Developing and Validating a Coding Scheme for Clinical Reasoning in History Taking Using Generative AI–Based Virtual Patients: Systematic Text Condensation Approach
JMIR Medical Education · 2026-04-13 · 12 · e84347-e84347
DOI: 10.2196/84347 ↗At a glance
Journal article in JMIR Medical Education, published online on 2026-04-13. Written by Naping Chen and 11 co-authors. Institution: Department of Clinical Skills Training Center, Shantou University Medical College, Shantou, Guangdong, China. Major MEDLINE topics: Clinical Reasoning, Medical History Taking, Students, Medical. Cited 2 times so far (Crossref); 67 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
Effective history taking helps clinicians identify key symptoms and form accurate hypotheses. Generative artificial intelligence (GenAI)–based virtual patients (VPs) are increasingly used to simulate and practice history taking. However, there is currently no straightforward approach to effectively identify students’ clinical reasoning activities during these interactions, which limits the ability to provide instructional feedback.
Objective
This study aims to develop and validate a coding scheme to identify medical students’ history-taking behaviors during interactions with GenAI-based VPs.
Methods
Second-year medical students (N=210) participated in 5 history-taking cases with GenAI-based VPs, yielding 1030 dialogues. Researchers applied the systematic text condensation method to these dialogue data from cases 1 to 4 to inductively develop a coding scheme and validate coding consistency. Subsequently, the dialogue data from case 5 were used to assess the correlation between the students’ history-taking behaviors and their academic performance, including diagnostic accuracy, history-taking checklist scores, clinical knowledge test scores, and postencounter form scores.
Results
A coding scheme comprising 12 behaviors across 3 dimensions—clinical reasoning behaviors, information gathering behaviors, and social interaction behaviors—was developed with high interrater reliability (κ≥0.85). The correlation analysis revealed that key clinical reasoning behaviors, such as summarizing and integrating and logical organization , showed significant positive correlations with multiple performance metrics, underscoring their importance in fostering clinical competence. In contrast, information gathering behaviors such as specifying symptoms and routine question were associated with clinical knowledge and thoroughness of history taking but were less predictive of diagnostic accuracy.
Conclusions
This study developed a reliable, theory-informed coding scheme that can identify students’ questioning behaviors during history taking with GenAI-based VPs. The scheme effectively captures higher-order cognitive strategies and provides valuable insights into the development of clinical reasoning in medical students. This approach offers a scalable and efficient way to integrate real-time feedback into future medical education, fostering personalized learning and advancing competency-based assessments in clinical training.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Clinical Skills Training Center, Shantou University Medical College, Shantou, Guangdong, China.
- Graduate School of Education, Peking University, 5th Yiheyuan Road, Beijing, 100871, China, 86 15210167528.
- Office of Teaching Affairs, Shantou University Medical College, Shantou, Guangdong, China.
- Faculty of Information Technology, Monash University, 25 Exhibition Walk, Clayton, Melbourne, VIC 3168, Australia.
- School of Public Health and Preventive Medicine, Monash University, Melbourne, Australia.
- Department of Cardiology, The First Affiliated Hospital of Shantou University Medical College, Shantou, Guangdong, China.
ORCID profiles: Naping Chen, Luzhen Tang, Yang Liu, Changmin Lin, Zijian Li, Chujun Shi, Mengyu Xia, Dragan Gasevic, Danijela Gasevic, Jinbin Zheng, Yizhou Fan, Xinyu Li
Cite
APA
Chen, N., Tang, L., Liu, Y., Lin, C., Li, Z., Shi, C., Xia, M., Gasevic, D., Gasevic, D., Zheng, J., Fan, Y., & Li, X. (2026). Developing and Validating a Coding Scheme for Clinical Reasoning in History Taking Using Generative AI–Based Virtual Patients: Systematic Text Condensation Approach. JMIR Medical Education, 12, e84347-e84347. https://doi.org/10.2196/84347
Vancouver
Chen N, Tang L, Liu Y, Lin C, Li Z, Shi C, et al. Developing and Validating a Coding Scheme for Clinical Reasoning in History Taking Using Generative AI–Based Virtual Patients: Systematic Text Condensation Approach. JMIR Medical Education. 2026;12:e84347-e84347. doi:10.2196/84347
BibTeX
@article{Chen2026,
author = {Chen, Naping and Tang, Luzhen and Liu, Yang and Lin, Changmin and Li, Zijian and Shi, Chujun and Xia, Mengyu and Gasevic, Dragan and Gasevic, Danijela and Zheng, Jinbin and Fan, Yizhou and Li, Xinyu},
title = {Developing and Validating a Coding Scheme for Clinical Reasoning in History Taking Using Generative AI–Based Virtual Patients: Systematic Text Condensation Approach},
journal = {JMIR Medical Education},
year = {2026},
volume = {12},
pages = {e84347--e84347},
doi = {10.2196/84347}
}
EUVIMED