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

Abstract 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...

Full description

Saved in:
Bibliographic Details
Main Authors: Ming-Jie Luo, Shaowei Bi, Jianyu Pang, Lixue Liu, Ching-Kit Tsui, Yunxi Lai, Wenben Chen, Yahan Yang, Kezheng Xu, Lanqin Zhao, Ling Jin, Duoru Lin, Xiaohang Wu, Jingjing Chen, Rongxin Chen, Zhenzhen Liu, Yuxian Zou, Yangfan Yang, Yiqing Li, Haotian Lin
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-025-01841-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849235442164039680
author Ming-Jie Luo
Shaowei Bi
Jianyu Pang
Lixue Liu
Ching-Kit Tsui
Yunxi Lai
Wenben Chen
Yahan Yang
Kezheng Xu
Lanqin Zhao
Ling Jin
Duoru Lin
Xiaohang Wu
Jingjing Chen
Rongxin Chen
Zhenzhen Liu
Yuxian Zou
Yangfan Yang
Yiqing Li
Haotian Lin
author_facet Ming-Jie Luo
Shaowei Bi
Jianyu Pang
Lixue Liu
Ching-Kit Tsui
Yunxi Lai
Wenben Chen
Yahan Yang
Kezheng Xu
Lanqin Zhao
Ling Jin
Duoru Lin
Xiaohang Wu
Jingjing Chen
Rongxin Chen
Zhenzhen Liu
Yuxian Zou
Yangfan Yang
Yiqing Li
Haotian Lin
author_sort Ming-Jie Luo
collection DOAJ
description Abstract 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.
format Article
id doaj-art-2226b4249747426eb8da3acdc4f95c8d
institution Kabale University
issn 2398-6352
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-2226b4249747426eb8da3acdc4f95c8d2025-08-20T04:02:46ZengNature Portfolionpj Digital Medicine2398-63522025-08-018111210.1038/s41746-025-01841-6A large language model digital patient system enhances ophthalmology history taking skillsMing-Jie Luo0Shaowei Bi1Jianyu Pang2Lixue Liu3Ching-Kit Tsui4Yunxi Lai5Wenben Chen6Yahan Yang7Kezheng Xu8Lanqin Zhao9Ling Jin10Duoru Lin11Xiaohang Wu12Jingjing Chen13Rongxin Chen14Zhenzhen Liu15Yuxian Zou16Yangfan Yang17Yiqing Li18Haotian Lin19State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesState Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular DiseasesAbstract 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.https://doi.org/10.1038/s41746-025-01841-6
spellingShingle Ming-Jie Luo
Shaowei Bi
Jianyu Pang
Lixue Liu
Ching-Kit Tsui
Yunxi Lai
Wenben Chen
Yahan Yang
Kezheng Xu
Lanqin Zhao
Ling Jin
Duoru Lin
Xiaohang Wu
Jingjing Chen
Rongxin Chen
Zhenzhen Liu
Yuxian Zou
Yangfan Yang
Yiqing Li
Haotian Lin
A large language model digital patient system enhances ophthalmology history taking skills
npj Digital Medicine
title A large language model digital patient system enhances ophthalmology history taking skills
title_full A large language model digital patient system enhances ophthalmology history taking skills
title_fullStr A large language model digital patient system enhances ophthalmology history taking skills
title_full_unstemmed A large language model digital patient system enhances ophthalmology history taking skills
title_short A large language model digital patient system enhances ophthalmology history taking skills
title_sort large language model digital patient system enhances ophthalmology history taking skills
url https://doi.org/10.1038/s41746-025-01841-6
work_keys_str_mv AT mingjieluo alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT shaoweibi alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT jianyupang alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT lixueliu alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT chingkittsui alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT yunxilai alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT wenbenchen alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT yahanyang alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT kezhengxu alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT lanqinzhao alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT lingjin alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT duorulin alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT xiaohangwu alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT jingjingchen alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT rongxinchen alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT zhenzhenliu alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT yuxianzou alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT yangfanyang alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT yiqingli alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT haotianlin alargelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT mingjieluo largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT shaoweibi largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT jianyupang largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT lixueliu largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT chingkittsui largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT yunxilai largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT wenbenchen largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT yahanyang largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT kezhengxu largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT lanqinzhao largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT lingjin largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT duorulin largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT xiaohangwu largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT jingjingchen largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT rongxinchen largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT zhenzhenliu largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT yuxianzou largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT yangfanyang largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT yiqingli largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills
AT haotianlin largelanguagemodeldigitalpatientsystemenhancesophthalmologyhistorytakingskills