Virtual Patients Using Large Language Models: Scalable, Contextualized Simulation of Clinician-Patient Dialogue With Feedback

Cook, David A.; Overgaard, Joshua; Pankratz, V. Shane; Fiol, Guilherme Del; Aakre, Christopher A.

doi:10.2196/68486

articleJournal of Medical Internet ResearchJan 13, 2025GOLD OA

Virtual Patients Using Large Language Models: Scalable, Contextualized Simulation of Clinician-Patient Dialogue With Feedback

DADavid A. Cook JOJoshua Overgaard VSV. Shane Pankratz GDGuilherme Del Fiol CAChristopher A. Aakre

Mayo Clinic · Mayo Clinic in Arizona · +3 more institutions

PubMed

Indexed incrossrefdoajpubmed

Abstract

Background

Virtual patients (VPs) are computer screen-based simulations of patient-clinician encounters. VP use is limited by cost and low scalability.

Objective

We aimed to show that VPs powered by large language models (LLMs) can generate authentic dialogues, accurately represent patient preferences, and provide personalized feedback on clinical performance. We also explored using LLMs to rate the quality of dialogues and feedback.

Citation impact

57

total citations

FWCI: 53.27
Percentile: 100%
References: 66

Citations per year

Authors

5

Topics & keywords

Topics

Keywords

Preprint
Dialog box
Computer science
Scalability
Human–computer interaction
World Wide Web
Language model
Multimedia

No related works found for this paper.