A large language model digital patient system enhances ophthalmology history taking skills

Система цифрового пациента на основе большой языковой модели улучшает навыки сбора анамнеза в офтальмологии
Duoru Lin, Lanqin Zhao, Haotian Lin, Zhenzhen Liu, Yahan Yang, Xiaohang Wu, Yangfan Yang, Yiqing Li, Mingjie Luo, Jianyu Pang, Shaowei Bi, Yunxi Lai, Jingjing Chen, Lixue Liu, Ling Jin, Wenben Chen, Rongxin Chen, Ching‐Kit Tsui, Kezheng Xu, Yuxian Zou
2025-08-04

digital patientlarge language modelmedical history-takingophthalmology educationretrieval-augmented framework
Clinical trainees face limited opportunities to practice medical history-taking skills due to scarce case diversity and access to real patients. To address this, we developed a large language model-based digital patient (LLMDP) system that transforms de‑identified electronic health records into voice‑enabled virtual patients capable of free‑text dialog and adaptive feedback, based on our previously established open-source retrieval-augmented framework. In a single‑center randomized controlled trial (ClinicalTrials.gov: NCT06229379; N = 84), students trained with LLMDP achieved a 10.50-point increase in medical history-taking assessment scores (95% CI: 4.66-16.33, p < 0.001) compared to those using traditional methods. LLMDP-trained students also demonstrated greater empathy. Participants reported high satisfaction with LLMDP, emphasizing its role in reducing training costs and boosting confidence for real patient interactions. These findings provide evidence that LLM-driven digital patients enhance medical history-taking skills and offer a scalable, low-risk pathway for integrating generative AI into ophthalmology education.
1
A voice-enabled large language model digital patient system transforms de-identified electronic health records into adaptive virtual history-taking encounters.
2
In a single-center randomized controlled trial of 84 students, LLMDP training increased history-taking assessment scores by 10.50 points versus traditional methods (95% CI: 4.66–16.33; p < 0.001).
3
Participants reported high satisfaction, citing reduced training costs and increased confidence for interactions with real patients.
4
Students trained with LLMDP demonstrated greater empathy than those using traditional training methods.
5
The system offers a scalable, low-risk approach for integrating generative AI into ophthalmology education.

LLM-based digital patient system for ophthalmology history-taking training

The system’s effectiveness in enhancing medical history-taking skills, empathy, confidence, and training satisfaction among clinical trainees

Publication Details
Publication Date
2025-08-04
Journal
Publisher
ISSN
Cited by
39
Access Type
Author Information
Authors
Duoru Lin
Lanqin Zhao
Haotian Lin
Zhenzhen Liu
Yahan Yang
Xiaohang Wu
Yangfan Yang
Yiqing Li
Mingjie Luo
Jianyu Pang
Shaowei Bi
Yunxi Lai
Jingjing Chen
Lixue Liu
Ling Jin
Wenben Chen
Rongxin Chen
Ching‐Kit Tsui
Kezheng Xu
Yuxian Zou
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%