EUVIMEDEUVIMED entdecken
Open Access

Developing and Validating a Coding Scheme for Clinical Reasoning in History Taking Using Generative AI–Based Virtual Patients: Systematic Text Condensation Approach

Naping Chen iD, Luzhen Tang iD, Yang Liu iD, Changmin Lin iD, Zijian Li iD, Chujun Shi iD, Mengyu Xia iD, Dragan Gasevic iD, Danijela Gasevic iD, Jinbin Zheng iD, Yizhou Fan iD, Xinyu Li iD

JMIR Medical Education · 13.04.2026 · 12 · e84347-e84347

DOI: 10.2196/84347 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Medical Education, online erschienen am 13.04.2026. Verfasst von Naping Chen und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Clinical Skills Training Center, Shantou University Medical College, Shantou, Guangdong, China. Hauptthemen laut MEDLINE: Clinical Reasoning, Medical History Taking, Students, Medical. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Clinical ReasoningMedical History TakingStudents, MedicalHumansGenerative Artificial IntelligenceClinical CompetenceEducation, Medical, UndergraduatePatient SimulationFemaleMale

Stichwörter der Autor:innen

clinical reasoningcoding schemegenerative artificial intelligencehistory takingmedical educationvirtual patients

Autor:innen und Institutionen

  • 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-Profile: Naping Chen, Luzhen Tang, Yang Liu, Changmin Lin, Zijian Li, Chujun Shi, Mengyu Xia, Dragan Gasevic, Danijela Gasevic, Jinbin Zheng, Yizhou Fan, Xinyu Li

Zitieren

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}
}
Kostenlos starten →