Feasibility study of using GPT for history-taking training in medical education: a randomized clinical trial

Abstract Backgrounds Traditional methods of teaching history-taking in medical education are limited by scalability and resource intensity. This study aims to assess the effectiveness of simulated patient interactions based on a custom-designed Generative Pre-trained Transformer (GPT) model, develop...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhen Wang, Ting-Ting Fan, Meng-Li Li, Nin-Jun Zhu, Xiao-Chen Wang
Format: Article
Language:English
Published: BMC 2025-07-01
Series:BMC Medical Education
Subjects:
Online Access:https://doi.org/10.1186/s12909-025-07614-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849343838393466880
author Zhen Wang
Ting-Ting Fan
Meng-Li Li
Nin-Jun Zhu
Xiao-Chen Wang
author_facet Zhen Wang
Ting-Ting Fan
Meng-Li Li
Nin-Jun Zhu
Xiao-Chen Wang
author_sort Zhen Wang
collection DOAJ
description Abstract Backgrounds Traditional methods of teaching history-taking in medical education are limited by scalability and resource intensity. This study aims to assess the effectiveness of simulated patient interactions based on a custom-designed Generative Pre-trained Transformer (GPT) model, developed using OpenAI’s ChatGPT GPTs platform, in enhancing medical students’ history-taking skills compared to traditional role-playing methods. Methods A total of 56 medical students were randomly assigned into two groups: an GPT group using GPT-simulated patients and a control group using traditional role-playing. Pre- and post-training assessments were conducted using a structured clinical examination to measure students’ abilities in history collection, clinical reasoning, communication skills, and professional behavior. Additionally, students’ evaluations of the educational effectiveness, satisfaction, and recommendation likelihood were assessed. Results The GPT-simulation group showed significantly higher post-training scores in the structured clinical examination compared to the control group (86.79 ± 5.46,73.64 ± 4.76, respectively, P < 0.001). Students in the GPT group exhibited higher enthusiasm for learning, greater self-directed learning motivation, and better communication feedback abilities compared to the control group (P < 0.05). Additionally, the student satisfaction survey revealed that the GPT group rated higher on the diversity of diseases encountered, ease of use, and likelihood of recommending the training compared to the control group (P < 0.05). Conclusions GPT-based history-taking training effectively enhances medical students’ history-taking skills, providing a solid foundation for the application of artificial intelligence (AI) in medical education. Clinical trial number NCT06766383.
format Article
id doaj-art-4b1a30873165465f82dfec5442fd1a2f
institution Kabale University
issn 1472-6920
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series BMC Medical Education
spelling doaj-art-4b1a30873165465f82dfec5442fd1a2f2025-08-20T03:42:51ZengBMCBMC Medical Education1472-69202025-07-0125111110.1186/s12909-025-07614-9Feasibility study of using GPT for history-taking training in medical education: a randomized clinical trialZhen Wang0Ting-Ting Fan1Meng-Li Li2Nin-Jun Zhu3Xiao-Chen Wang4Department of Cardiology, The Second Affiliated Hospital of Anhui Medical UniversityDepartment of Cardiology, The Second Affiliated Hospital of Anhui Medical UniversityDepartment of Cardiology, The Second Affiliated Hospital of Anhui Medical UniversityDepartment of Cardiology, The Second Affiliated Hospital of Anhui Medical UniversityDepartment of Cardiology, The Second Affiliated Hospital of Anhui Medical UniversityAbstract Backgrounds Traditional methods of teaching history-taking in medical education are limited by scalability and resource intensity. This study aims to assess the effectiveness of simulated patient interactions based on a custom-designed Generative Pre-trained Transformer (GPT) model, developed using OpenAI’s ChatGPT GPTs platform, in enhancing medical students’ history-taking skills compared to traditional role-playing methods. Methods A total of 56 medical students were randomly assigned into two groups: an GPT group using GPT-simulated patients and a control group using traditional role-playing. Pre- and post-training assessments were conducted using a structured clinical examination to measure students’ abilities in history collection, clinical reasoning, communication skills, and professional behavior. Additionally, students’ evaluations of the educational effectiveness, satisfaction, and recommendation likelihood were assessed. Results The GPT-simulation group showed significantly higher post-training scores in the structured clinical examination compared to the control group (86.79 ± 5.46,73.64 ± 4.76, respectively, P < 0.001). Students in the GPT group exhibited higher enthusiasm for learning, greater self-directed learning motivation, and better communication feedback abilities compared to the control group (P < 0.05). Additionally, the student satisfaction survey revealed that the GPT group rated higher on the diversity of diseases encountered, ease of use, and likelihood of recommending the training compared to the control group (P < 0.05). Conclusions GPT-based history-taking training effectively enhances medical students’ history-taking skills, providing a solid foundation for the application of artificial intelligence (AI) in medical education. Clinical trial number NCT06766383.https://doi.org/10.1186/s12909-025-07614-9Artificial IntelligenceHistory-taking TrainingMedical EducationGPT SimulationClinical Skills
spellingShingle Zhen Wang
Ting-Ting Fan
Meng-Li Li
Nin-Jun Zhu
Xiao-Chen Wang
Feasibility study of using GPT for history-taking training in medical education: a randomized clinical trial
BMC Medical Education
Artificial Intelligence
History-taking Training
Medical Education
GPT Simulation
Clinical Skills
title Feasibility study of using GPT for history-taking training in medical education: a randomized clinical trial
title_full Feasibility study of using GPT for history-taking training in medical education: a randomized clinical trial
title_fullStr Feasibility study of using GPT for history-taking training in medical education: a randomized clinical trial
title_full_unstemmed Feasibility study of using GPT for history-taking training in medical education: a randomized clinical trial
title_short Feasibility study of using GPT for history-taking training in medical education: a randomized clinical trial
title_sort feasibility study of using gpt for history taking training in medical education a randomized clinical trial
topic Artificial Intelligence
History-taking Training
Medical Education
GPT Simulation
Clinical Skills
url https://doi.org/10.1186/s12909-025-07614-9
work_keys_str_mv AT zhenwang feasibilitystudyofusinggptforhistorytakingtraininginmedicaleducationarandomizedclinicaltrial
AT tingtingfan feasibilitystudyofusinggptforhistorytakingtraininginmedicaleducationarandomizedclinicaltrial
AT menglili feasibilitystudyofusinggptforhistorytakingtraininginmedicaleducationarandomizedclinicaltrial
AT ninjunzhu feasibilitystudyofusinggptforhistorytakingtraininginmedicaleducationarandomizedclinicaltrial
AT xiaochenwang feasibilitystudyofusinggptforhistorytakingtraininginmedicaleducationarandomizedclinicaltrial