Geisel Professor Harnesses AI to Act Like a Patient

News subtitle

Medical students can hone diagnostic skills using an app created by a Dartmouth team.

Image
Image
Geisel student and professor using app.
Nsomma Alilonu, MED ’26, and Geisel professor Thomas Thesen test the interactive voice component on the AI Patient Actor app. (Photo by Katie Lenhart)
Body

A new application developed at Dartmouth and geared to medical students is tapping the power of artificial intelligence to role-play as a patient.

And it is using tools from ChatGPT, the chatbot from OpenAI, to make it possible.

Created by a team led by Thomas Thesen, associate professor of medical education at Geisel School of Medicine and director of the Neuroscience-Informed Learning and Education Lab, the AI Patient Actor app helps second-year medical school students practice interacting with patients and sharpens their diagnostic and interpersonal skills.

Medical schools often employ people who act as patients based on a script that includes a medical history and the symptoms they are experiencing, Thesen says. Medical students are given the opportunity to interact with the actors, learning how to do everything from establishing a bedside rapport to developing a final diagnosis by quizzing the patient actors about symptoms.

But hiring and training to act as patients is resource-intensive, limiting the frequency with which the mock interviews are available as learning experiences to budding medical professionals.

When ChatGPT began to make waves for its ability to mimic human conversations, Thesen hit upon the idea of creating virtual patients. His first text-based prototype for the app drew from medical case histories prewritten by Thesen and was powered by ChatGPT’s language model to answer students’ questions with a conversational ease.

The app can be thought of as a customized version of ChatGPT, says Thesen, allowing educators to create a database of tailor-made cases that would be most instructive for students learning the ropes of clinical history-taking and diagnosis.

To develop the app further and make it deployable on the web, Thesen teamed up with Simon Stone, a research data science specialist at Dartmouth Library. “Simon had the skills to make the app really user-friendly and take it to the next level. Without that, it would have probably stayed on my laptop,” says Thesen.

Thesen debuted AI Patient Actor in his ongoing Neuroscience and Neurology course that medical students take in their second year. Students have the option to practice diagnosing two or three cases every week that are related to the diseases they learn about in class.

The clinical information behind the app is richly detailed. Not only does it enumerate routine vital signs and relevant symptoms, but the app also reports back lab results for tests that a doctor would likely need to differentiate between diseases that are symptomatically similar.

In Thesen’s course, for example, students were learning to diagnose neurological conditions. After asking a set of preliminary questions, the student could say, “I’m ordering an MRI.” The app would then present the test results and the student could be more certain based on the MRI images that the patient was showing signs of Alzheimer’s and not Parkinson’s disease.

Students receive individualized feedback on their interaction with the patient based on an evaluation rubric built into the app. They can use the feedback to have another go at the interview, improving their clinical and diagnostic skills with each turn.

Modeling a clinical interaction with a virtual patient is an easy first step before graduating to actual clinical settings or even mock interviews with actors, says Nsomma Alilonu, a second-year Geisel student who worked with Thesen on the experimental design for evaluating AI Patient Actor, creating a feedback rubric and providing a student’s perspective on the app’s functionality.

“It’s a very good way to practice interviewing patients in a stress-free environment and get formative feedback,” she says.

Alilonu majored in computer science as an undergraduate and was thrilled to explore new ways of integrating medicine and technology through this project. “Even if just one patient can benefit from having a doctor who has refined their skills by practicing with our app, it’s really worth it,” she says.

“While our initial experiences with the AI Patient Actor app have been exceptional, we are undertaking a rigorous scientific experiment to validate its performance,” Thesen says. This validation study looks at the accuracy of the patient simulation and the generated feedback and assesses the implicit bias in the large language model’s responses that may occur as a result of biases in the training data.

Since its debut, the team has added several features to the app. Besides English, AI Patient Actor is now available in Spanish and Swahili and can be expanded to other languages as well. They started with these languages, Thesen says, because Geisel offers students a Spanish Medical Pathway as part of its curriculum and the team has begun a partnership to train medical students at Aga Khan University Medical College in Kenya.

Users now have the option to speak to their virtual patients. The latest update allows users to choose between text or voice as input or output, enabling students to have a verbal conversation with their virtual patient.

Eventually, the team hopes to scale the AI Patient Actor app and make it available to medical educators outside the Dartmouth community.

“In higher education there is a prevailing fear that AI will take the human side out of learning,” says Thesen. “The beauty of this way of using AI is that it actually helps students to become better communicators and ultimately connect better with their patients.”

Harini Barath