Evaluation of Prompt Design and Internal Reasoning in Chatbot-Based Medical History Taking: Simulation Study
JMIR Medical Informatics · 21.08.2026 · 14 · e94614-e94614
DOI: 10.2196/94614 ↗Kurz gefasst
Fachartikel in der Zeitschrift JMIR Medical Informatics, online erschienen am 21.08.2026. Verfasst von Nattawipa Thawinwisan und 5 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Medicine, Kyoto University, 54 Shogoin-kawahara-cho, Sakyo-ku, Kyoto, Japan, 81 75-366-7701. Hauptthemen laut MEDLINE: Medical History Taking. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
A persistent discrepancy exists between patient-reported information and physician documentation. While conversational agents have been developed to collect medical histories prior to consultations, existing evaluations have largely focused on diagnostic accuracy or user satisfaction rather than on the completeness and clinical relevance of the information collected. There remains a need to assess the extent to which clinically relevant information is captured through chatbot-based interviews, and to understand how model configurations and instructional strategies influence this coverage.
Objective
This study aimed to evaluate the extent to which a chatbot can obtain clinically useful patient history information, and to examine how prompt detail and internal reasoning influence information coverage during chatbot-based medical interviews.
Methods
We developed a medical history-taking chatbot using the Qwen3-14B-Instruct model and evaluated 4 configurations in a 2×2 factorial design: detailed and thinking mode, detailed and nonthinking mode, minimal and thinking mode, and minimal and nonthinking mode. These configurations were compared against a rule-based system baseline (choice mode) using 66 standardized primary care clinical cases, with simulated patients interacting with the chatbot according to predefined case scripts. Information coverage (%) was assessed using a checklist inspired by Objective Structured Clinical Examination (OSCE) frameworks. Three physicians independently evaluated transcript coverage, with interrater agreement assessed using full agreement rates and Fleiss κ. For the 4 LLM configurations, coverage was analyzed using 2-way repeated-measures ANOVA to examine the effects of prompt detail, internal reasoning, and their interaction. All 5 configurations, including the rule-based baseline, were additionally compared using 1-way repeated-measures ANOVA with post hoc 2-tailed paired t tests.
Results
Interrater agreement was substantial (Fleiss κ=0.75). Across all 66 simulated cases, information coverage differed significantly among configurations ( P
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Graduate School of Medicine, Kyoto University, 54 Shogoin-kawahara-cho, Sakyo-ku, Kyoto, Japan, 81 75-366-7701.
- Preemptive Medicine and Lifestyle-Related Disease Research Center, Kyoto University Hospital, Kyoto, Japan.
- Division of Medical Information Technology and Administration Planning, Kyoto University Hospital, Kyoto, Japan.
ORCID-Profile: Nattawipa Thawinwisan, Chang Liu, Goshiro Yamamoto, Kazumasa Kishimoto, Yukiko Mori, Tomohiro Kuroda
Zitieren
APA
Thawinwisan, N., Liu, C., Yamamoto, G., Kishimoto, K., Mori, Y., & Kuroda, T. (2026). Evaluation of Prompt Design and Internal Reasoning in Chatbot-Based Medical History Taking: Simulation Study. JMIR Medical Informatics, 14, e94614-e94614. https://doi.org/10.2196/94614
Vancouver
Thawinwisan N, Liu C, Yamamoto G, Kishimoto K, Mori Y, Kuroda T. Evaluation of Prompt Design and Internal Reasoning in Chatbot-Based Medical History Taking: Simulation Study. JMIR Medical Informatics. 2026;14:e94614-e94614. doi:10.2196/94614
BibTeX
@article{Thawinwisan2026,
author = {Thawinwisan, Nattawipa and Liu, Chang and Yamamoto, Goshiro and Kishimoto, Kazumasa and Mori, Yukiko and Kuroda, Tomohiro},
title = {Evaluation of Prompt Design and Internal Reasoning in Chatbot-Based Medical History Taking: Simulation Study},
journal = {JMIR Medical Informatics},
year = {2026},
volume = {14},
pages = {e94614--e94614},
doi = {10.2196/94614}
}
EUVIMED