DOI QR코드

DOI QR Code

Exploring the feasibility of developing an education tool for pattern identification using a large language model: focusing on the case of a simulated patient with fatigue symptom and dual deficiency of the heart-spleen pattern

거대언어모델을 활용한 변증 교육도구 개발 가능성 탐색: 피로주증의 심비양허형 모의환자에 대한 사례구축을 중심으로

  • Won-Yung Lee (Department of Pathology, College of Korean Medicine, Wonkwang University) ;
  • Sang Yun Han (The Office of Korean Medicine Education, College of Korean Medicine, Daejeon University) ;
  • Seungho Lee (Department of Pathology, College of Korean Medicine, Woosuk University)
  • 이원융 (원광대학교 한의과대학 병리학교실) ;
  • 한상윤 (대전대학교 한의과대학 한의학교육실) ;
  • 이승호 (우석대학교 한의과대학 병리학교실)
  • Received : 2024.01.11
  • Accepted : 2024.01.29
  • Published : 2024.02.28

Abstract

Objective : This study aims to assess the potential of utilizing large language models in pattern identification education by developing a simulated patient with fatigue and dual deficiency of the heart-spleen pattern. Methods : A simulated patient dataset was constructed using the clinical practice examination module provided by the National Institute for Korean Medicine Development. The dataset was divided into patient characteristics, sample questions, and responses, and utilized to design the system, assistant, and user prompts, respectively. A web-based interface was developed using the Django framework and WebSocket. Results : We developed a simulated fatigue patient representing dual deficiency of the heart-spleen pattern through prompt engineering. To make practical tools, we further implemented web-based interfaces for the examinee's and evaluator's roles. The interface for examinees allows one to examine the simulated patient and provides access to a personalized number for future access. In addition, the interface for evaluators included a page that provided an overview of each examinees' chat history and evaluation criteria in real-time. Conclusion : This study is the first development of an educational tool integrated with a large language model for pattern identification education, which is expected to be widely applied to Korean medicine education.

Keywords

Acknowledgement

이 논문은 우석대학교 교내학술연구비 지원에 의하여 연구됨.

References

  1. Jin H-J, Lee J, Jang E. Research trends of pattern identification of korean medicine using the network analysis. The Journal of the Korea Contents Association. 2014;14(12):1037-1046.  https://doi.org/10.5392/JKCA.2014.14.12.1037
  2. Kim JW, Kim HJ, Jang ES, Jung HJ, Hwang MW, Nam DH. Survey on pattern identification and treatment of chronic fatigue in Korea medicine. Journal of Physiology & Pathology in Korean Medicine. 2018;32(2):126-133.  https://doi.org/10.15188/kjopp.2018.04.32.2.126
  3. Tian S, Yang W, Le Grange JM, Wang P, Huang W, Ye Z. Smart healthcare: making medical care more intelligent. Global Health Journal. 2019;3(3):62-65.  https://doi.org/10.1016/j.glohj.2019.07.001
  4. Bourke J, Roper S, Love JH. Innovation in legal services: The practices that influence ideation and codification activities. Journal of Business Research. 2020;109:132-147.  https://doi.org/10.1016/j.jbusres.2019.11.057
  5. Kocon J, Cichecki I, Kaszyca O, et al. ChatGPT: Jack of all trades, master of none. Information Fusion. 2023:101861. 
  6. Brin D, Sorin V, Vaid A, et al. Comparing ChatGPT and GPT-4 performance in USMLE soft skill assessments. Scientific Reports. 2023;13(1):16492. 
  7. Garabet R, Mackey BP, James Cross M, Weingarten M. ChatGPT-4 performance on USMLE Step 1 questions and its implications for medical education: A comparative study across systems and disciplines. 2023; 
  8. Ekin S. Prompt engineering for ChatGPT: A quick guide to techniques, tips, and best practices. Authorea Preprints. 2023; 
  9. Jang D, Yun T-R, Lee C-Y, Kwon Y-K, Kim C-E. GPT-4 can pass the Korean National Licensing Examination for Korean Medicine Doctors. PLOS Digital Health. 2023;2(12):e0000416. 
  10. National Institute for Korean Medicine Development. https://nikom.or.kr/nikom/index.do 
  11. Cleland JA, Abe K, Rethans J-J. The use of simulated patients in medical education: AMEE Guide No 42. Medical teacher. 2009;31(6):477-486.  https://doi.org/10.1080/01421590903002821
  12. Zellers R, Holtzman A, Rashkin H, et al. Defending against neural fake news. Advances in neural information processing systems. 2019;32