case study questions for teachers

Using Case Studies to Teach

Why Use Cases?

Many students are more inductive than deductive reasoners, which means that they learn better from examples than from logical development starting with basic principles. The use of case studies can therefore be a very effective classroom technique.

Case studies are have long been used in business schools, law schools, medical schools and the social sciences, but they can be used in any discipline when instructors want students to explore how what they have learned applies to real world situations. Cases come in many formats, from a simple “What would you do in this situation?” question to a detailed description of a situation with accompanying data to analyze. Whether to use a simple scenario-type case or a complex detailed one depends on your course objectives.

Most case assignments require students to answer an open-ended question or develop a solution to an open-ended problem with multiple potential solutions. Requirements can range from a one-paragraph answer to a fully developed group action plan, proposal or decision.

Common Case Elements

Most “full-blown” cases have these common elements:

• A decision-maker who is grappling with some question or problem that needs to be solved.
• A description of the problem’s context (a law, an industry, a family).
• Supporting data, which can range from data tables to links to URLs, quoted statements or testimony, supporting documents, images, video, or audio.

Case assignments can be done individually or in teams so that the students can brainstorm solutions and share the work load.

The following discussion of this topic incorporates material presented by Robb Dixon of the School of Management and Rob Schadt of the School of Public Health at CEIT workshops. Professor Dixon also provided some written comments that the discussion incorporates.

Advantages to the use of case studies in class

A major advantage of teaching with case studies is that the students are actively engaged in figuring out the principles by abstracting from the examples. This develops their skills in:

• Problem solving
• Analytical tools, quantitative and/or qualitative, depending on the case
• Decision making in complex situations
• Coping with ambiguities

Guidelines for using case studies in class

In the most straightforward application, the presentation of the case study establishes a framework for analysis. It is helpful if the statement of the case provides enough information for the students to figure out solutions and then to identify how to apply those solutions in other similar situations. Instructors may choose to use several cases so that students can identify both the similarities and differences among the cases.

Depending on the course objectives, the instructor may encourage students to follow a systematic approach to their analysis.  For example:

• What is the issue?
• What is the goal of the analysis?
• What is the context of the problem?
• What key facts should be considered?
• What alternatives are available to the decision-maker?
• What would you recommend — and why?

An innovative approach to case analysis might be to have students  role-play the part of the people involved in the case. This not only actively engages students, but forces them to really understand the perspectives of the case characters. Videos or even field trips showing the venue in which the case is situated can help students to visualize the situation that they need to analyze.

Accompanying Readings

Case studies can be especially effective if they are paired with a reading assignment that introduces or explains a concept or analytical method that applies to the case. The amount of emphasis placed on the use of the reading during the case discussion depends on the complexity of the concept or method. If it is straightforward, the focus of the discussion can be placed on the use of the analytical results. If the method is more complex, the instructor may need to walk students through its application and the interpretation of the results.

Leading the Case Discussion and Evaluating Performance

Decision cases are more interesting than descriptive ones. In order to start the discussion in class, the instructor can start with an easy, noncontroversial question that all the students should be able to answer readily. However, some of the best case discussions start by forcing the students to take a stand. Some instructors will ask a student to do a formal “open” of the case, outlining his or her entire analysis.  Others may choose to guide discussion with questions that move students from problem identification to solutions.  A skilled instructor steers questions and discussion to keep the class on track and moving at a reasonable pace.

In order to motivate the students to complete the assignment before class as well as to stimulate attentiveness during the class, the instructor should grade the participation—quantity and especially quality—during the discussion of the case. This might be a simple check, check-plus, check-minus or zero. The instructor should involve as many students as possible. In order to engage all the students, the instructor can divide them into groups, give each group several minutes to discuss how to answer a question related to the case, and then ask a randomly selected person in each group to present the group’s answer and reasoning. Random selection can be accomplished through rolling of dice, shuffled index cards, each with one student’s name, a spinning wheel, etc.

Tips on the Penn State U. website: http://tlt.its.psu.edu/suggestions/cases/

If you are interested in using this technique in a science course, there is a good website on use of case studies in the sciences at the University of Buffalo.

Dunne, D. and Brooks, K. (2004) Teaching with Cases (Halifax, NS: Society for Teaching and Learning in Higher Education), ISBN 0-7703-8924-4 (Can be ordered at http://www.bookstore.uwo.ca/ at a cost of $15.00)

Center for Teaching

Case studies.

Print Version

Case studies are stories that are used as a teaching tool to show the application of a theory or concept to real situations. Dependent on the goal they are meant to fulfill, cases can be fact-driven and deductive where there is a correct answer, or they can be context driven where multiple solutions are possible. Various disciplines have employed case studies, including humanities, social sciences, sciences, engineering, law, business, and medicine. Good cases generally have the following features: they tell a good story, are recent, include dialogue, create empathy with the main characters, are relevant to the reader, serve a teaching function, require a dilemma to be solved, and have generality.

Instructors can create their own cases or can find cases that already exist. The following are some things to keep in mind when creating a case:

• What do you want students to learn from the discussion of the case?
• What do they already know that applies to the case?
• What are the issues that may be raised in discussion?
• How will the case and discussion be introduced?
• What preparation is expected of students? (Do they need to read the case ahead of time? Do research? Write anything?)
• What directions do you need to provide students regarding what they are supposed to do and accomplish?
• Do you need to divide students into groups or will they discuss as the whole class?
• Are you going to use role-playing or facilitators or record keepers? If so, how?
• What are the opening questions?
• How much time is needed for students to discuss the case?
• What concepts are to be applied/extracted during the discussion?
• How will you evaluate students?

To find other cases that already exist, try the following websites:

• The National Center for Case Study Teaching in Science , University of Buffalo. SUNY-Buffalo maintains this set of links to other case studies on the web in disciplines ranging from engineering and ethics to sociology and business
• A Journal of Teaching Cases in Public Administration and Public Policy , University of Washington

For more information:

• World Association for Case Method Research and Application

Book Review :  Teaching and the Case Method , 3rd ed., vols. 1 and 2, by Louis Barnes, C. Roland (Chris) Christensen, and Abby Hansen. Harvard Business School Press, 1994; 333 pp. (vol 1), 412 pp. (vol 2).

Teaching Guides

• Online Course Development Resources
• Principles & Frameworks
• Pedagogies & Strategies
• Reflecting & Assessing
• Challenges & Opportunities
• Populations & Contexts

Quick Links

• Services for Departments and Schools
• Examples of Online Instructional Modules

• Our Mission

Making Learning Relevant With Case Studies

The open-ended problems presented in case studies give students work that feels connected to their lives.

To prepare students for jobs that haven’t been created yet, we need to teach them how to be great problem solvers so that they’ll be ready for anything. One way to do this is by teaching content and skills using real-world case studies, a learning model that’s focused on reflection during the problem-solving process. It’s similar to project-based learning, but PBL is more focused on students creating a product.

Case studies have been used for years by businesses, law and medical schools, physicians on rounds, and artists critiquing work. Like other forms of problem-based learning, case studies can be accessible for every age group, both in one subject and in interdisciplinary work.

You can get started with case studies by tackling relatable questions like these with your students:

• How can we limit food waste in the cafeteria?
• How can we get our school to recycle and compost waste? (Or, if you want to be more complex, how can our school reduce its carbon footprint?)
• How can we improve school attendance?
• How can we reduce the number of people who get sick at school during cold and flu season?

Addressing questions like these leads students to identify topics they need to learn more about. In researching the first question, for example, students may see that they need to research food chains and nutrition. Students often ask, reasonably, why they need to learn something, or when they’ll use their knowledge in the future. Learning is most successful for students when the content and skills they’re studying are relevant, and case studies offer one way to create that sense of relevance.

Teaching With Case Studies

Ultimately, a case study is simply an interesting problem with many correct answers. What does case study work look like in classrooms? Teachers generally start by having students read the case or watch a video that summarizes the case. Students then work in small groups or individually to solve the case study. Teachers set milestones defining what students should accomplish to help them manage their time.

During the case study learning process, student assessment of learning should be focused on reflection. Arthur L. Costa and Bena Kallick’s Learning and Leading With Habits of Mind gives several examples of what this reflection can look like in a classroom: 

Journaling: At the end of each work period, have students write an entry summarizing what they worked on, what worked well, what didn’t, and why. Sentence starters and clear rubrics or guidelines will help students be successful. At the end of a case study project, as Costa and Kallick write, it’s helpful to have students “select significant learnings, envision how they could apply these learnings to future situations, and commit to an action plan to consciously modify their behaviors.”

Interviews: While working on a case study, students can interview each other about their progress and learning. Teachers can interview students individually or in small groups to assess their learning process and their progress.

Student discussion: Discussions can be unstructured—students can talk about what they worked on that day in a think-pair-share or as a full class—or structured, using Socratic seminars or fishbowl discussions. If your class is tackling a case study in small groups, create a second set of small groups with a representative from each of the case study groups so that the groups can share their learning.

4 Tips for Setting Up a Case Study

1. Identify a problem to investigate: This should be something accessible and relevant to students’ lives. The problem should also be challenging and complex enough to yield multiple solutions with many layers.

2. Give context: Think of this step as a movie preview or book summary. Hook the learners to help them understand just enough about the problem to want to learn more.

3. Have a clear rubric: Giving structure to your definition of quality group work and products will lead to stronger end products. You may be able to have your learners help build these definitions.

4. Provide structures for presenting solutions: The amount of scaffolding you build in depends on your students’ skill level and development. A case study product can be something like several pieces of evidence of students collaborating to solve the case study, and ultimately presenting their solution with a detailed slide deck or an essay—you can scaffold this by providing specified headings for the sections of the essay.

Problem-Based Teaching Resources

There are many high-quality, peer-reviewed resources that are open source and easily accessible online.

• The National Center for Case Study Teaching in Science at the University at Buffalo built an online collection of more than 800 cases that cover topics ranging from biochemistry to economics. There are resources for middle and high school students.
• Models of Excellence , a project maintained by EL Education and the Harvard Graduate School of Education, has examples of great problem- and project-based tasks—and corresponding exemplary student work—for grades pre-K to 12.
• The Interdisciplinary Journal of Problem-Based Learning at Purdue University is an open-source journal that publishes examples of problem-based learning in K–12 and post-secondary classrooms.
• The Tech Edvocate has a list of websites and tools related to problem-based learning.

In their book Problems as Possibilities , Linda Torp and Sara Sage write that at the elementary school level, students particularly appreciate how they feel that they are taken seriously when solving case studies. At the middle school level, “researchers stress the importance of relating middle school curriculum to issues of student concern and interest.” And high schoolers, they write, find the case study method “beneficial in preparing them for their future.”

How it works

For Business

Join Mind Tools

Article • 10 min read

Case Study-Based Learning

Enhancing learning through immediate application.

By the Mind Tools Content Team

If you've ever tried to learn a new concept, you probably appreciate that "knowing" is different from "doing." When you have an opportunity to apply your knowledge, the lesson typically becomes much more real.

Adults often learn differently from children, and we have different motivations for learning. Typically, we learn new skills because we want to. We recognize the need to learn and grow, and we usually need – or want – to apply our newfound knowledge soon after we've learned it.

A popular theory of adult learning is andragogy (the art and science of leading man, or adults), as opposed to the better-known pedagogy (the art and science of leading children). Malcolm Knowles , a professor of adult education, was considered the father of andragogy, which is based on four key observations of adult learners:

• Adults learn best if they know why they're learning something.
• Adults often learn best through experience.
• Adults tend to view learning as an opportunity to solve problems.
• Adults learn best when the topic is relevant to them and immediately applicable.

This means that you'll get the best results with adults when they're fully involved in the learning experience. Give an adult an opportunity to practice and work with a new skill, and you have a solid foundation for high-quality learning that the person will likely retain over time.

So, how can you best use these adult learning principles in your training and development efforts? Case studies provide an excellent way of practicing and applying new concepts. As such, they're very useful tools in adult learning, and it's important to understand how to get the maximum value from them.

What Is a Case Study?

Case studies are a form of problem-based learning, where you present a situation that needs a resolution. A typical business case study is a detailed account, or story, of what happened in a particular company, industry, or project over a set period of time.

The learner is given details about the situation, often in a historical context. The key players are introduced. Objectives and challenges are outlined. This is followed by specific examples and data, which the learner then uses to analyze the situation, determine what happened, and make recommendations.

The depth of a case depends on the lesson being taught. A case study can be two pages, 20 pages, or more. A good case study makes the reader think critically about the information presented, and then develop a thorough assessment of the situation, leading to a well-thought-out solution or recommendation.

Why Use a Case Study?

Case studies are a great way to improve a learning experience, because they get the learner involved, and encourage immediate use of newly acquired skills.

They differ from lectures or assigned readings because they require participation and deliberate application of a broad range of skills. For example, if you study financial analysis through straightforward learning methods, you may have to calculate and understand a long list of financial ratios (don't worry if you don't know what these are). Likewise, you may be given a set of financial statements to complete a ratio analysis. But until you put the exercise into context, you may not really know why you're doing the analysis.

With a case study, however, you might explore whether a bank should provide financing to a borrower, or whether a company is about to make a good acquisition. Suddenly, the act of calculating ratios becomes secondary – it's more important to understand what the ratios tell you. This is how case studies can make the difference between knowing what to do, and knowing how, when, and why to do it.

Then, what really separates case studies from other practical forms of learning – like scenarios and simulations – is the ability to compare the learner's recommendations with what actually happened. When you know what really happened, it's much easier to evaluate the "correctness" of the answers given.

When to Use a Case Study

As you can see, case studies are powerful and effective training tools. They also work best with practical, applied training, so make sure you use them appropriately.

Remember these tips:

• Case studies tend to focus on why and how to apply a skill or concept, not on remembering facts and details. Use case studies when understanding the concept is more important than memorizing correct responses.
• Case studies are great team-building opportunities. When a team gets together to solve a case, they'll have to work through different opinions, methods, and perspectives.
• Use case studies to build problem-solving skills, particularly those that are valuable when applied, but are likely to be used infrequently. This helps people get practice with these skills that they might not otherwise get.
• Case studies can be used to evaluate past problem solving. People can be asked what they'd do in that situation, and think about what could have been done differently.

Ensuring Maximum Value From Case Studies

The first thing to remember is that you already need to have enough theoretical knowledge to handle the questions and challenges in the case study. Otherwise, it can be like trying to solve a puzzle with some of the pieces missing.

Here are some additional tips for how to approach a case study. Depending on the exact nature of the case, some tips will be more relevant than others.

• Read the case at least three times before you start any analysis. Case studies usually have lots of details, and it's easy to miss something in your first, or even second, reading.
• Once you're thoroughly familiar with the case, note the facts. Identify which are relevant to the tasks you've been assigned. In a good case study, there are often many more facts than you need for your analysis.
• If the case contains large amounts of data, analyze this data for relevant trends. For example, have sales dropped steadily, or was there an unexpected high or low point?
• If the case involves a description of a company's history, find the key events, and consider how they may have impacted the current situation.
• Consider using techniques like SWOT analysis and Porter's Five Forces Analysis to understand the organization's strategic position.
• Stay with the facts when you draw conclusions. These include facts given in the case as well as established facts about the environmental context. Don't rely on personal opinions when you put together your answers.

Writing a Case Study

You may have to write a case study yourself. These are complex documents that take a while to research and compile. The quality of the case study influences the quality of the analysis. Here are some tips if you want to write your own:

• Write your case study as a structured story. The goal is to capture an interesting situation or challenge and then bring it to life with words and information. You want the reader to feel a part of what's happening.
• Present information so that a "right" answer isn't obvious. The goal is to develop the learner's ability to analyze and assess, not necessarily to make the same decision as the people in the actual case.
• Do background research to fully understand what happened and why. You may need to talk to key stakeholders to get their perspectives as well.
• Determine the key challenge. What needs to be resolved? The case study should focus on one main question or issue.
• Define the context. Talk about significant events leading up to the situation. What organizational factors are important for understanding the problem and assessing what should be done? Include cultural factors where possible.
• Identify key decision makers and stakeholders. Describe their roles and perspectives, as well as their motivations and interests.
• Make sure that you provide the right data to allow people to reach appropriate conclusions.
• Make sure that you have permission to use any information you include.

A typical case study structure includes these elements:

• Executive summary. Define the objective, and state the key challenge.
• Opening paragraph. Capture the reader's interest.
• Scope. Describe the background, context, approach, and issues involved.
• Presentation of facts. Develop an objective picture of what's happening.
• Description of key issues. Present viewpoints, decisions, and interests of key parties.

Because case studies have proved to be such effective teaching tools, many are already written. Some excellent sources of free cases are The Times 100 , CasePlace.org , and Schroeder & Schroeder Inc . You can often search for cases by topic or industry. These cases are expertly prepared, based mostly on real situations, and used extensively in business schools to teach management concepts.

Case studies are a great way to improve learning and training. They provide learners with an opportunity to solve a problem by applying what they know.

There are no unpleasant consequences for getting it "wrong," and cases give learners a much better understanding of what they really know and what they need to practice.

Case studies can be used in many ways, as team-building tools, and for skill development. You can write your own case study, but a large number are already prepared. Given the enormous benefits of practical learning applications like this, case studies are definitely something to consider adding to your next training session.

Knowles, M. (1973). 'The Adult Learner: A Neglected Species [online].' Available here .

You've accessed 1 of your 2 free resources.

Get unlimited access

Discover more content

Book Insights

Five Star Service: How to Deliver Exceptional Customer Service

Michael Heppel

Expert Interviews

Kiss, Bow, or Shake Hands

Terri Morrison

Add comment

Comments (0)

Be the first to comment!

Get 30% off your first year of Mind Tools

Great teams begin with empowered leaders. Our tools and resources offer the support to let you flourish into leadership. Join today!

Sign-up to our newsletter

Subscribing to the Mind Tools newsletter will keep you up-to-date with our latest updates and newest resources.

Subscribe now

Business Skills

Personal Development

Leadership and Management

Member Extras

Most Popular

Newest Releases

What Is Stakeholder Management?

GE-McKinsey Matrix

Mind Tools Store

About Mind Tools Content

Discover something new today

Business reports.

Using the Right Format for Sharing Information

Making the Right Career Move

Choosing the Role That's Best for You

How Emotionally Intelligent Are You?

Boosting Your People Skills

Self-Assessment

What's Your Leadership Style?

Learn About the Strengths and Weaknesses of the Way You Like to Lead

Recommended for you

Negotiation no-nos.

Avoid These Mistakes To Get What You Want

Animated Video

Business Operations and Process Management

Strategy Tools

Customer Service

Business Ethics and Values

Handling Information and Data

Project Management

Knowledge Management

Self-Development and Goal Setting

Time Management

Presentation Skills

Learning Skills

Career Skills

Communication Skills

Negotiation, Persuasion and Influence

Working With Others

Difficult Conversations

Creativity Tools

Self-Management

Work-Life Balance

Stress Management and Wellbeing

Coaching and Mentoring

Change Management

Team Management

Managing Conflict

Delegation and Empowerment

Performance Management

Leadership Skills

Developing Your Team

Talent Management

Problem Solving

Decision Making

Member Podcast

• Columbia University in the City of New York
• Office of Teaching, Learning, and Innovation
• University Policies
• Columbia Online
• Academic Calendar
• Resources and Technology
• Resources and Guides

Case Method Teaching and Learning

What is the case method? How can the case method be used to engage learners? What are some strategies for getting started? This guide helps instructors answer these questions by providing an overview of the case method while highlighting learner-centered and digitally-enhanced approaches to teaching with the case method. The guide also offers tips to instructors as they get started with the case method and additional references and resources.

On this page:

What is case method teaching.

• Case Method at Columbia

Why use the Case Method?

Case method teaching approaches, how do i get started.

• Additional Resources

The CTL is here to help!

For support with implementing a case method approach in your course, email [email protected] to schedule your 1-1 consultation .

Cite this resource: Columbia Center for Teaching and Learning (2019). Case Method Teaching and Learning. Columbia University. Retrieved from [today’s date] from https://ctl.columbia.edu/resources-and-technology/resources/case-method/  

Case method 1 teaching is an active form of instruction that focuses on a case and involves students learning by doing 2 3 . Cases are real or invented stories 4  that include “an educational message” or recount events, problems, dilemmas, theoretical or conceptual issue that requires analysis and/or decision-making.

Case-based teaching simulates real world situations and asks students to actively grapple with complex problems 5 6 This method of instruction is used across disciplines to promote learning, and is common in law, business, medicine, among other fields. See Table 1 below for a few types of cases and the learning they promote.

Table 1: Types of cases and the learning they promote.

For a more complete list, see Case Types & Teaching Methods: A Classification Scheme from the National Center for Case Study Teaching in Science.

Back to Top

Case Method Teaching and Learning at Columbia

The case method is actively used in classrooms across Columbia, at the Morningside campus in the School of International and Public Affairs (SIPA), the School of Business, Arts and Sciences, among others, and at Columbia University Irving Medical campus.

Faculty Spotlight:

Professor Mary Ann Price on Using Case Study Method to Place Pre-Med Students in Real-Life Scenarios

Read more  

Professor De Pinho on Using the Case Method in the Mailman Core

Case method teaching has been found to improve student learning, to increase students’ perception of learning gains, and to meet learning objectives 8 9 . Faculty have noted the instructional benefits of cases including greater student engagement in their learning 10 , deeper student understanding of concepts, stronger critical thinking skills, and an ability to make connections across content areas and view an issue from multiple perspectives 11 . 

Through case-based learning, students are the ones asking questions about the case, doing the problem-solving, interacting with and learning from their peers, “unpacking” the case, analyzing the case, and summarizing the case. They learn how to work with limited information and ambiguity, think in professional or disciplinary ways, and ask themselves “what would I do if I were in this specific situation?”

The case method bridges theory to practice, and promotes the development of skills including: communication, active listening, critical thinking, decision-making, and metacognitive skills 12 , as students apply course content knowledge, reflect on what they know and their approach to analyzing, and make sense of a case. 

Though the case method has historical roots as an instructor-centered approach that uses the Socratic dialogue and cold-calling, it is possible to take a more learner-centered approach in which students take on roles and tasks traditionally left to the instructor. 

Cases are often used as “vehicles for classroom discussion” 13 . Students should be encouraged to take ownership of their learning from a case. Discussion-based approaches engage students in thinking and communicating about a case. Instructors can set up a case activity in which students are the ones doing the work of “asking questions, summarizing content, generating hypotheses, proposing theories, or offering critical analyses” 14 . 

The role of the instructor is to share a case or ask students to share or create a case to use in class, set expectations, provide instructions, and assign students roles in the discussion. Student roles in a case discussion can include: 

• discussion “starters” get the conversation started with a question or posing the questions that their peers came up with; 
• facilitators listen actively, validate the contributions of peers, ask follow-up questions, draw connections, refocus the conversation as needed; 
• recorders take-notes of the main points of the discussion, record on the board, upload to CourseWorks, or type and project on the screen; and 
• discussion “wrappers” lead a summary of the main points of the discussion. 

Prior to the case discussion, instructors can model case analysis and the types of questions students should ask, co-create discussion guidelines with students, and ask for students to submit discussion questions. During the discussion, the instructor can keep time, intervene as necessary (however the students should be doing the talking), and pause the discussion for a debrief and to ask students to reflect on what and how they learned from the case activity. 

Note: case discussions can be enhanced using technology. Live discussions can occur via video-conferencing (e.g., using Zoom ) or asynchronous discussions can occur using the Discussions tool in CourseWorks (Canvas) .

Table 2 includes a few interactive case method approaches. Regardless of the approach selected, it is important to create a learning environment in which students feel comfortable participating in a case activity and learning from one another. See below for tips on supporting student in how to learn from a case in the “getting started” section and how to create a supportive learning environment in the Guide for Inclusive Teaching at Columbia . 

Table 2. Strategies for Engaging Students in Case-Based Learning

Approaches to case teaching should be informed by course learning objectives, and can be adapted for small, large, hybrid, and online classes. Instructional technology can be used in various ways to deliver, facilitate, and assess the case method. For instance, an online module can be created in CourseWorks (Canvas) to structure the delivery of the case, allow students to work at their own pace, engage all learners, even those reluctant to speak up in class, and assess understanding of a case and student learning. Modules can include text, embedded media (e.g., using Panopto or Mediathread ) curated by the instructor, online discussion, and assessments. Students can be asked to read a case and/or watch a short video, respond to quiz questions and receive immediate feedback, post questions to a discussion, and share resources. 

For more information about options for incorporating educational technology to your course, please contact your Learning Designer .

To ensure that students are learning from the case approach, ask them to pause and reflect on what and how they learned from the case. Time to reflect  builds your students’ metacognition, and when these reflections are collected they provides you with insights about the effectiveness of your approach in promoting student learning.

Well designed case-based learning experiences: 1) motivate student involvement, 2) have students doing the work, 3) help students develop knowledge and skills, and 4) have students learning from each other.  

Designing a case-based learning experience should center around the learning objectives for a course. The following points focus on intentional design. 

Identify learning objectives, determine scope, and anticipate challenges. 

• Why use the case method in your course? How will it promote student learning differently than other approaches? 
• What are the learning objectives that need to be met by the case method? What knowledge should students apply and skills should they practice? 
• What is the scope of the case? (a brief activity in a single class session to a semester-long case-based course; if new to case method, start small with a single case). 
• What challenges do you anticipate (e.g., student preparation and prior experiences with case learning, discomfort with discussion, peer-to-peer learning, managing discussion) and how will you plan for these in your design? 
• If you are asking students to use transferable skills for the case method (e.g., teamwork, digital literacy) make them explicit. 

Determine how you will know if the learning objectives were met and develop a plan for evaluating the effectiveness of the case method to inform future case teaching. 

• What assessments and criteria will you use to evaluate student work or participation in case discussion? 
• How will you evaluate the effectiveness of the case method? What feedback will you collect from students? 
• How might you leverage technology for assessment purposes? For example, could you quiz students about the case online before class, accept assignment submissions online, use audience response systems (e.g., PollEverywhere) for formative assessment during class? 

Select an existing case, create your own, or encourage students to bring course-relevant cases, and prepare for its delivery

• Where will the case method fit into the course learning sequence? 
• Is the case at the appropriate level of complexity? Is it inclusive, culturally relevant, and relatable to students? 
• What materials and preparation will be needed to present the case to students? (e.g., readings, audiovisual materials, set up a module in CourseWorks). 

Plan for the case discussion and an active role for students

• What will your role be in facilitating case-based learning? How will you model case analysis for your students? (e.g., present a short case and demo your approach and the process of case learning) (Davis, 2009). 
• What discussion guidelines will you use that include your students’ input? 
• How will you encourage students to ask and answer questions, summarize their work, take notes, and debrief the case? 
• If students will be working in groups, how will groups form? What size will the groups be? What instructions will they be given? How will you ensure that everyone participates? What will they need to submit? Can technology be leveraged for any of these areas? 
• Have you considered students of varied cognitive and physical abilities and how they might participate in the activities/discussions, including those that involve technology? 

Student preparation and expectations

• How will you communicate about the case method approach to your students? When will you articulate the purpose of case-based learning and expectations of student engagement? What information about case-based learning and expectations will be included in the syllabus?
• What preparation and/or assignment(s) will students complete in order to learn from the case? (e.g., read the case prior to class, watch a case video prior to class, post to a CourseWorks discussion, submit a brief memo, complete a short writing assignment to check students’ understanding of a case, take on a specific role, prepare to present a critique during in-class discussion).

Andersen, E. and Schiano, B. (2014). Teaching with Cases: A Practical Guide . Harvard Business Press. 

Bonney, K. M. (2015). Case Study Teaching Method Improves Student Performance and Perceptions of Learning Gains†. Journal of Microbiology & Biology Education , 16 (1), 21–28. https://doi.org/10.1128/jmbe.v16i1.846

Davis, B.G. (2009). Chapter 24: Case Studies. In Tools for Teaching. Second Edition. Jossey-Bass. 

Garvin, D.A. (2003). Making the Case: Professional Education for the world of practice. Harvard Magazine. September-October 2003, Volume 106, Number 1, 56-107.

Golich, V.L. (2000). The ABCs of Case Teaching. International Studies Perspectives. 1, 11-29. 

Golich, V.L.; Boyer, M; Franko, P.; and Lamy, S. (2000). The ABCs of Case Teaching. Pew Case Studies in International Affairs. Institute for the Study of Diplomacy. 

Heath, J. (2015). Teaching & Writing Cases: A Practical Guide. The Case Center, UK. 

Herreid, C.F. (2011). Case Study Teaching. New Directions for Teaching and Learning. No. 128, Winder 2011, 31 – 40. 

Herreid, C.F. (2007). Start with a Story: The Case Study Method of Teaching College Science . National Science Teachers Association. Available as an ebook through Columbia Libraries. 

Herreid, C.F. (2006). “Clicker” Cases: Introducing Case Study Teaching Into Large Classrooms. Journal of College Science Teaching. Oct 2006, 36(2). https://search.proquest.com/docview/200323718?pq-origsite=gscholar  

Krain, M. (2016). Putting the Learning in Case Learning? The Effects of Case-Based Approaches on Student Knowledge, Attitudes, and Engagement. Journal on Excellence in College Teaching. 27(2), 131-153. 

Lundberg, K.O. (Ed.). (2011). Our Digital Future: Boardrooms and Newsrooms. Knight Case Studies Initiative. 

Popil, I. (2011). Promotion of critical thinking by using case studies as teaching method. Nurse Education Today, 31(2), 204–207. https://doi.org/10.1016/j.nedt.2010.06.002

Schiano, B. and Andersen, E. (2017). Teaching with Cases Online . Harvard Business Publishing. 

Thistlethwaite, JE; Davies, D.; Ekeocha, S.; Kidd, J.M.; MacDougall, C.; Matthews, P.; Purkis, J.; Clay D. (2012). The effectiveness of case-based learning in health professional education: A BEME systematic review . Medical Teacher. 2012; 34(6): e421-44. 

Yadav, A.; Lundeberg, M.; DeSchryver, M.; Dirkin, K.; Schiller, N.A.; Maier, K. and Herreid, C.F. (2007). Teaching Science with Case Studies: A National Survey of Faculty Perceptions of the Benefits and Challenges of Using Cases. Journal of College Science Teaching; Sept/Oct 2007; 37(1). 

Weimer, M. (2013). Learner-Centered Teaching: Five Key Changes to Practice. Second Edition. Jossey-Bass.

Additional resources 

Teaching with Cases , Harvard Kennedy School of Government. 

Features “what is a teaching case?” video that defines a teaching case, and provides documents to help students prepare for case learning, Common case teaching challenges and solutions, tips for teaching with cases. 

Promoting excellence and innovation in case method teaching: Teaching by the Case Method , Christensen Center for Teaching & Learning. Harvard Business School. 

National Center for Case Study Teaching in Science . University of Buffalo. 

A collection of peer-reviewed STEM cases to teach scientific concepts and content, promote process skills and critical thinking. The Center welcomes case submissions. Case classification scheme of case types and teaching methods:

• Different types of cases: analysis case, dilemma/decision case, directed case, interrupted case, clicker case, a flipped case, a laboratory case. 
• Different types of teaching methods: problem-based learning, discussion, debate, intimate debate, public hearing, trial, jigsaw, role-play. 

Columbia Resources

Resources available to support your use of case method: The University hosts a number of case collections including: the Case Consortium (a collection of free cases in the fields of journalism, public policy, public health, and other disciplines that include teaching and learning resources; SIPA’s Picker Case Collection (audiovisual case studies on public sector innovation, filmed around the world and involving SIPA student teams in producing the cases); and Columbia Business School CaseWorks , which develops teaching cases and materials for use in Columbia Business School classrooms.

Center for Teaching and Learning

The Center for Teaching and Learning (CTL) offers a variety of programs and services for instructors at Columbia. The CTL can provide customized support as you plan to use the case method approach through implementation. Schedule a one-on-one consultation. 

Office of the Provost

The Hybrid Learning Course Redesign grant program from the Office of the Provost provides support for faculty who are developing innovative and technology-enhanced pedagogy and learning strategies in the classroom. In addition to funding, faculty awardees receive support from CTL staff as they redesign, deliver, and evaluate their hybrid courses.

The Start Small! Mini-Grant provides support to faculty who are interested in experimenting with one new pedagogical strategy or tool. Faculty awardees receive funds and CTL support for a one-semester period.

Explore our teaching resources.

• Blended Learning
• Contemplative Pedagogy
• Inclusive Teaching Guide
• FAQ for Teaching Assistants
• Metacognition

CTL resources and technology for you.

• Overview of all CTL Resources and Technology
• The origins of this method can be traced to Harvard University where in 1870 the Law School began using cases to teach students how to think like lawyers using real court decisions. This was followed by the Business School in 1920 (Garvin, 2003). These professional schools recognized that lecture mode of instruction was insufficient to teach critical professional skills, and that active learning would better prepare learners for their professional lives. ↩
• Golich, V.L. (2000). The ABCs of Case Teaching. International Studies Perspectives. 1, 11-29. ↩
• Herreid, C.F. (2007). Start with a Story: The Case Study Method of Teaching College Science . National Science Teachers Association. Available as an ebook through Columbia Libraries. ↩
• Davis, B.G. (2009). Chapter 24: Case Studies. In Tools for Teaching. Second Edition. Jossey-Bass. ↩
• Andersen, E. and Schiano, B. (2014). Teaching with Cases: A Practical Guide . Harvard Business Press. ↩
• Lundberg, K.O. (Ed.). (2011). Our Digital Future: Boardrooms and Newsrooms. Knight Case Studies Initiative. ↩
• Heath, J. (2015). Teaching & Writing Cases: A Practical Guide. The Case Center, UK. ↩
• Bonney, K. M. (2015). Case Study Teaching Method Improves Student Performance and Perceptions of Learning Gains†. Journal of Microbiology & Biology Education , 16 (1), 21–28. https://doi.org/10.1128/jmbe.v16i1.846 ↩
• Krain, M. (2016). Putting the Learning in Case Learning? The Effects of Case-Based Approaches on Student Knowledge, Attitudes, and Engagement. Journal on Excellence in College Teaching. 27(2), 131-153. ↩
• Thistlethwaite, JE; Davies, D.; Ekeocha, S.; Kidd, J.M.; MacDougall, C.; Matthews, P.; Purkis, J.; Clay D. (2012). The effectiveness of case-based learning in health professional education: A BEME systematic review . Medical Teacher. 2012; 34(6): e421-44. ↩
• Yadav, A.; Lundeberg, M.; DeSchryver, M.; Dirkin, K.; Schiller, N.A.; Maier, K. and Herreid, C.F. (2007). Teaching Science with Case Studies: A National Survey of Faculty Perceptions of the Benefits and Challenges of Using Cases. Journal of College Science Teaching; Sept/Oct 2007; 37(1). ↩
• Popil, I. (2011). Promotion of critical thinking by using case studies as teaching method. Nurse Education Today, 31(2), 204–207. https://doi.org/10.1016/j.nedt.2010.06.002 ↩
• Weimer, M. (2013). Learner-Centered Teaching: Five Key Changes to Practice. Second Edition. Jossey-Bass. ↩
• Herreid, C.F. (2006). “Clicker” Cases: Introducing Case Study Teaching Into Large Classrooms. Journal of College Science Teaching. Oct 2006, 36(2). https://search.proquest.com/docview/200323718?pq-origsite=gscholar ↩

This website uses cookies to identify users, improve the user experience and requires cookies to work. By continuing to use this website, you consent to Columbia University's use of cookies and similar technologies, in accordance with the Columbia University Website Cookie Notice .

Publications

• Conferences & Events
• Professional Learning
• Science Standards
• Awards & Competitions
• Instructional Materials
• Free Resources
• American Rescue Plan
• For Preservice Teachers
• NCCSTS Case Collection
• Partner Jobs in Education
• Interactive eBooks+
• Digital Catalog
• Regional Product Representatives
• e-Newsletters
• Bestselling Books
• Latest Books
• Popular Book Series
• Prospective Authors
• Web Seminars
• Exhibits & Sponsorship
• Conference Reviewers
• National Conference • Denver 24
• Leaders Institute 2024
• National Conference • New Orleans 24
• Submit a Proposal
• Latest Resources
• Professional Learning Units & Courses
• For Districts
• Online Course Providers
• Schools & Districts
• College Professors & Students
• The Standards
• Teachers and Admin
• eCYBERMISSION
• Toshiba/NSTA ExploraVision
• Junior Science & Humanities Symposium
• Teaching Awards
• Climate Change
• Earth & Space Science
• New Science Teachers
• Early Childhood
• Middle School
• High School
• Postsecondary
• Informal Education
• Journal Articles
• Lesson Plans
• e-newsletters
• Science & Children
• Science Scope
• The Science Teacher
• Journal of College Sci. Teaching
• Connected Science Learning
• NSTA Reports
• Next-Gen Navigator
• Science Update
• Teacher Tip Tuesday
• Trans. Sci. Learning

MyNSTA Community

• My Collections

NCCSTS Case Collection • Teaching Resources

The publications listed below have been produced by the National Center for Case Study Teaching in Science.

Start with a Story: The Case Study Method of Teaching College Science , edited by Clyde Freeman Herreid, originally published in 2006 by NSTA Press; reprinted by the National Center for Case Study Teaching in Science (NCCSTS) in 2013. Collection of 40+ essays examining every aspect of the case study method and its use in the science classroom. The book is available for purchase through NSTA .

Science Stories You Can Count On: 51 Case Studies with Quantitative Reasoning in Biology , edited by Clyde Freeman Herreid, Nancy A. Schiller, and Ky F. Herreid, NSTA Press, 2014. Includes case studies as well as tips and techniques for promoting quantitative reasoning in biology. The book is available for purchase through NSTA or from Amazon .

Science Stories: Using Case Studies to Teach Critical Thinking , edited by Clyde Freeman Herreid, Nancy A. Schiller, and Ky F. Herreid, NSTA Press, 2012. A compilation of case studies with questions and teaching notes that can be used to help develop STEM students’ critical thinking skills. The book is available for purchase through NSTA or from Amazon .

The NCCSTS has produced two training videos with supporting brochures on the case method and its use in science education.

Use of Case Studies and Group Discussion in Science Education This hands-on video shows the classical method of running a case study class used by Harvard law and business school professors for almost 100 years—the art of using successful group discussion. In 26 minutes you will learn how to ensure that your large group discussion is not a free-for-all or an exercise in futility as you try to get students to say something intelligent. Preparation and control are the key ingredients. For preparation students must read a case study ahead of time. But it is more than that. In this video, which focuses on a case study involving genetically modified food, you will see how an actual class is given a “warm-up” by breaking into small groups to discuss the reading they’ve done ahead of time. Then you will see how a large group discussion is successfully controlled. It’s the important, yet subtle, use of appropriate questions, body language, blackboard planning, and summarization that makes it all work. Video on YouTube | Access the video booklet (PDF)

Team Learning: Cooperative Learning in the Science Classroom Having students work in small groups is arguably the best way to teach science and this includes teaching science using cases. But how can we run a classroom this way? Here is one answer using a method called Team Learning. This 26-minute video shows you how to establish groups, how to set up a grading system that encourages group participation, how to answer students’ questions and, most importantly, why this is a superior method of teaching. Video on YouTube | Access the video booklet (PDF)

Bibliographies

• Bibliography on Case Study Teaching in Science compiled by Nancy A. Schiller and Clyde Freeman Herreid.

Selected Articles by Clyde F. Herreid and other members of the NCCSTS

Getting started.

• Case Studies in Science: A Novel Method of Science Education
• What is a Case? Bringing to Science Education the Established Teaching Tool of Law and Medicine
• My Favorite Case and What Makes It So
• What Makes a Good Case? Some Basic Rules of Good Storytelling Help Teachers Generate Student Excitement in the Classroom
• Sorting Potatoes for Miss Bonner: Bringing Order to Case Study Methodology Through a Classification Scheme
• Can Case Studies Be Used to Teach Critical Thinking?
• A Peek Behind the Curtain of Tenure and Promotion

Writing Cases

• Cooking With Betty Crocker: A Recipe for Case Writing
• The Way of Flesch: The Art of Writing Readable Cases
• Twixt Fact and Fiction: A Case Writer’s Dilemma
• Let’s Get Personal: Putting Personality into your Cases
• Puttin’ on the Ritz: How to Put Science into Cases
• Putting Words in Their Mouth: Writing Dialogue for Case Studies
• And All That Jazz: An Essay Extolling the Virtues of Writing Case Teaching Notes
• Exercises in Style: Is There a Best Way to Write a Case Study?
• The Chef Returns: A Recipe for Writing Great Case Studies
• Creating a Video Case Study

Teaching with Cases

• Don't! What Not to Do When Teaching Cases
• Return to Mars: How Not to Teach a Case Study
• Assembling a Case Study Tool Kit: 10 Tools for Teaching With Cases
• The Interrupted Case Method
• Case Studies and the Flipped Classroom
• A Chat with the Survey Monkey: Case Studies and the Flipped Classroom
• Intimate Debate Technique
• "Clicker" Cases: Introducing Case Study Teaching into Large Classrooms
• Structured Controversy: A Case Study Strategy
• Trigger Cases Versus Capstone Cases
• The Boy Scouts Said Its Best: Some Advice on Case Study Teaching and Student Prepara-tion
• Naming Names
• Science, Pseudoscience, and Nonsense

Cases and Cooperative Learning

• The Bee and the Groundhog: Lessons in Cooperative Learning
• I Never Knew Joe Paterno: An Essay on Teamwork and Love
• The Wisdom of Groups

Grading Case Work

• When Justice Peeks: Evaluating Students in Case Study Teaching

Start with a Story: The Case Study Method of Teaching College Science

Edited by Clyde Freeman Herreid

Originally published in 2006 by NSTA Press; reprinted by the National Center for Case Study Teaching in Science (NCCSTS) in 2013. Collection of 40+ essays examining every aspect of the case study method and its use in the science classroom. The book is available for purchase through NSTA .

Science Stories You Can Count On: 51 Case Studies with Quantitative Reasoning in Biology

Edited by Clyde Freeman Herreid, Nancy A. Schiller, and Ky F. Herreid, NSTA Press, 2014.

Includes case studies as well as tips and techniques for promoting quantitative reasoning in biology. The book is available for purchase through NSTA or from Amazon .

Science Stories: Using Case Studies to Teach Critical Thinking

Edited by Clyde Freeman Herreid, Nancy A. Schiller, and Ky F. Herreid, NSTA Press, 2012.

A compilation of case studies with questions and teaching notes that can be used to help develop STEM students’ critical thinking skills. The book is available for purchase through NSTA or from Amazon .

Use of Case Studies and Group Discussion in Science Education

This hands-on video shows the classical method of running a case study class used by Harvard law and business school professors for almost 100 years—the art of using successful group discussion. In 26 minutes you will learn how to ensure that your large group discussion is not a free-for-all or an exercise in futility as you try to get students to say something intelligent. Preparation and control are the key ingredients. For preparation students must read a case study ahead of time. But it is more than that. In this video, which focuses on a case study involving genetically modified food, you will see how an actual class is given a “warm-up” by breaking into small groups to discuss the reading they’ve done ahead of time. Then you will see how a large group discussion is successfully controlled. It’s the important, yet subtle, use of appropriate questions, body language, blackboard planning, and summarization that makes it all work.

Video on YouTube | Access the video booklet (PDF)

Team Learning: Cooperative Learning in the Science Classroom

Having students work in small groups is arguably the best way to teach science and this includes teaching science using cases. But how can we run a classroom this way? Here is one answer using a method called Team Learning. This 26-minute video shows you how to establish groups, how to set up a grading system that encourages group participation, how to answer students’ questions and, most importantly, why this is a superior method of teaching.

The articles listed below are selected by Clyde F. Herreid and other members of the NCCSTS.

• 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

What the Case Study Method Really Teaches

• Nitin Nohria

Seven meta-skills that stick even if the cases fade from memory.

It’s been 100 years since Harvard Business School began using the case study method. Beyond teaching specific subject matter, the case study method excels in instilling meta-skills in students. This article explains the importance of seven such skills: preparation, discernment, bias recognition, judgement, collaboration, curiosity, and self-confidence.

During my decade as dean of Harvard Business School, I spent hundreds of hours talking with our alumni. To enliven these conversations, I relied on a favorite question: “What was the most important thing you learned from your time in our MBA program?”

• Nitin Nohria is the George F. Baker Professor of Business Administration, Distinguished University Service Professor, and former dean of Harvard Business School.

Partner Center

22 Cases and Articles to Help Bring Diversity Issues into Class Discussions

Explore more.

• Course Materials
• Diversity, Equity, and Inclusion

T he recent civic unrest in the United States following the death of George Floyd has elevated the urgency to recognize and study issues of diversity and the needs of underrepresented groups in all aspects of public life.

Business schools—and educational institutions across the spectrum—are no exception. It’s vital that educators facilitate safe and productive dialogue with students about issues of inclusion and diversity. To help, we’ve gathered a collection of case studies (all with teaching notes) and articles that can encourage and support these critical discussions.

These materials are listed across three broad topic areas: leadership and inclusion, cases featuring protagonists from historically underrepresented groups, and women and leadership around the world. This list is hardly exhaustive, but we hope it provides ways to think creatively and constructively about how educators can integrate these important topics in their classes. HBP will continue to curate and share content that addresses these equity issues and that features diverse protagonists.

Editors’ note: To access the full text of these articles, cases, and accompanying teaching notes, you must be registered with HBP Education. We invite you to sign up for a free educator account here . Verification may take a day; in the meantime, you can read all of our Inspiring Minds content .

Leadership and Inclusion

John Rogers, Jr.—Ariel Investments Co.

—by Steven S. Rogers and Greg White

Gender and Free Speech at Google (A)

—by Nien-hê Hsieh, Martha J. Crawford, and Sarah Mehta

The Massport Model: Integrating Diversity and Inclusion into Public-Private Partnerships

—by Laura Winig and Robert Livingston

“Numbers Take Us Only So Far”

—by Maxine Williams

For Women and Minorities to Get Ahead, Managers Must Assign Work Fairly

—by Joan C. Williams and Marina Multhaup

How Organizations Are Failing Black Workers—and How to Do Better

—by Adia Harvey Wingfield

To Retain Employees, Focus on Inclusion—Not Just Diversity

—by Karen Brown

From HBR 's The Big Idea:

Toward a Racially Just Workplace: Diversity efforts are failing black employees. Here’s a better approach.

—by Laura Morgan Roberts and Anthony J. Mayo

Cases with Protagonists from Historically Underrepresented Groups

Arlan Hamilton and Backstage Capital

—by Laura Huang and Sarah Mehta

United Housing—Otis Gates

—by Steven Rogers and Mercer Cook

Eve Hall: The African American Investment Fund in Milwaukee

—by Steven Rogers and Alterrell Mills

Dylan Pierce at Peninsula Industries

—by Karthik Ramanna

Maggie Lena Walker and the Independent Order of St. Luke

—by Anthony J. Mayo and Shandi O. Smith

Multimedia Cases:

Enterprise Risk Management at Hydro One, Multimedia Case

—by Anette Mikes

Women and Leadership Around the World

Monique Leroux: Leading Change at Desjardins

—by Rosabeth Moss Kanter and Ai-Ling Jamila Malone

Kaweyan: Female Entrepreneurship and the Past and Future of Afghanistan

—by Geoffrey G. Jones and Gayle Tzemach Lemmon

Womenomics in Japan

—by Boris Groysberg, Mayuka Yamazaki, Nobuo Sato, and David Lane

Women MBAs at Harvard Business School: 1962-2012

—by Boris Groysberg, Kerry Herman, and Annelena Lobb

Beating the Odds

—by Laura Morgan Roberts, Anthony J. Mayo, Robin J. Ely, and David A. Thomas

Rethink What You “Know” About High-Achieving Women

—by Robin J. Ely, Pamela Stone, and Colleen Ammerman

“I Try to Spark New Ideas”

—by Christine Lagarde and Adi Ignatius

How Women Manage the Gendered Norms of Leadership

—by Wei Zheng, Ronit Kark, and Alyson Meister

Is this list helpful to you? What other topics or materials would you like to see featured in our next curated list? Let us know .

Related Articles

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 .

Case Study Disciplines

We have created a substantial collection of unique and practical case studies that allow professors to educate at a fraction of the cost. All of the Value, with No more reoccurring Licenses.

Accounting ( 13 )

General Management ( 55 )

Finance ( 18 )

Information Systems ( 23 )

Operations Management ( 16 )

Communications ( 7 )

Marketing ( 26 )

International Business ( 19 )

Leadership ( 26 )

Economics & Public Policy ( 6 )

Human Resource MGMT ( 35 )

Strategy ( 63 )

Organizational Behaviour ( 34 )

Entrepreneurship ( 12 )

Legal ( 2 )

Ethics ( 37 )

Sustainability ( 9 )

“Complete Assessments ready for your Classroom. Simply Download and Use.”

Pre-order now.

Prompt-ology

Demystifying  the art of ai prompting.

Practical Research and Hands On Guide

Prompt Engineering matters to you because…. . when you are using AI to do any task from content creation to analysis or idea generation, the quality and relevance of the output you get is directly correlated to the quality, specificity, context and removal of ambiguity in your prompt.

In Layman’s terms… without Prompting, there is NO POINT to use AI.

Prompting is EVERYTHING!!

What’s included?

Pre-order benefits – $55 value for only 19.99 Pre-order

• Secure a Copy of Prompt-ology
• Bonus copy of ChatGPT for Educators – $15 value for free
• Bonus copy of Case-spiration E1 – $20 value for free

Let’s Turn Ideas Into Authentic Assessments

Never Before have educators be able to create their very own Case Study or Collection of Case Studies for their course. We offer an exceptional service where we talk through the creation of your very own Cases. These Cases are your own! When we are done and there are no more Fees.

Pin It on Pinterest

• 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

511 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]