A professor at the Geisel School of Medicine at Dartmouth has an interesting use for large language models: Using them to role-play patients for medical students. (Full story from the school is here)
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.
The 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.
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.
Return to the Concord Monitor