CoChat

Development of a GPT-4-powered virtual simulated patient and communication training platform for medical students to practice discussing abnormal mammogram results with patients: Multiphase study

Open access

Published version of a preprint

The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.

Abstract

Background: Standardized patients (SPs) prepare medical students for difficult conversations with patients. Despite their value, SP-based simulation training is constrained by available resources and competing clinical demands. Researchers are turning to artificial intelligence and large language models, such as generative pretrained transformers, to create communication training that incorporates virtual simulated patients (VSPs). GPT-4 is a large language model advance allowing developers to design virtual simulation scenarios using text-based prompts instead of relying on branching path simulations with prescripted dialogue. These nascent developmental practices have not taken root in the literature to guide other researchers in developing their own simulations. Objective: This study aims to describe our developmental process and lessons learned for creating a GPT-4–driven VSP. We designed the VSP to help medical student learners rehearse discussing abnormal mammography results with a patient as a primary care physician (PCP). We aimed to assess GPT-4’s ability to generate appropriate VSP responses to learners during spoken conversations and provide appropriate feedback on learner performance. Methods: A research team comprised of physicians, a medical student, an educator, an SP program director, a learning experience designer, and a health care researcher conducted the study. A formative phase with in-depth knowledge user interviews informed development, followed by a development phase to create the virtual training module. The team conducted interviews with 5 medical students, 5 PCPs, and 5 breast cancer survivors. They then developed a VSP using simulation authoring software and provided the GPT-4–enabled VSP with an initial prompt consisting of a scenario description, emotional state, and expectations for learner dialogue. It was iteratively refined through an agile design process involving repeated cycles of testing, documenting issues, and revising the prompt. As an exploratory feature, the simulation used GPT-4 to provide written feedback to learners about their performance communicating with the VSP and their adherence to guidelines for difficult conversations. Results: In-depth interviews helped establish the appropriate timing, mode of communication, and protocol for conversations between PCPs and patients during the breast cancer screening process. The scenario simulated a telephone call between a physician and patient to discuss the abnormal results of a diagnostic mammogram that that indicated a need for a biopsy. Preliminary testing was promising. The VSP asked sensible questions about their mammography results and responded to learner inquiries using a voice replete with appropriate emotional inflections. GPT-4 generated performance feedback that successfully identified strengths and areas for improvement using relevant quotes from the learner-VSP conversation, but it occasionally misidentified learner adherence to communication protocols. Conclusions: GPT-4 streamlined development and facilitated more dynamic, humanlike interactions between learners and the VSP compared to branching path simulations. For the next steps, we will pilot-test the VSP with medical students to evaluate its feasibility and acceptability.

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 · 10.2196/65670

Cites

41 of 41 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 First stage of the schematic of the original scenario flow design for a branching path simulation that consists of 6 distinct stages (1 for each step of the Setting, Perception, Invitation, Knowledge, Emotion, and Summarize [SPIKES] protocol), 12 critical decision points, 68 scripted user response options (consisting of ideal, acceptable, and unacceptable examples), and 65 scripted patient responses. Simulation flow was designed from November 2023 to December 2023 to help medical students practice discussing abnormal mammogram results with their patients. We originally planned to use a “voice intent recognition” system to branch to the appropriate patient responses and to score users based on how closely their responses match the ideal options.
Figure 1 First stage of the schematic of the original scenario flow design for a branching path simulation that consists of 6 distinct stages (1 for each step of the Setting, Perception, Invitation, Knowledge, Emotion, and Summarize [SPIKES] protocol), 12 critical decision points, 68 scripted user response options (consisting of ideal, acceptable, and unacceptable examples), and 65 scripted patient responses. Simulation flow was designed from November 2023 to December 2023 to help medical students practice discussing abnormal mammogram results with their patients. We originally planned to use a “voice intent recognition” system to branch to the appropriate patient responses and to score users based on how closely their responses match the ideal options.CC BY · PubMed Central
Figure 2 Hyperskill (SimInsights) authoring interface, which shows the final scenario flow from March 2024 for our artificial intelligence (AI)–driven virtual simulated patient to help medical students practice discussing abnormal mammogram results with their patients. The final scenario flow consists of only 2 states (setup and feedback). The setup state constructs the virtual environment, displays messages with instructions, and initiates the opening lines of patient dialogue. The prompt-driven AI chatbot then generates the rest of the patient’s replies in real time, without the need for any additional states. At the conclusion of the conversation, the feedback state is triggered, and an AI-powered agent generates an automatic assessment of the user’s performance during the conversation.
Figure 2 Hyperskill (SimInsights) authoring interface, which shows the final scenario flow from March 2024 for our artificial intelligence (AI)–driven virtual simulated patient to help medical students practice discussing abnormal mammogram results with their patients. The final scenario flow consists of only 2 states (setup and feedback). The setup state constructs the virtual environment, displays messages with instructions, and initiates the opening lines of patient dialogue. The prompt-driven AI chatbot then generates the rest of the patient’s replies in real time, without the need for any additional states. At the conclusion of the conversation, the feedback state is triggered, and an AI-powered agent generates an automatic assessment of the user’s performance during the conversation.CC BY · PubMed Central
Figure 3 Screenshot of the virtual environment for our simulated phone call with Olivia Patterson, a virtual simulated patient designed to help medical students practice discussing abnormal mammogram results with their patients. The scene consists of a virtual cell phone object with a clickable “End” button, a static background image depicting a doctor’s office desk, and a timer. Date: August 2024.
Figure 3 Screenshot of the virtual environment for our simulated phone call with Olivia Patterson, a virtual simulated patient designed to help medical students practice discussing abnormal mammogram results with their patients. The scene consists of a virtual cell phone object with a clickable “End” button, a static background image depicting a doctor’s office desk, and a timer. Date: August 2024.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 41 references

Research works printed but not linked: 7

  1. Ha, JF, 2010, Ochsner J, 10, 38
  2. Nelson, G, 2022, S D Med, 75, 454
  3. Li, Y, arXiv. Preprint posted online on April 13, 2024
  4. Bojic, L, arXiv. Preprint posted online on December 15, 2023
  5. Nori, H, arXiv. Preprint posted online on March 20, 2023
  6. Ruan, J, arXiv. Preprint posted online on August 7, 2023
  7. Rabow, MW, 1999, West J Med, 171, 260

Cited by

See all 42

Metadata

Authors
Weisman, D., Sugarman, A., Huang, Y. M., Gelberg, L., Ganz, P. A., & Comulada, W. S.
Affiliations
University of California, Los Angeles (US)
Corresponding author
Comulada, Warren Scott
Venue
JMIR Formative Research
Published
2025-04-17
Volume
9
Pages
e65670
ISSN
2561-326X (ISSN-L)
OpenAlex
W4407545831
Cited by
37
References
37
Citations by year
2026: 28 · 2025: 9
FWCI
23.81
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • JMIR Formative Research (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • eScholarship (California Digital Library) (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Breast Cancer Research Foundation
  • University of California, Los Angeles
  • National Cancer Institute (P30CA016042)
  • Jonsson Comprehensive Cancer Center
Topics
  • Social Sciences › Education › Simulation-Based Education in Healthcare
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Social Sciences › Education › Innovations in Medical Education
Keywords
GPT-4, large language models, medical communication training, difficult conversations, breast cancer screening, prompt engineering, telephone consultation, medical students, breast cancer survivors, artificial intelligence in medical education, shared decision-making, informed consent, informed refusal
MeSH terms
Breast Neoplasms, Communication, Female, Humans, Male, Mammography, Physician-Patient Relations, Students, Medical, Patient Simulation

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Development of a GPT-4-powered virtual simulated patient and communication training platform for medical students to practice discussing abnormal mammogram results with patients: Multiphase study. https://app.cochat.ai/papers/10.2196/65670
The paper
Weisman, D., Sugarman, A., Huang, Y. M., Gelberg, L., Ganz, P. A., & Comulada, W. S. (2025). Development of a GPT-4-powered virtual simulated patient and communication training platform for medical students to practice discussing abnormal mammogram results with patients: Multiphase study. JMIR Formative Research. https://doi.org/10.2196/65670

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.