volkswagen case study questions and answers

Brought to you by:

The Volkswagen Emissions Scandal

By: Luann J. Lynch, Cameron Cutro, Elizabeth Bird

In September 2015, VW had admitted to United States regulators that it had deliberately installed "defeat devices" in many of its diesel cars, which enabled the cars to cheat on federal and state…

• Length: 17 page(s)
• Publication Date: Jul 21, 2016
• Discipline: Strategy
• Product #: UV7245-PDF-ENG

What's included:

• Teaching Note
• Educator Copy

$4.95 per student

degree granting course

$8.95 per student

non-degree granting course

Get access to this material, plus much more with a free Educator Account:

• Access to world-famous HBS cases
• Up to 60% off materials for your students
• Resources for teaching online
• Tips and reviews from other Educators

Already registered? Sign in

• Student Registration
• Non-Academic Registration
• Included Materials

In September 2015, VW had admitted to United States regulators that it had deliberately installed "defeat devices" in many of its diesel cars, which enabled the cars to cheat on federal and state emissions tests, making them able to pass the tests and hit ambitious mileage and performance targets while actually emitting up to 40 times more hazardous gases into the atmosphere than legally allowed. The discovery had prompted the U.S. Environmental Protection Agency (EPA) to halt final certification of VW's 2016 diesel models, and VW itself had halted sales of its 2015 models. As fallout from the defeat devices developed, VW posted its first quarterly loss in more than 15 years, and its stock plummeted. Top executives were replaced, and VW abandoned its goal of becoming the world's largest automaker. Stakeholders around the world had been asking since the scandal broke: "How could this have happened at Volkswagen?"

Jul 21, 2016 (Revised: Oct 30, 2018)

Discipline:

Darden School of Business

UV7245-PDF-ENG

We use cookies to understand how you use our site and to improve your experience, including personalizing content. Learn More . By continuing to use our site, you accept our use of cookies and revised Privacy Policy .

Jeff Gothelf

Volkswagen’s electric car ambitions: a Sense & Respond case study

“What they didn’t consider: Electric vehicles are more about software than hardware. And producing exquisitely engineered gas-powered cars doesn’t translate into coding savvy.” source WSJ

This damning statement from the Wall Street Journal’s profile of VW’s struggling electric car program is the raw truth and painful realization of nearly every legacy corporation trying to “transform” into a digital organization. It’s been four years since Sense & Respond , the second book Josh Seiden and I wrote together, was published. If you haven’t read it (you should) here is the simplest breakdown of the thesis in that book:

• Every business of scale or that seeks to scale is a software business at its core — you cannot reach mass market success or maintain it without technology and software driving every aspect of your business. This includes how you deliver value to and continue to optimize your product or service for your customers.
• Software is continuous — the modern nature of software is systemic. Software is dynamic, not static. There is no end to your software projects. They are products and services you provide in perpetuity. You are not in the software manufacturing business. In fact, the quantity of software you produce is irrelevant. Producing more software guarantees you only two things: more software and technical debt. That’s it. The actual goal is to develop as little software as possible knowing your teams will have to maintain that code forever.
• Continuous software provides us with a unique opportunity to learn continuously — Amazon ships code to production every second . In Sense & Respond we wrote that it was every 11.6 seconds. That was true. 5 years ago. Shipping code continuously into the hands of your customers allows you to learn how that code impacts their behavior equally as fast. Customer expectations are changing rapidly particularly due to the mass market usage of popular services like Google Maps, Facebook, Amazon, iOS and many others. In addition, usage of your products evolves over short periods of time and ultimately emerges from the ongoing interaction with that system. Behaviors you never predicted or expected show up as users attempt to manipulate your product to do what they really need it to do. Shipping continuously allows us to sense continuously what people are doing with our products or services. We then have an obligation to respond to what we’re sensing with updates, optimizations, rollbacks or perhaps brand new systems. In essence, we can now have a continuous conversation with our customers in real time.
• Managing a software-based business is fundamentally different from a traditional company — If you can ship software every second (and you can), the delivery of software becomes a non-event. In other words, any kind of manufacturing process, incentive or optimization makes no sense in a software-driven business. What you measure, manage and reward must change to support the continuous improvement of your products and services. Your customers expect this and will take their business elsewhere if the software is broken, doesn’t improve and has a bad user experience. Managing your teams to deliver high-quality software is only half the battle. They must also be incentivized to understand their customer so they can accurately determine which features, upgrades and improvements to ship. This impacts how you frame work for your teams, measure their success, determine their performance criteria, empower them to make evidence-based decisions quickly and celebrate their ability to adjust course quickly based on the evidence they collect as they ship, sense and respond. 

The Volkswagen story illustrates the benefits of every aspect of this thesis. VW assumed their manufacturing expertise and vast resources ($50 billion dollars!) would guarantee their success in the electric vehicle market. The comparisons to Tesla are obvious perhaps but it’s worth pointing out the key difference — Tesla is a software company that makes cars . Elon Musk is a technologist first and foremost. Software is in Tesla’s DNA. Infusing that in VW’s DNA is proving difficult. 

Ultimately, VW is taking steps in the right direction. “In order to be successful in this new world and secure the prosperity of many people…VW must completely change,” Herbert Diess, CEO of VW said in a LinkedIn post . As the WSJ article points out, software has been in cars for years but it’s never been centralized as electric vehicles demand. The complexity of building a centralized operating system for an electric car requires technical expertise VW has lacked to date. “You can’t just flip a switch and be a software company.”

To become a software-driven business, VW is now doing the hard work of digital transformation and reorganization. They are consolidating the various software teams under one roof. They’re bringing the majority of their efforts in-house — and out of the hands of over 19 external vendors. They hold regular collaboration workshops and adjust prioritization based on learning that emerges as the next version of their electric car, the ID.4, is being developed.  They continue to struggle with culture change as the company is technically successful and profitable. These new ways of working are challenging veteran staff and leadership who don’t feel the pressure to evolve into a truly software-driven company. 

The thing that still strikes me as VW’s achilles heel(s) in this effort is the people they’ve chosen to lead this change and the late stage at which they’ve adopted some of these ideas. It’s now 2021 but it took VW until 2020 to realize Clayton Christensen’s ideas in The Innovator’s Dilemma (first published in 1997!) are the right way to frame their innovation efforts (they’re carving out a separate team and business unit called Artemis to work on the customer experience of the ID.4). In addition, these digital transformation efforts are being led by auto industry veterans from Audi, BMW and VW itself. These folks have vast institutional knowledge but it’s exactly The Institution that is getting in the way of their building a modern, software based business. 

Transformation is risky. Moving away from your core expertise in manufacturing to one based in technology poses many risks. Compared, however, to the existential risk of losing market share and industry irrelevance, companies have no choice. The VW story continues to evolve but is a cautionary tale for other legacy companies, not just in the automotive industry. If you don’t build a customer-centric, tech-driven approach to your ways of working you will be disrupted. Previous success is not an indicator of future success. And, as Professor Rita Gunter Mcgrath , continues to remind us the end of competitive advantage is here. Sense, respond and evolve or fail. 

One thought on “ Volkswagen’s electric car ambitions: a Sense & Respond case study ”

Good article! I can add that Design Thinking is an accelerator in any culture change and human touch in digitalization is needed for a good and sustainable customer experience in electrification and e-mobility within automative industry too

Comments are closed.

SustainCase – Sustainability Magazine

• trending News
• Climate News
• Collections
• case studies

Case study: How the Volkswagen Group promotes compliance

The Volkswagen Group is one of the world’s leading automobile manufacturers and the largest automaker in Europe – delivering, in 2018, a total of 10,834,012 cars and commercial vehicles to customers. Compliance with national and international laws and regulations, internal rules and voluntary commitments is among the Volkswagen Group’s guiding principles     Tweet This! , along with ensuring compliant behaviour in a lasting manner.

This case study is based on the 2018 Sustainability Report b y the Volkswagen Group published on the Global Reporting Initiative Sustainability Disclosure Database  that can be found at this link . Through all case studies we aim to demonstrate what CSR/ ESG/ sustainability reporting done responsibly means. Essentially, it means: a) identifying a company’s most important impacts on the environment, economy and society, and b) measuring, managing and changing.

The Volkswagen Group believes that only with lasting, dependable integrity and compliant behaviour will it gain and strengthen the trust of its staff, customers, shareholders, business partners and the general public and seeks to become a role model when it comes to integrity and compliance. In order to promote compliance the Volkswagen Group took action to:

• implement a Code of Conduct
• provide channels for reporting misconduct
• encourage training and communication

Subscribe for free and read the rest of this case study

Please subscribe to the SustainCase Newsletter to keep up to date with the latest sustainability news and gain access to over 2000 case studies. These case studies demonstrate how companies are dealing responsibly with their most important impacts, building trust with their stakeholders (Identify > Measure > Manage > Change).

With this case study you will see:

• Which are the most important impacts (material issues) the Volkswagen Group has identified;
• How the Volkswagen Group proceeded with stakeholder engagement , and
• What actions were taken by the Volkswagen Group to promote compliance

Already Subscribed? Type your email below and click submit

What are the material issues the company has identified?

In its 2018 Sustainability Report the Volkswagen Group identified a range of material issues, such as environmentally friendly products, human rights, product and transport safety, zero-impact mobility, customer satisfaction. Among these, promoting compliance stands out as a key material issue for the Volkswagen Group.

Stakeholder engagement in accordance with the GRI Standards

The Global Reporting Initiative (GRI) defines the Principle of Stakeholder Inclusiveness when identifying material issues (or a company’s most important impacts) as follows:

“The reporting organization shall identify its stakeholders, and explain how it has responded to their reasonable expectations and interests.”

Stakeholders must be consulted in the process of identifying a company’s most important impacts and their reasonable expectations and interests must be taken into account. This is an important cornerstone for CSR / sustainability reporting done responsibly.

Key stakeholder groups the Volkswagen Group engages with:

To identify and prioritise material topics the Volkswagen Group carried out a number of stakeholder surveys and, also, organised a Stakeholder Panel.

What actions were taken by the Volkswagen Group to promote compliance ?

In its 2018 Sustainability Report the Volkswagen Group reports that it took the following actions for promoting compliance:

• Implementing a Code of Conduct
• The Volkswagen Group’s Code of Conduct is the key instrument for strengthening employees’ awareness of correct behaviour and finding the right contact persons in cases of doubt. The Code of Conduct was revised in 2017, and was established throughout the Group. The framework is available to all employees on the intranet and to third parties on the Internet at any time. The Code of Conduct is also integrated into operating processes. For example, employment contracts for employees of Volkswagen AG include a reference to the Code of Conduct and the obligation to comply with it. In addition, compliance with the Code of Conduct remained part of employees’ annual reviews in the reporting period and was thus taken into account when calculating their variable, performance-related remuneration. In addition to the Code of Conduct, there are various Group policies and guidelines regarding specific compliance issues. Organisational instructions also apply on dealing with gifts and invitations, as well as on making donations.
• Providing channels for reporting misconduct
• The Volkswagen Group has had a system for reporting any breaches of the law or rules since 2006. This system is optimised on an ongoing basis. Among other things, a central investigative office has been set up in the Compliance department, which is responsible for coordinating the whistleblower system within the Volkswagen Group and for processing information concerning Volkswagen AG and its subsidiaries. Information on misconduct can be submitted in any of the major languages used by the Group and is treated confidentially. The people providing the information will be protected and need not fear any sanctions for their actions. They can decide for themselves whether they wish to give their names. For this reason, a specially protected online reporting channel was set up in 2017, via which information can be sent to the investigative office anonymously. The Volkswagen Group continues to rely on established channels such as the ombudsman system, too. This system can be used to confidentially report any suspicions – in one of 11 different languages – to two independent lawyers appointed by the Group. The ombudspersons and the whistleblower system can be used by anyone, employees and people outside the Group. In addition to the existing reporting channels, since August 2018 it has also been possible to report potential breaches of rules via a 24/7 telephone hotline. By calling the relevant number, employees, business partners and customers anywhere in the world can provide information round the clock, 365 days a year. A caller who calls the global telephone number will speak to a specially trained person, who can include an interpreter in the call if necessary. In addition, a revised Group policy was passed in 2018. This has further improved the whistleblower system, by providing extra communication options. The whistleblower system was also strengthened significantly by adding more staff. In 2018, a total of 2,920 reports were registered throughout the Group. All substantiated reports have been, or will be, investigated, and any misconduct penalised.
• Encouraging training and communication
• The Code of Conduct, is a key component of compliance training. The training is completed by anyone, from directors to individual employees. Face-to-face and web-based or online training is used. Following a risk-based approach, mandatory compliance training is provided for specific target groups. In addition to traditional lectures and online tutorials, case studies, role-playing games and other interactive formats form part of the training provided to employees and managers. Employees can also use special e-mail addresses to solicit advice on compliance issues. All internal channels are used to communicate regulations and other compliance-related content, with a focus on further developing the whistleblower system over the course of the reporting period. Online communication takes place mainly via employees’ own posts on the Volkswagen intranet and on the internal, Group-wide communications platform “Group Connect”. There are also articles, interviews and other publications in cross-brand and specific divisions’ media. At the same time, compliance-related issues are publicised at various employee information events and company meetings held at a number of locations.

Which GRI Standards and corresponding Sustainable Development Goals (SDGs) have been addressed?

The GRI Standards addressed in this case are:

1)  Disclosure 205-2 Communication and training about anti-corruption policies and procedures

2)  Disclosure 205-3 Confirmed incidents of corruption and actions taken

Disclosure 205-2  Communication and training about anti-corruption policies and procedures corresponds to:

• Sustainable Development Goal (SDG) 16 : Promote peaceful and inclusive societies for sustainable development, provide access to justice for all and build effective, accountable and inclusive institutions at all levels
• Business theme:  Anti-corruption

Disclosure 205-3  Confirmed incidents of corruption and actions taken corresponds to:

78% of the world’s 250 largest companies report in accordance with the GRI Standards

SustainCase was primarily created to demonstrate, through case studies, the importance of dealing with a company’s most important impacts in a structured way, with use of the GRI Standards. To show how today’s best-run companies are achieving economic, social and environmental success – and how you can too.

Research by well-recognised institutions is clearly proving that responsible companies can look to the future with optimism .

7 GRI sustainability disclosures get you started

Any size business can start taking sustainability action

GRI, IEMA, CPD Certified Sustainability courses (2-5 days): Live Online or Classroom  (venue: London School of Economics)

• Exclusive FBRH template to begin reporting from day one
• Identify your most important impacts on the Environment, Economy and People
• Formulate in group exercises your plan for action. Begin taking solid, focused, all-round sustainability action ASAP. 
• Benchmarking methodology to set you on a path of continuous improvement

See upcoming training dates.

References:

1) This case study is based on published information by the Volkswagen Group, located at the link below. For the sake of readability, we did not use brackets or ellipses. However, we made sure that the extra or missing words did not change the report’s meaning. If you would like to quote these written sources from the original, please revert to the original on the Global Reporting Initiative’s Sustainability Disclosure Database at the link:

http://database.globalreporting.org/

2)  https://www.globalreporting.org/standards/gri-standards-download-center/

Note to the Volkswagen Group: With each case study we send out an email requesting a comment on this case study. If you have not received such an email please contact us .

Privacy Overview

MBA Knowledge Base

Business • Management • Technology

Home » Management Case Studies » Case Study: Corporate Merger Between Volkswagen and Porsche

Case Study: Corporate Merger Between Volkswagen and Porsche

The German Dr. Ing. H. C. F. Porsche (Porsche) automobile manufacturer specializes in sports cars and a new line of all-terrain vehicles. In the mid-2000s, Porsche was recognized as a leading global brand for its consistent quality and cultural icon status with models including the 911, the Boxster, and the Cayenne. The company achieved strong financial performance cementing Porsche’s market dominance. Porsche’s operating profit increased from 1,204 million in 2002 to 1,832 million in 2006, representing a growth rate of 52.1%. The net profit of the company also increased to 1,368 million in 2006, an increase of 74.8% over 2005.

One of the central elements of Porsche’s business model is its low manufacturing depth, which means that it does not have huge centralized production plants. Many building processes are outsourced while Porsche concentrates on its core competencies of development, engine production, quality control , and sale of vehicles. This allows Porsche to keep trim and agile in the luxury market.

Volkswagen AG is a manufacturer of passenger and commercial vehicles. The group markets its vehicles under the following brands: Volkswagen passenger cars, Audi, Skoda, SEAT, Bentley, Scania, and Volkswagen commercial vehicles. A strong brand portfolio enables Volkswagen to provide a competitive advantage over its peers. Leading market position enhanced the brand image of the group and held investors’ confidence. In 2007, the group increased the number of vehicles delivered to customers to 6.2 million, corresponding to a 9.8% share of the world passenger car market. However, rising raw material prices threaten the margins of the group by increasing its operating costs.

The Underlying Reasons Why Porsche Attempted to Takeover Volkswagen

With the protection of Germany’s 1960 “VW Law” that long shielded Volkswagen from takeover, no matter how poorly it performed. VW’s 174,000 workers exerted a huge influence over management through their Labor Union which focused on protecting jobs at the expense of efficiency. The German state, with its 20% share, typically sided with labor over the years because they were reluctant to restructure VW’s inefficient operations and eliminate jobs. With governing bodies that cared more for jobs than future growth, VW became increasingly inefficient and entered the 21st century with a bloated workforce, the highest manufacturing costs, and the shortest workweek [32 hours] in the global automotive industry.

Evidence of just how unruly VW had become erupted in a 2005 scandal when evidence was revealed of millions of dollars in funds granted by management to bribe union leaders for their support. The funds were used to pay for pleasure trips, parties, and others. After being carried for many news cycles, several managers have pleaded guilty to paying off labor officials and have been fined.

In the mid-2000s, VW was palpably vulnerable, but why a takeover bid? Why would the world’s most profitable automaker sink billions into mass-market VW with its debilitating cost structure , strong unions, and weak profits?

A closer look reveals that Porsche moved to take VW for their technology development and keep access to a production ally. In effect, though Porsche was financially stronger, it needed VW more than VW needed Porsche. Only about 20% of what makes a Porsche a Porsche-largely the engine and transmission is made by Porsche workers. The rest is outsourced, mainly to VW. Porsche co-developed the Cayenne with Volkswagen, sharing parts, production, and development costs. The joint development and outsourced production help fuel Porsche’s profits by keeping its fixed costs and capital investments low. In addition, the planned integration of Porsche into Volkswagen and the associated, closer cooperation will realize significant synergies on both the income and the cost side. Both companies could focus on finding synergies for such items as electronic architectures and engineering work on future vehicle circuitry platforms and common parts such as air conditioning.

For Volkswagen, the merger benefits are clear — protection against a hostile takeover . It may also get a lift from Porsche’s image and well-regarded management. VW needs the help. With profits of 484 million on sales of 55.4 billion in the first half of calendar 2005, VW’s profit margin is less than 1%. Volkswagen has 15 times the annual revenue of Porsche-but Porsche’s profit margins are seven times bigger than VW’s.

VW was a gold mine for Porsche as they envisioned the future demand for products designed by Porsche but co-produced by Volkswagen. Porsche focused on a particular type of luxury product and VW ran stables of brands producing across many segments. With the threat of materials costs shooting through the roof, Porsche was looking for ways to turn threats into opportunities and garner some serious market power. VW was a goldmine. The only thing that Porsche would have to do was dig day and night.

Strategy to Gain Control

Porsche utilized pure financial leverage combined with speculation to attempt to gain control over VW. All of these actions were not done in complete secrecy, but the information fed to the public was a time in a very strategic way.

On the open market Porsche accumulated shares in VW and accompanied these actions with simple and believable statements that they were merely trying to secure VW as a partner company in the development of different platforms of cars. Porsche made statements to the effect that they were not interested in owning VW but merely had a vested interest in the continued cooperation of the two companies for joint ventures.

Simultaneously and not so publicly Porsche bought options on VW stock by paying a fee to be able to purchase VW shares at a given price sometime in the future. These types of transactions are extremely common in financial markets; however, the extent to which Porsche did this was tremendous. In the end, they had accumulated these options to such an extent that they had the right to purchase nearly every free share on the market. Before this information was public, it had little effect on the share prices. However, when Porsche went public with this information, market forces went to work. The financial institutions that had sold these options to Porsche had done so “short” meaning they did not actually own the shares. When these institutions learned of the situation they realized that Porsche would exercise these options to attain 75% of VW, and they would be forced to buy VE shares on the open market and sell them to Porsche at the lower agreed price. This resulted in the institutions rushing to purchase all available shares to minimize their losses when Porsche exercised the options.

The accumulation of the options and the resulting profits from exercising these options certainly emboldened Porsche to press for an ever-larger stake in VW. With stable financing in place, Porsche could have essentially bought 75% of VW, with the government owning 20%, and only 5% of the share would be public. Stable financing and overall economic conditions that existed during the final push for shares severely stressed the financial capabilities of Porsche. As a result, the hostile takeover attempt has morphed into a merger offer. Additionally, the legal battle with the state of Lower Saxony continues. The VW law continues to be an obstacle to the voting right of all other shareholders.

Impact of the Attempted Take-Over on Stock Prices

The most striking result comes from a comparison of the two company’s stock prices at the beginning of this period and the ending relationship in stock value on a percentage basis. The most divergent area in October of 2006 was the direct result of the secretive accumulation of options on VW stock by Porsche. As stated above the announcement by Porsche that essentially has claims to all the remaining VW shares on the open market sent investments banks scrambling. These investment banks were the ones that were short VW shares and essentially could have the options put at them resulting in huge losses. The attempt to cover all the outstanding options drove the share price of VW through the proverbial roof.

As it stands on June 25, 2010, the share price of Porsche is 36.04$ as compared to a share price of 94.04$ on September 3, 2008, the earliest date available on Yahoo Finance. This represents a 62% decline in the value of the company. During the same period, VW shares have gone from 199.52$ to 79.01. In essence, this merger has been completed although outstanding issues remain. During the course of this attempted takeover now turned merger over 50% of the market value of the two companies has been lost.

Initial Merger Proposal and the Final Outcome

The saga of the Porsche-VW merger began with an attempt by Porsche to secure production agreements with VW by acquiring a 31% share, which, along with the government’s 20% share, would make VW unassailable by threats from outside interests. Whether or not this was the actual intent of Porsche or a disguised initial play to gain control of VW is unknown, but soon after, Porsche began a run to obtain up to 75% of VW, ending up with 51%.

Having gained control, Porsche still faced three obstacles: 1) Germany’s prevailing “VW Law,” which limits any shareholder’s voting rights to 20%, regardless of the number of shares they own, 2) the large amount of debt they shouldered in the acquisition process, and 3) suspicions about the foul play during an options deal on VW stock where Porsche made millions.

One of these obstacles was overcome when the European Commission ordered Germany to repeal the VW Law because it restricted the free flow of capital, but the debt proved to be overwhelming, in part due to the recession and the difficulty firms faced obtaining capital at reasonable rates, and Porsche was forced to turn to VW for help. This was the beginning of the final merger process , which, as of today, is still incomplete due, in part, to lingering suspicions about the options deal.

Although not set in stone, as it stands, VW owns 49.9% of Porsche while Porsche owns 53% of VW, Qatar Holding owns 10% of Porsche and 17% of VW and the government of Lower Saxony retains its 20% of VW. The Piech and Porsche families, the founders of both companies, own about 40% of the merged company and Porsche’s CEO and CFO, the guys who engineered the options deal and the takeover bid, and who turned Porsche into a profitable company in the first place, have resigned.

Highlight both Costs and Benefits for both Firms under the Proposed Merger

The benefits of the merger are that VW’s operating profit is expected to increase by 700 million euros a year, Porsche engineering may boost the appeal of VW’s more expensive models, and the “platform” system of cutting costs by using standard parts for multiple car models will be expanded as Porsche lines are integrated into VW’s stable. Another benefit, which may not be a benefit so much as a bragging right, is that an expansion of VW brings it that much closer to becoming the world’s biggest carmaker. Finally, and although not directly tied to the merger an issue that gained additional attention from it, is the EU-ordered repeal of the VW Law. Porsche’s former boss, Wiedeking, was looking forward to changing VW’s culture from a socialized, semi-protected concern to a capital-efficient machine-like Porsche, and if VW does indeed become more competitive in the global market as a result of the merger or the repeal of the law they could see an increase in profits.

In contrast to the more speculative nature of the merger’s benefits are its costs. At the top of the list is the debt load acquired by both companies during the process, particularly Porsche, which racked up 12 billion when it was buying VW stock. During the merger, Porsche has been losing billions due to costs associated with combining with VW. In the second half of 2009, Porsche’s net income dropped by 83%, and is planning to raise 5 billion through stock issuance. Porsche’s exposure in the options lawsuit has expanded to nearly 2 billion. For its part, VW is paying 3.9 billion for 49.9% of Porsche and is selling 135 million preferred shares in the next few years to cover some of the cost. Meanwhile, both VW and Porsche seem to be counting on increasing sales in Brazil and China to cover those debts.

Secondly, there is the tension created by putting the competing brands of Audi, Bentley, Porsche, Bugatti, and Lamborghini under the same, corporate umbrella, a move that should naturally result in a reduction in the number of models offered and price increases in the luxury car market.

Finally, there is also the issue of management to consider. Porsche was the world’s most profitable, small carmaker when the process began, and its initial steps to acquire VW shares were motivated by that company’s weakness. Now with the merger, the new company is larger and more debt-ridden, and VW’s leadership will be taking over Porsche rather than the other way around. In essence, a larger, weaker company has absorbed a smaller, stronger one, and while Porsche seemed to have a strategy of turning VW into a more cost-efficient and profitable company, VW is merging with Porsche only because it can, or must.

On paper, with its 53% share of VW, Porsche seems to have control, since VW only owns 49.9% of Porsche. However, Bloomberg is reporting that “Volkswagen AG considers naming Matthias Mueller, its chief product strategist, to run the sports-car maker (Porsche)”, which is a strong indication that VW is calling the shots and supports the frequent descriptions of VW’s “reverse take-over.” However, the reality is that the ownership of the two companies is so closely tied that it is easier just to say they remain under the control of the Piech and Porsche families, with large portions held by Lower Saxony and Qatar. In fact, there are so few shares left available that VW’s ordinary shares might be removed from the German stock exchange.

As previously stated, we don’t believe that the merger was particularly worthwhile because the costs involved outweigh the benefits. Certainly, the 2008 recession exasperated the cost involved because Porsche’s access to cheap capital became harder to come by. It racked up more debt acquiring VW stock than it would have a year or two earlier. In this sense, Porsche choose a poor time to embark on an aggressive, financial maneuver, and VW, who performed their own “reverse take-over” later on, did so in the same environment.

New car sales were down globally in 2008, and the general reduction in sales should’ve affected both companies equally, making it a moot point. Although it isn’t explicitly mentioned, Porsche should’ve suffered more in the recession because they only sell a luxury products, a category of goods that is very elastic in relation to income levels. VW, in contrast, has a wider variety of products, including more affordable cars, which might help to keep them afloat as sales of their many luxury brands fall off.

Rising oil prices shouldn’t be that important to VW or Porsche. Owners of luxury cars that sell for more than 100,000 don’t blink if the cost of gasoline goes up, so Porsche sales should be unaffected. VW’s luxury models should also see the same effect. However, VW should see a short-term drop-off in sales of their affordable, high consumption models like their SUVs but partially make up for that drop-off in increased sales of more fuel-efficient models, although those tend to have smaller profit margins.

Related Posts:

• Business Strategy Case Study: Relaunch of Fiat 500
• Brand Case Study: De Beers,Volkswagen and Nokia
• Case Study: Causes of the Recent Decline of Tesla
• Case Study on Corporate Governance: WorldCom Scandal
• Case Study: An Analysis of Competitive Advantages of Honda Corporation
• Case Study: Acquisition of Jaguar and Land Rover by Tata Motors
• Case Study: Delta Airlines Successful Business Turnaround Strategy
• The Leveraged Buy-out Deal of Tata & Tetley
• Case Study: Frequent Restructuring at Sony Corporation
• Case Study: Restructuring Process of Volkswagen

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

• 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

281 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]