.

The five OSPE items generated were suitable to assess the prescription writing competency of pre-clerkship medical students. The clinical scenarios identified by the three AI platforms were comparable; these scenarios include patients with hypertension and impaired glucose tolerance in a 65-year-old male, hypertension with chronic kidney disease (CKD) in a 55-year-old woman, resistant hypertension with obstructive sleep apnea in a 45-year-old man, and gestational hypertension at 32 weeks in a 35-year-old (Claude-Instant AI). Incorporating appropriate instructions facilitates the learner’s ability to educate patients and maximize safe and effective therapy. The OSPE item required students to write a prescription with guidance to start conservatively, choose an appropriate antihypertensive drug class (drug) based on the patients’ profile, specifying drug name, dose, dosing frequency, drug quantity to be dispensed, patient name, date, refill, and caution as appropriate, in addition to prescribers’ name, signature, and license number. In contrast, ChatGPT identified clinical scenarios to include patients with hypertension and CKD, hypertension and bronchial asthma, gestational diabetes, hypertension and heart failure, and hypertension and gout (ChatGPT). Guidance for dosage titration, warnings to be aware, safety monitoring, and frequency of follow-up and dose adjustment. These test items are designed to assess learners’ knowledge of P & T of antihypertensives, as well as their ability to provide appropriate instructions to patients. These clinical scenarios for writing prescriptions assess students’ ability to choose an appropriate drug class, write prescriptions with proper labeling and dosing, reflect drug safety profiles, and risk factors, and make modifications to meet the requirements of special populations. The prescription is required to state the drug name, dose, dosing frequency, patient name, date, refills, and cautions or instructions as needed. A conservative starting dose, once or twice daily dosing frequency based on the drug, and instructions to titrate the dose slowly if required.

The responses from Claude-Instant and ChatGPT for the search query related to generating OSPE test items at the time of graduation are listed in electronic supplementary materials 35 and 36 . In contrast to the pre-clerkship phase, OSPEs generated for graduating doctors’ competence assessed more advanced drug therapy comprehension. For example, writing a prescription for:

(1) A 65-year- old male with resistant hypertension and CKD stage 3 to optimize antihypertensive regimen required the answer to include starting ACEI and diuretic, titrating the dosage over two weeks, considering adding spironolactone or substituting ACEI with an ARB, and need to closely monitor serum electrolytes and kidney function closely.

(2) A 55-year-old woman with hypertension and paroxysmal arrhythmia required the answer to include switching ACEI to ARB due to cough, adding a CCB or beta blocker for rate control needs, and adjusting the dosage slowly and monitoring for side effects.

(3) A 45-year-old man with masked hypertension and obstructive sleep apnea require adding a centrally acting antihypertensive at bedtime and increasing dosage as needed based on home blood pressure monitoring and refer to CPAP if not already using one.

(4) A 75-year-old woman with isolated systolic hypertension and autonomic dysfunction to require stopping diuretic and switching to an alpha blocker, upward dosage adjustment and combining with other antihypertensives as needed based on postural blood pressure changes and symptoms.

(5) A 35-year-old pregnant woman with preeclampsia at 29 weeks require doubling methyldopa dose and consider adding labetalol or nifedipine based on severity and educate on signs of worsening and to follow-up immediately for any concerning symptoms.

These case scenarios are designed to assess the ability of the learner to comprehend the complexity of antihypertensive regimens, make evidence-based regimen adjustments, prescribe multidrug combinations based on therapeutic response and tolerability, monitor complex patients for complications, and educate patients about warning signs and follow-up.

A similar output was provided by ChatGPT, with clinical scenarios such as prescribing for patients with hypertension and myocardial infarction; hypertension and chronic obstructive pulmonary airway disease (COPD); hypertension and a history of angina; hypertension and a history of stroke, and hypertension and advanced renal failure. In these cases, wherever appropriate, pharmacotherapeutic issues like taking ramipril after food to reduce side effects such as giddiness; selection of the most appropriate beta-blocker such as nebivolol in patients with COPD comorbidity; the importance of taking amlodipine at the same time every day with or without food; preference for telmisartan among other ARBs in stroke; choosing furosemide in patients with hypertension and edema and taking the medication with food to reduce the risk of gastrointestinal adverse effect are stressed.

The AI outputs on OSPE test times were observed to be technically accurate, thorough in addressing core sub-topics suitable for the learner’s level and did not have any construction defects (Table  3 ). Both AIs provided the model answers with explanatory notes. This facilitates the use of such OSPEs for self-assessment by learners for formative assessment purposes. The detailed instructions are helpful in creating optimized therapy regimens, and designing evidence-based regimens, to provide appropriate instructions to patients with complex medical histories. One can rely on multiple AI sources to identify, shortlist required case scenarios, and OSPE items, and seek guidance on expected model answers with explanations. The model answer guidance for antihypertensive drug classes is more appropriate (rather than a specific drug of a given class) from a teaching/learning perspective. We believe that these scenarios can be refined further by providing a focused case history along with relevant clinical and laboratory data to enhance clinical fidelity and bring a closer fit to the competency framework.

In the present study, AI tools have generated SLOs that comply with the current principles of medical education [ 15 ]. AI tools are valuable in constructing SLOs and so are especially useful for medical fraternities where training in medical education is perceived as inadequate, more so in the early stages of their academic career. Data suggests that only a third of academics in medical schools have formal training in medical education [ 16 ] which is a limitation. Thus, the credibility of alternatives, such as the AIs, is evaluated to generate appropriate course learning outcomes.

We observed that the AI platforms in the present study generated quality test items suitable for different types of assessment purposes. The AI-generated outputs were similar with minor variation. We have used generative AIs in the present study that could generate new content from their training dataset [ 17 ]. Problem-based and interactive learning approaches are referred to as “bottom-up” where learners obtain first-hand experience in solving the cases first and then indulge in discussion with the educators to refine their understanding and critical thinking skills [ 18 ]. We suggest that AI tools can be useful for this approach for imparting the core knowledge and skills related to Pharmacology and Therapeutics to undergraduate medical students. A recent scoping review evaluating the barriers to writing quality test items based on 13 studies has concluded that motivation, time constraints, and scheduling were the most common [ 19 ]. AI tools can be valuable considering the quick generation of quality test items and time management. However, as observed in the present study, the AI-generated test items nevertheless require scrutiny by faculty members for content validity. Moreover, it is important to train faculty in AI technology-assisted teaching and learning. The General Medical Council recommends taking every opportunity to raise the profile of teaching in medical schools [ 20 ]. Hence, both the academic faculty and the institution must consider investing resources in AI training to ensure appropriate use of the technology [ 21 ].

The AI outputs assessed in the present study had errors, particularly with A-type MCQs. One notable observation was that often the AI tools were unable to differentiate the differences between ACEIs and ARBs. AI platforms access several structured and unstructured data, in addition to images, audio, and videos. Hence, the AI platforms can commit errors due to extracting details from unauthenticated sources [ 22 ] created a framework identifying 28 factors for reconstructing the path of AI failures and for determining corrective actions. This is an area of interest for AI technical experts to explore. Also, this further iterates the need for human examination of test items before using them for assessment purposes.

There are concerns that AIs can memorize and provide answers from their training dataset, which they are not supposed to do [ 23 ]. Hence, the use of AIs-generated test items for summative examinations is debatable. It is essential to ensure and enhance the security features of AI tools to reduce or eliminate cross-contamination of test items. Researchers have emphasized that AI tools will only reach their potential if developers and users can access full-text non-PDF formats that help machines comprehend research papers and generate the output [ 24 ].

AI platforms may not always have access to all standard treatment guidelines. However, in the present study, it was observed that all three AI platforms generally provided appropriate test items regarding the choice of medications, aligning with recommendations from contemporary guidelines and standard textbooks in pharmacology and therapeutics. The prompts used in the study were specifically focused on the pre-clerkship phase of the undergraduate medical curriculum (and at the time of their graduation) and assessed fundamental core concepts, which were also reflected in the AI outputs. Additionally, the recommended first-line antihypertensive drug classes have been established for several decades, and information regarding their pharmacokinetics, ADRs, and indications is well-documented in the literature.

Different paradigms and learning theories have been proposed to support AI in education. These paradigms include AI- directed (learner as recipient), AI-supported (learner as collaborator), and AI-empowered (learner as leader) that are based on Behaviorism, Cognitive-Social constructivism, and Connectivism-Complex adaptive systems, respectively [ 25 ]. AI techniques have potential to stimulate and advance instructional and learning sciences. More recently a three- level model that synthesizes and unifies existing learning theories to model the roles of AIs in promoting learning process has been proposed [ 26 ]. The different components of our study rely upon these paradigms and learning theories as the theoretical underpinning.

Strengths and limitations

To the best of our knowledge, this is the first study evaluating the utility of AI platforms in generating test items related to a discipline in the undergraduate medical curriculum. We have evaluated the AI’s ability to generate outputs related to most types of assessment in the undergraduate medical curriculum. The key lessons learnt for improving the AI-generated test item quality from the present study are outlined in Table  7 . We used a structured framework for assessing the content validity of the test items. However, we have demonstrated using a single case study (hypertension) as a pilot experiment. We chose to evaluate anti-hypertensive drugs as it is a core learning objective and one of the most common disorders relevant to undergraduate medical curricula worldwide. It would be interesting to explore the output from AI platforms for other common (and uncommon/region-specific) disorders, non-/semi-core objectives, and disciplines other than Pharmacology and Therapeutics. An area of interest would be to look at the content validity of the test items generated for different curricula (such as problem-based, integrated, case-based, and competency-based) during different stages of the learning process. Also, we did not attempt to evaluate the generation of flowcharts, algorithms, or figures for generating test items. Another potential area for exploring the utility of AIs in medical education would be repeated procedural practices such as the administration of drugs through different routes by trainee residents [ 27 ]. Several AI tools have been identified for potential application in enhancing classroom instructions and assessment purposes pending validation in prospective studies [ 28 ]. Lastly, we did not administer the AI-generated test items to students and assessed their performance and so could not comment on the validity of test item discrimination and difficulty indices. Additionally, there is a need to confirm the generalizability of the findings to other complex areas in the same discipline as well as in other disciplines that pave way for future studies. The conceptual framework used in the present study for evaluating the AI-generated test items needs to be validated in a larger population. Future studies may also try to evaluate the variations in the AI outputs with repetition of the same queries.

Notwithstanding ongoing discussions and controversies, AI tools are potentially useful adjuncts to optimize instructional methods, test blueprinting, test item generation, and guidance for test standard-setting appropriate to learners’ stage in the medical program. However, experts need to critically review the content validity of AI-generated output. These challenges and caveats are to be addressed before the use of widespread use of AIs in medical education can be advocated.

Data availability

All the data included in this study are provided as Electronic Supplementary Materials.

Tolsgaard MG, Pusic MV, Sebok-Syer SS, Gin B, Svendsen MB, Syer MD, Brydges R, Cuddy MM, Boscardin CK. The fundamentals of Artificial Intelligence in medical education research: AMEE Guide 156. Med Teach. 2023;45(6):565–73.

Article   Google Scholar  

Sriwastwa A, Ravi P, Emmert A, Chokshi S, Kondor S, Dhal K, Patel P, Chepelev LL, Rybicki FJ, Gupta R. Generative AI for medical 3D printing: a comparison of ChatGPT outputs to reference standard education. 3D Print Med. 2023;9(1):21.

Azer SA, Guerrero APS. The challenges imposed by artificial intelligence: are we ready in medical education? BMC Med Educ. 2023;23(1):680.

Masters K. Ethical use of Artificial Intelligence in Health Professions Education: AMEE Guide 158. Med Teach. 2023;45(6):574–84.

Nagi F, Salih R, Alzubaidi M, Shah H, Alam T, Shah Z, Househ M. Applications of Artificial Intelligence (AI) in Medical Education: a scoping review. Stud Health Technol Inf. 2023;305:648–51.

Google Scholar  

Mehta N, Harish V, Bilimoria K, et al. Knowledge and attitudes on artificial intelligence in healthcare: a provincial survey study of medical students. MedEdPublish. 2021;10(1):75.

Mir MM, Mir GM, Raina NT, Mir SM, Mir SM, Miskeen E, Alharthi MH, Alamri MMS. Application of Artificial Intelligence in Medical Education: current scenario and future perspectives. J Adv Med Educ Prof. 2023;11(3):133–40.

Garg T. Artificial Intelligence in Medical Education. Am J Med. 2020;133(2):e68.

Matheny ME, Whicher D, Thadaney IS. Artificial intelligence in health care: a report from the National Academy of Medicine. JAMA. 2020;323(6):509–10.

Sage Poe. Available at: https://poe.com/Assistant (Accessed on. 3rd June 2023).

Claude-Instant: Available at: https://poe.com/Claude-instant (Accessed on 3rd. June 2023).

ChatGPT: Available at: https://poe.com/ChatGPT (Accessed on 3rd. June 2023).

James PA, Oparil S, Carter BL, Cushman WC, Dennison-Himmelfarb C, Handler J, Lackland DT, LeFevre ML, MacKenzie TD, Ogedegbe O, Smith SC Jr, Svetkey LP, Taler SJ, Townsend RR, Wright JT Jr, Narva AS, Ortiz E. 2014 evidence-based guideline for the management of high blood pressure in adults: report from the panel members appointed to the Eighth Joint National Committee (JNC 8). JAMA. 2014;311(5):507–20.

Eschenhagen T. Treatment of hypertension. In: Brunton LL, Knollmann BC, editors. Goodman & Gilman’s the pharmacological basis of therapeutics. 14th ed. New York: McGraw Hill; 2023.

Shabatura J. September. Using Bloom’s taxonomy to write effective learning outcomes. https://tips.uark.edu/using-blooms-taxonomy/ (Accessed on 19th 2023).

Trainor A, Richards JB. Training medical educators to teach: bridging the gap between perception and reality. Isr J Health Policy Res. 2021;10(1):75.

Boscardin C, Gin B, Golde PB, Hauer KE. ChatGPT and generative artificial intelligence for medical education: potential and opportunity. Acad Med. 2023. https://doi.org/10.1097/ACM.0000000000005439 . (Published ahead of print).

Duong MT, Rauschecker AM, Rudie JD, Chen PH, Cook TS, Bryan RN, Mohan S. Artificial intelligence for precision education in radiology. Br J Radiol. 2019;92(1103):20190389.

Karthikeyan S, O’Connor E, Hu W. Barriers and facilitators to writing quality items for medical school assessments - a scoping review. BMC Med Educ. 2019;19(1):123.

Developing teachers and trainers in undergraduate medical education. Advice supplementary to Tomorrow’s Doctors. (2009). https://www.gmc-uk.org/-/media/documents/Developing_teachers_and_trainers_in_undergraduate_medical_education___guidance_0815.pdf_56440721.pdf (Accessed on 19th September 2023).

Cooper A, Rodman A. AI and Medical Education - A 21st-Century Pandora’s Box. N Engl J Med. 2023;389(5):385–7.

Chanda SS, Banerjee DN. Omission and commission errors underlying AI failures. AI Soc. 2022;17:1–24.

Narayanan A, Kapoor S. ‘GPT-4 and Professional Benchmarks: The Wrong Answer to the Wrong Question’. Substack newsletter. AI Snake Oil (blog). https://aisnakeoil.substack.com/p/gpt-4-and-professional-benchmarks (Accessed on 19th September 2023).

Brainard J. November. As scientists face a flood of papers, AI developers aim to help. Science, 21 2023. doi.10.1126/science.adn0669.

Ouyang F, Jiao P. Artificial intelligence in education: the three paradigms. Computers Education: Artif Intell. 2021;2:100020.

Gibson D, Kovanovic V, Ifenthaler D, Dexter S, Feng S. Learning theories for artificial intelligence promoting learning processes. Br J Edu Technol. 2023;54(5):1125–46.

Guerrero DT, Asaad M, Rajesh A, Hassan A, Butler CE. Advancing Surgical Education: the Use of Artificial Intelligence in Surgical Training. Am Surg. 2023;89(1):49–54.

Lee S. AI tools for educators. EIT InnoEnergy Master School Teachers Conference. 2023. https://www.slideshare.net/ignatia/ai-toolkit-for-educators?from_action=save (Accessed on 24th September 2023).

Download references

Author information

Authors and affiliations.

Department of Pharmacology & Therapeutics, College of Medicine & Medical Sciences, Arabian Gulf University, Manama, Kingdom of Bahrain

Kannan Sridharan & Reginald P. Sequeira

You can also search for this author in PubMed   Google Scholar

Contributions

RPS– Conceived the idea; KS– Data collection and curation; RPS and KS– Data analysis; RPS and KS– wrote the first draft and were involved in all the revisions.

Corresponding author

Correspondence to Kannan Sridharan .

Ethics declarations

Ethics approval and consent to participate.

Not applicable as neither there was any interaction with humans, nor any personal data was collected in this research study.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

Rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Sridharan, K., Sequeira, R.P. Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study. BMC Med Educ 24 , 431 (2024). https://doi.org/10.1186/s12909-024-05365-7

Download citation

Received : 26 September 2023

Accepted : 28 March 2024

Published : 22 April 2024

DOI : https://doi.org/10.1186/s12909-024-05365-7

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Medical education
• Pharmacology
• Therapeutics

BMC Medical Education

ISSN: 1472-6920

• Submission enquiries: [email protected]
• General enquiries: [email protected]

• SUGGESTED TOPICS
• The Magazine
• Newsletters
• Managing Yourself
• Managing Teams
• Work-life Balance
• The Big Idea
• Data & Visuals
• Reading Lists
• Case Selections
• HBR Learning
• Topic Feeds
• Account Settings
• Email Preferences

Lessons from Beyoncé on Navigating Exclusion

• Ella F. Washington,
• Hildana Haileyesus,
• Laura Morgan Roberts

The star’s path from CMA Awards backlash to Cowboy Carter is a case study in strategic response.

In 2016, Beyoncé’s performance at the CMA Awards sparked backlash from fans complaining about everything from her attire to her lack of connection to the genre. This year, she released her first country album, which debuted at number one on the Billboard 200. Her actions over the past eight years have been a case study in how to navigate workplace exclusion. As a first step, it often makes sense to exit the conversation and wait for a better moment to respond. Then, work behind the scenes, ideally with collaborators, to push for change. Finally, consider focusing on your own authenticity and strengths to create your own lane within your organization or outside it.

Beyoncé, the globally revered singer, songwriter, and entrepreneur, last month released her new album Cowboy Carter.   However, this project is much more than another musical release from a leading star. It offers a case study in how to navigate workplace exclusion.

• Ella F. Washington  is an organizational psychologist; the founder and CEO of Ellavate Solutions, a DEI strategy firm; and a professor of practice at Georgetown University’s McDonough School of Business. She is the author of  The Necessary Journey: Making Real Progress on Equity and Inclusion  (HBR Press, November 2022) and  Unspoken: A Guide to Cracking the Hidden Corporate Code  (Forbes Books, May 2024). 
• Hildana Haileyesus  is a DEI consultant at  Ellavate Solutions with a background in training and facilitation, client strategy, and research. She has worked across higher education and business and applies a sociological lens to equity-driven change efforts.
• Laura Morgan Roberts is a Frank M. Sands Sr. Associate Professor of Business Administration at the University of Virginia’s Darden School of Business. She is an organizational psychologist and the coeditor of Race, Work and Leadership: New Perspectives on the Black Experience (Harvard Business Review Press, 2019).

Partner Center

Chronic wasting disease: Death of 2 hunters in US raises concerns of 'zombie deer'

The 2022 report of two hunters who developed neurological diseases after eating potentially infected deer meat has raised concerns 'zombie deer disease' could pass to humans as mad cow disease did..

Two hunters who ate meat from a population of deer known to have chronic wasting disease − or "zombie deer disease" − developed similar neurological conditions and died, raising concerns that it can pass from animals to humans.

Found in deer in northern Colorado and southern Wyoming in the 1990s, chronic wasting disease (CWD) has been recorded in free-ranging deer, elk and moose in at least 32 states across all parts of the continental U.S., according to the U.S. Centers for Disease Control and Prevention .

Deer infected with CWD may be called "zombie deer" because the disease leads to weight loss, lack of coordination, stumbling, listlessness, weight loss, drooling, and lack of fear of people.

The 2022 case did prove that CWD could infect humans. But scientists and health officials have been concerned that CWD could jump to humans as mad cow disease did in the United Kingdom in the 1990s . In 2022, scientists in Canada published a study, based on mice research, suggesting a risk of CWD transmission to humans .

Here's what you need to know about chronic wasting disease and whether you need to worry about it.

Researchers identify troubling case involving 2 deaths

Researchers at the University of Texas Health Science Center at San Antonio have reported how two hunters who ate venison from a deer population known to have CWD died in 2022 after developing sporadic Creutzfeldt-Jakob disease (CJD), which is a neurological disease like CWD.

The second man to die, who was 77, suffered "rapid-onset confusion and aggression," the researchers said, and died within a month despite treatment.

"The patient’s history, including a similar case in his social group, suggests a possible novel animal-to-human transmission of CWD," they wrote in the case report , which was presented earlier this month at the annual meeting of the American Academy of Neurology and published in the peer-reviewed journal Neurology.

The researchers did not say where the men lived or hunted. But the highest concentration of CWD-infected deer can be found in Kansas, Nebraska, Wisconsin and Wyoming, according to CDC and US. Geological Survey reports.

Because of the difficulty in distinguishing between the diseases, the researchers said the case does not represent a proven case of transmission. However, "this cluster emphasizes the need for further investigation into the potential risks of consuming CWD-infected deer and its implications for public health," they wrote.

'Zombie deer disease': What to know about chronic wasting disease and its spread in the US.

What is 'zombie deer disease'? What are prion diseases?

Also known as chronic wasting disease, "zombie deer disease" is a prion disease, a rare, progressive and fatal neurodegenerative disorder that affects deer, elk, moose and other animals, the CDC says.

In prion diseases, the abnormal folding of certain "prion proteins" leads to brain damage and other symptoms, according to the CDC. Prion diseases , which usually progress rapidly and are always fatal, can affect humans and animals. 

Creutzfeldt-Jacob disease (CJD) and variant Creutzfeldt-Jacob disease (vCJD), which is a form of mad cow disease, are prion diseases found in people.

Mad cow disease  is an example of a prion disease that can spread from cattle to humans, and some researchers have likened "zombie deer disease" to it.

For instance, with mad cow disease, it usually took four to six years from infection for cattle to show symptoms, according to the Food and Drug Administration . Deer may have an incubation period of up to two years before the onset of symptoms. So, the animals could have the disease but look normal until the onset of symptoms, such as weight loss, notes the U.S. Geological Survey .

The development of vCJD in humans in the wake of mad cow disease – its official name is bovine spongiform encephalopathy, or BSE – through eating meat from contaminated cattle has concerned scientists about the possible transmission of chronic wasting disease (CWD) to humans.

Can 'zombie deer disease' be transmitted to humans?

Even though there has been no known confirmed case of deer-to-human transmission of "zombie deer disease,' concerns have risen since officials found CWD in a dead deer in Yellowstone National Park in November.

"As of yet, there has been no transmission from deer or elk to humans," Jennifer Mullinax, associate professor of wildlife ecology and management at the University of Maryland, told BBC . "However, given the nature of prions, CDC and other agencies have supported all efforts to keep any prion disease out of the food chain."

Should CWD transmit to humans, it could create a "potential crisis" similar to what mad cow disease caused, Michael Osterholm, director of the Center for Infectious Disease Research and Policy at the University of Minnesota, told BBC .

"However, it’s important to note that BSE and CWD prions differ structurally, and we do not yet know whether the pathology and clinical presentation would be comparable if CWD transmission to humans were to occur," he said.

Meanwhile, chronic wasting disease continues to spread to more states; the most recent is Indiana. The disease was detected this month in a male white-tailed deer in the northeastern part of the state, which borders part of Michigan, where CWD had been detected earlier, according to the Center for Infectious Disease Research and Policy .

The U.S. Geological Survey updated its tracking of chronic wasting disease on Friday to include 33 states (adding Indiana), as well as four Canadian provinces and four other countries (Finland, Norway, Sweden and South Korea).

Contributing: Sara Chernikoff and Julia Gomez

Follow Mike Snider on X and Threads:  @mikesnider  & mikegsnider .

What's everyone talking about? Sign up for our trending newsletter to get the latest news of the day

New study offers hope for a rare and devastating eye cancer

After more than a decade studying a rare eye cancer that produces some of the hardest-to-fight tumors, researchers from University of Pittsburgh Medical Center have found a treatment that works on some patients and, more importantly, a tool that can predict when it is likely to succeed.

The work, published in Nature Communications, is being validated in a clinical trial involving at least 30 patients. It could pave the way for similar methods designed to overcome one of the enduring frustrations of cancer care.

Because tumors differ, not only between patients but even inside the same patient, a treatment that works on one mass may fail on another, even when both are of the same cancer type.

The researchers in Pittsburgh tackled this problem in uveal melanoma, an eye cancer that afflicts only 5 people in a million, but that half the time spreads to other parts of the body, often the liver. The median survival once uveal melanoma has spread has been less than seven months, according to a 2018 study in the journal JAMA Ophthalmology.

“We chose this because it was one of the only cancers that 10 years ago when we started, there was nothing approved for it,” said Udai Kammula, who led the study and directs the Solid Tumor Cell Therapy Program at UPMC Hillman Cancer Center in Pittsburgh.

Scientists had long speculated that the reason uveal melanoma is so tough to fight is that something helps the tumor keep out T cells, a key part of the body’s immune system that develops in bone marrow. However, previous studies by Kammula and his colleagues showed that uveal melanoma tumors actually have T cells inside, and they are turned on.

The problem? The cells lie dormant instead of multiplying and reaching numbers large enough to overwhelm the tumor.

The culprit appears to reside somewhere inside the tumor’s ecosystem of cells, molecules and blood vessels, known formally as the tumor’s “microenvironment.” Kammula compares this ecosystem to the infrastructure that supports a city. Something in that infrastructure helps protect uveal melanoma tumors by preventing the critical T cells from multiplying.

“Ultimately, if we’re going to get rid of cancer, we have to get rid of this infrastructure,” Kammula said.

A tool for predicting success

He and his colleagues have had some success using a treatment known as adoptive cell therapy, which was developed in the 1980s by Steven Rosenberg at the National Institutes of Health.

The treatment involves removing the T cells from the tumor, where they have been unable to proliferate. Scientists then take those T cells and grow them outside the body in a lab dish. They treat patients with chemotherapy to kill off the last of their old immune systems. Finally, they reinfuse the lab-grown T cells into the patient’s blood stream and the cells, now in much greater numbers, go on to attack the tumor.

In this treatment, the T cells are often referred to as tumor-infiltrating leukocytes, or TILs.

Kammula said his team has found that tumors shrink partially or completely in about 35 percent of patients who receive the treatment. But they wanted to know why it doesn’t work in the majority of cases, and whether there might be some way to predict beforehand when it will succeed.

To find out, the researchers analyzed samples from 100 different uveal melanoma tumors that had spread to different parts of the body in 84 patients, seeking to examine all of the tumors’ genetic material.

“We basically put the tumor biopsy in a blender that had the stroma [supportive tissue], the blood vessels, the immune cells, the tumor cells. It had everything,” Kammula said, explaining that they then analyzed all of the tumor’s genetic material.

They found 2,394 genes that could have helped make the tumor susceptible to treatment, some of them genes that experts would regard as “the usual suspects” and others that were unexpected. Using this long list of genes, the scientists searched for characteristics that they shared.

The genes were predominantly involved in helping the body defend itself against viruses, bacteria and other foreign invaders by removing the invaders and helping tissue heal. Kammula and the study’s lead author, Shravan Leonard-Murali, a postdoctoral fellow in the lab, used the different activity levels of these genes to develop a clinical tool.

The tool, known as a biomarker, assigns a score to a uveal melanoma tumor based on the likelihood that it will respond well to the treatment ― removing T cells, growing them outside the body, then reinfusing them.

So far, Kammula said, the biomarker has been “extremely good,” in predicting when the treatment will be effective, though he added, “these findings will need confirmation in the current ongoing clinical trial.”

“I thought it was somewhat of a tour de force, honestly,” said Eric Tran, an associate member of the Earle A. Chiles Research Institute, a division of Providence Cancer Institute in Portland, Ore. Tran did not participate in the study.

He said that while it will be important to validate these results, “I was certainly encouraged by their studies. And from my perspective, I wonder if that sort of strategy can be deployed in other cancers.”

Ryan J. Sullivan, an oncologist at Massachusetts General Hospital and associate professor at Harvard Medical School who was not involved in the study, called the team’s work “timely” and said “it is even more significant that they appear to have a [tool] that appears to predict which patients will benefit.”

The team at UPMC is already investigating possible wider application of both the treatment and the biomarker in a second clinical trial that involves a dozen different cancers.