CoChat

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

Open access
Cook, David A, Overgaard, Joshua, Pankratz, V Shane, Del Fiol, Guilherme, Aakre, Chris A · 2025 · Journal of Medical Internet Research

Published version of a preprint

The DOI matches its Crossref record; 66 of the 66 references it cites were found in a registry or an index.

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. Methods: We conducted an intrinsic evaluation study rating 60 VP-clinician conversations. We used carefully engineered prompts to direct OpenAI’s generative pretrained transformer (GPT) to emulate a patient and provide feedback. Using 2 outpatient medicine topics (chronic cough diagnosis and diabetes management), each with permutations representing different patient preferences, we created 60 conversations (dialogues plus feedback): 48 with a human clinician and 12 “self-chat” dialogues with GPT role-playing both the VP and clinician. Primary outcomes were dialogue authenticity and feedback quality, rated using novel instruments for which we conducted a validation study collecting evidence of content, internal structure (reproducibility), relations with other variables, and response process. Each conversation was rated by 3 physicians and by GPT. Secondary outcomes included user experience, bias, patient preferences represented in the dialogues, and conversation features that influenced authenticity. Results: The average cost per conversation was US $0.51 for GPT-4.0-Turbo and US $0.02 for GPT-3.5-Turbo. Mean (SD) conversation ratings, maximum 6, were overall dialogue authenticity 4.7 (0.7), overall user experience 4.9 (0.7), and average feedback quality 4.7 (0.6). For dialogues created using GPT-4.0-Turbo, physician ratings of patient preferences aligned with intended preferences in 20 to 47 of 48 dialogues (42%-98%). Subgroup comparisons revealed higher ratings for dialogues using GPT-4.0-Turbo versus GPT-3.5-Turbo and for human-generated versus self-chat dialogues. Feedback ratings were similar for human-generated versus GPT-generated ratings, whereas authenticity ratings were lower. We did not perceive bias in any conversation. Dialogue features that detracted from authenticity included that GPT was verbose or used atypical vocabulary (93/180, 51.7% of conversations), was overly agreeable (n=56, 31%), repeated the question as part of the response (n=47, 26%), was easily convinced by clinician suggestions (n=35, 19%), or was not disaffected by poor clinician performance (n=32, 18%). For feedback, detractors included excessively positive feedback (n=42, 23%), failure to mention important weaknesses or strengths (n=41, 23%), or factual inaccuracies (n=39, 22%). Regarding validation of dialogue and feedback scores, items were meticulously developed (content evidence), and we confirmed expected relations with other variables (higher ratings for advanced LLMs and human-generated dialogues). Reproducibility was suboptimal, due largely to variation in LLM performance rather than rater idiosyncrasies. Conclusions: LLM-powered VPs can simulate patient-clinician dialogues, demonstrably represent patient preferences, and provide personalized performance feedback. This approach is scalable, globally accessible, and inexpensive. LLM-generated ratings of feedback quality are similar to human ratings.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.2196/68486

Cites

66 of 66 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Overview of the study design. GPT=GPT−4.0-turbo except as otherwise noted. A “conversation” refers to the virtual patient–clinician dialogue plus feedback. API: application programming interface; GPT: generative pretrained transformer.
Figure 1 Overview of the study design. GPT=GPT−4.0-turbo except as otherwise noted. A “conversation” refers to the virtual patient–clinician dialogue plus feedback. API: application programming interface; GPT: generative pretrained transformer.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 66 references

Research works printed but not linked: 3

  1. Tong, Y, 2014, The standards for educational and psychological testing, 11
  2. Roller, S, arXiv, 2006.12442 · arXiv
  3. Adiwardana, D, arXiv

Cited by

See all 96

Metadata

Authors
Cook, D. A., Overgaard, J., Pankratz, V. S., Del Fiol, G., & Aakre, C. A.
Affiliations
  • Mayo Clinic (US)
  • University of New Mexico (US)
Corresponding author
Cook, David A
Venue
Journal of Medical Internet Research
Published
2025-04-04
Volume
27
Pages
e68486
ISSN
1438-8871 (ISSN-L)
OpenAlex
W4406327404
Cited by
96
References
65
Citations by year
2026: 72 · 2025: 24
FWCI
23.11
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Journal of Medical Internet Research (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Edinburgh Napier University
  • Gentofte Hospital
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Social Sciences › Education › Simulation-Based Education in Healthcare
  • Social Sciences › Education › Innovations in Medical Education
Keywords
virtual patients, large language models, GPT, personalized feedback, patient preferences, GPT-3.5-turbo, diabetes management, simulation scalability, user experience, prompt engineering
MeSH terms
Large Language Models, Communication, Diabetes Mellitus, Feedback, Humans, Language, Physician-Patient Relations, User-Computer Interface, Patient Simulation, Patient Preference

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.