LLM-Based Clinical History Taking System: A Persona-Driven Approach
  • Choi, Dasol
  • Jung, Yujoon
  • Kim, Joonyoung
  • Oh, Namkee
  • Oh, Herin
  • ... Kim, Taerim
  • 외 2명
Citations

WEB OF SCIENCE

0
Citations

SCOPUS

1

초록

Standardized patients (SPs) are vital for clinical training but resource-intensive. We developed a systematic approach for generating SP cases using GPT-4o and validated 12 cases across three chief complaints. Expert validation showed good clinical authenticity (information flow: 3.7±0.5, realism: 3.4±0.8) and accuracy (3.4±0.5). Medical students (n=15) rated virtual patient interactions positively (appropriateness: 7.9/10, accuracy: 7.5/10). Results suggest LLM-generated SP cases offer viable educational tools complementing traditional SP programs.

키워드

Large Language ModelsMedical EducationStandardized PatientsVirtual Patients
제목
LLM-Based Clinical History Taking System: A Persona-Driven Approach
저자
Choi, DasolJung, YujoonKim, JoonyoungOh, NamkeeOh, HerinLee, SeunghyupSeo, JunhyukKim, Taerim
DOI
10.3233/SHTI251254
발행일
2025-08
유형
Article
저널명
Studies in health technology and informatics
329
페이지
1866 ~ 1867