Abstract Details

Title Double Agent AI: GPT as Virtual Patient and Tutor in Resident ��ɫ��

Topic ��ɫ��, Research, and Methodology

Presentation(s) P8 - Poster Session 8 (8:00 AM-9:00 AM)

Poster/Presentation
Number 5-012

Objective Develop a custom GPT that simulates virtual patient encounters, enhancing residents' clinical reasoning within a self-regulated learning framework.

Background Virtual patient simulations are effective for GME learners to build clinical reasoning skills within a self-regulated learning framework. Simulations facilitate practice in history taking, neurological examination (via video), and clinical formulation. ChatGPT simulates natural language encounters, allowing asynchronous learning across digital devices. Moreover, developing an instruction template for building GPT simulation tools, adaptable to multiple topics, allows transferability to other learning contexts.

Design/Methods We instructed a custom GPT to play roles as a virtual patient with tremor and an observing tutor. Prompts were developed through iterative optimization with ChatGPT itself. The GPT's knowledge base comprised published review articles. The initial GPT was shared with 5 trainees, 3 movement disorder faculty, and 2 medical education faculty for testing. Feedback was collected and informed refinements. (ChatGPT was involved in editing portions of this abstract).

Results The GPT simulated 5 unique tremor cases. Interactions between learners and the GPT used natural language though GPT responses were deemed slightly unnatural by testers. Refinements prevented virtual patients from summarizing entire histories without targeted questioning. Experts found the interaction consistent with the diagnoses simulated. The tool facilitated clinical reasoning through tutor-facilitated prompting, feedback, and instruction. The GPT hyperlinked videos of examinations enhancing simulation fidelity. Technical limitations from detailed GPT prompting included a high computational burden, limiting session time for users.

Conclusions ChatGPT shows high potential for simulating patient encounters to help learners develop clinical skills asynchronously within a self-regulated learning framework. We provide a methodology for development and refinement of an educational ChatGPT. Adopters of this technology must optimize GPT prompts for effectiveness and efficiency to improve user experience and maximize session utility. While validation with learners is pending, this blueprint can guide GPT development across different educational goals.

Authors/Disclosures
Jeffrey B. Ratliff, MD, FAAN (Thomas Jefferson University) PRESENTER	Dr. Ratliff has received personal compensation in the range of $500-$4,999 for serving as an Editor, Associate Editor, or Editorial Advisory Board Member for the journal Neurology. The institution of Dr. Ratliff has received research support from Scion NeuroStim, LLC.
Jason H. Margolesky, MD, FAAN (University of Miami School of Medicine)	Dr. Margolesky has nothing to disclose.
Nicole M. Calautti, MD (Thomas Jefferson University Hospital)	Dr. Calautti has nothing to disclose.
Regina Kurapova, MD (Thomas Jefferson University Hospital)	Ms. Kurapova has nothing to disclose.
Helen Hernandez Lage, MD	Mrs. Hernandez Lage has nothing to disclose.
Patricia Jokl Graese, MD	Dr. Graese has nothing to disclose.
Sara M. Schaefer, MD, FAAN	Dr. Schaefer has received personal compensation in the range of $500-$4,999 for serving as an Editor, Associate Editor, or Editorial Advisory Board Member for Movement Disorders Journal. The institution of Dr. Schaefer has received research support from American Parkinson Disease Association. Dr. Schaefer has received personal compensation in the range of $500-$4,999 for serving as a RITE Section Lead with ��ɫ��. Dr. Schaefer has received personal compensation in the range of $500-$4,999 for serving as a QOD Question Writer with ��ɫ��.
William A. Dalrymple, MD (University of Virginia Health System)	Dr. Dalrymple has received personal compensation in the range of $500-$4,999 for serving as a Consultant for REACH. Dr. Dalrymple has received personal compensation in the range of $0-$499 for serving as a Consultant for M3. Dr. Dalrymple has received personal compensation in the range of $0-$499 for serving as a Consultant for Boxer Capital. Dr. Dalrymple has received personal compensation in the range of $0-$499 for serving as a Consultant for Capvision. Dr. Dalrymple has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Atheneum. Dr. Dalrymple has received personal compensation in the range of $0-$499 for serving as a Consultant for Cencora. Dr. Dalrymple has received personal compensation in the range of $0-$499 for serving as a Consultant for Lumanity. Dr. Dalrymple has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for Huntington Study Group. Dr. Dalrymple has received personal compensation in the range of $500-$4,999 for serving as an officer or member of the Board of Directors for Huntington Study Group. The institution of Dr. Dalrymple has received research support from Huntington's Disease Society of America.
Courtney Seebadri-White, MD (Thomas Jefferson University Hospital)	Dr. Seebadri-White has nothing to disclose.
Andres Fernandez, MD (Thomas Jefferson University Hospital)	Dr. Fernandez has nothing to disclose.

��ɫ����

��ɫ����

��ɫ��

��ɫ��