EUVIMEDEUVIMED entdecken
Open Access

Quality Assessment of Large Language Model–Generated Medical Dialogue for Clinical Vignettes: Evaluation Study

Yasutaka Yanagita iD, Daiki Yokokawa iD, Shiichi Ihara iD, Ryo Yoshida iD, Yoshihide Okano iD, Takanori Uehara iD

JMIR Formative Research · 2025

DOI: 10.2196/80752 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Formative Research, 2025. Verfasst von Yasutaka Yanagita und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of General Medicine, Chiba University Hospital, Chiba, Japan, Chiba, Japan. Hauptthemen laut MEDLINE: Physician-Patient Relations, Artificial Intelligence, Communication, Language. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Traditional clinical vignettes, though widely used in medical education, often focus on prototypical presentations; require substantial time and effort to develop; and fail to represent patient diversity, the complexity of clinical conditions, patients’ perspectives, and the dynamic nature of physician-patient interactions.

Objective

This study aimed to evaluate the quality of Japanese-language physician-patient dialogues produced by generative artificial intelligence (AI), focusing on their medical accuracy and overall appropriateness as medical interviews.

Methods

We created an AI prompt that included a specific clinical history and instructed the model to simulate a cooperative patient responding to the physician’s questions to generate a physician-patient dialogue. The target diseases were those covered by the Japanese National Medical Licensing Examination. Each dialogue consisted of 25 turns by the physician and 25 by the patient, reflecting the typical volume of conversation in Japanese outpatient settings. Three internists independently evaluated each generated dialogue using a 7-point Likert scale across 6 criteria: coherence of the conversation, medical accuracy of the patient’s responses, medical accuracy of the physician’s responses, content of the medical history, communication skills, and professionalism. In addition, a composite score for each dialogue was calculated as the overall mean of these 6 criteria. Each dialogue was also examined for the presence of 5 essential clinical components commonly included in medical interviews: chief concern and clinical course since onset, physical findings, test results, diagnosis, and treatment course. A dialogue was considered to include a component only if all 3 evaluators independently confirmed its presence.

Results

The mean composite score was 5.7 (SD 1.0), indicating high overall quality. Mean scores for each criterion were as follows: coherence of the conversation, 5.9 (SD 0.9); medical accuracy of the patient’s responses, 6.0 (SD 0.9); medical accuracy of the physician’s responses, 5.6 (SD 1.1); content of medical history taking, 5.9 (SD 0.9); communication skills, 5.6 (SD 0.9); and professionalism, 5.5 (SD 1.1). Among the 5 clinical components assessed in each dialogue across 47 clinical cases, chief concern and clinical course were included in all 47 (100%) cases, physical findings in 15 (32%) cases, test results in 27 (57%) cases, diagnosis in 45 (96%) cases, and treatment course in 0 (0%) cases.

Conclusions

While physician oversight remains essential, it is feasible to efficiently create AI-generated educational materials for medical education that overcome the limitations of traditional clinical vignettes. This approach may reduce time and financial burdens, enhancing opportunities to practice clinical interviewing in settings that closely mirror real-world encounters.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Physician-Patient RelationsArtificial IntelligenceCommunicationLanguageHumansFemaleJapanMaleAdultLarge Language Models

Stichwörter der Autor:innen

ChatGPTartificial intelligenceclinical vignettesgenerative AImedical educationphysician-patient dialogue

Autor:innen und Institutionen

  • Department of General Medicine, Chiba University Hospital, Chiba, Japan, Chiba, Japan.

ORCID-Profile: Yasutaka Yanagita, Daiki Yokokawa, Shiichi Ihara, Ryo Yoshida, Yoshihide Okano, Takanori Uehara

Zitieren

APA

Yanagita, Y., Yokokawa, D., Ihara, S., Yoshida, R., Okano, Y., & Uehara, T. (2025). Quality Assessment of Large Language Model–Generated Medical Dialogue for Clinical Vignettes: Evaluation Study. JMIR Formative Research. https://doi.org/10.2196/80752

Vancouver

Yanagita Y, Yokokawa D, Ihara S, Yoshida R, Okano Y, Uehara T. Quality Assessment of Large Language Model–Generated Medical Dialogue for Clinical Vignettes: Evaluation Study. JMIR Formative Research. 2025. doi:10.2196/80752

BibTeX
@article{Yanagita2025,
  author = {Yanagita, Yasutaka and Yokokawa, Daiki and Ihara, Shiichi and Yoshida, Ryo and Okano, Yoshihide and Uehara, Takanori},
  title = {Quality Assessment of Large Language Model–Generated Medical Dialogue for Clinical Vignettes: Evaluation Study},
  journal = {JMIR Formative Research},
  year = {2025},
  doi = {10.2196/80752}
}
Kostenlos starten →