LLM-configured simulated patient as a scalable, standardized practice environment for history taking

Design · All designs
Evidence · 2 claims (2 for) · 1 study (1 causal), q3 · 1 of 1 report an effect size · 2 claims rest on one study

Description

The article configures a large language model (ChatGPT-5.2, temperature 0.7, top-p 0.9, not fine-tuned) with preloaded gynecological case scripts to "behave as a real patient using predefined gynecological cases". Behavioral constraints restrict it from giving medical advice, require lay language, and withhold diagnostic clues unless elicited. Students interview it via text in 15–30 minute self-paced sessions without faculty supervision, positioning it as a scalable, 24/7-accessible adjunct to standardized patients.

Design Implications

Context

Requirements

• Preloaded standardized case scripts with chief complaint, history of present illness, past medical history, personal history, and family history
• Structured prompt controls and predefined technical parameters for reproducibility

Constraints

• Knowledge cutoff constraints and absence of non-verbal clinical cues
• AI output was not monitored in real time during student encounters

Target Learners

• fourth-year medical students in a gynecology clerkship

Learning Goals

• gynecological history-taking skills
• systematic clinical information gathering

Claims

• Ai Simulated Patient Checklist Completion Gynecology [+M]
• Ai Simulated Patient Osce Scores Gynecology [+M]

Related Designs

Examples

-

Key Sources

• Gao Lingling, Zhang Li, Zhang Yanxin, Wu Min, Xu Jianbo, Lu Dan. (2026). Utilizing generative artificial intelligence to create simulated patient for history taking in gynecology. BMC Medical Education. https://doi.org/10.1186/s12909-026-09219-2

Page metadata

Field	Value
type	design
id	llm-simulated-patient-history-taking-model
title	LLM-configured simulated patient as a scalable, standardized practice environment for history taking
description	The article configures a large language model (ChatGPT-5.2, temperature 0.7, top-p 0.9, not fine-tuned) with preloaded gynecological case scripts to "behave as a real patient using predefined gynecological cases".
status	review
generated	by process:settle-candidates on 2026-11-04
trust	unverified — no one has confirmed this page's content
sources	1 — gao-lingling-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.