Application of Large Language Models in Medical Training Evaluation—Using ChatGPT as a Standardized Patient: Multimetric Assessment
ChatGPT, as a representative LLM, is a viable tool for simulating standardized patients in medical assessments, with the potential to enhance medical training. By incorporating proper prompts, ChatGPT's scoring accuracy and response realism significantly improved, approaching the feasibility of actual clinical use. Also, the influence of the adopted language is nonsignificant on the outcome of the chatbot.
Authors
- Xiaomei Tan (ORCID: https://orcid.org/0000-0002-5347-7115)
- Guangwu Qian (ORCID: https://orcid.org/0000-0001-9241-1699)
- Chenxu Wang (ORCID: https://orcid.org/0009-0009-0751-0242)
- Shuhan Li (ORCID: https://orcid.org/0009-0005-8225-944X)
- Rong Yin (ORCID: https://orcid.org/0000-0003-4596-5407)
- Di Liu (ORCID: https://orcid.org/0009-0005-6433-5904)
- Nuoxi Lin (ORCID: https://orcid.org/0009-0002-5239-493X)
- Kang Li (ORCID: https://orcid.org/0000-0002-8136-9816)
- Ying Han (ORCID: https://orcid.org/0009-0002-5230-4164)
- Xiandi Wang (ORCID: https://orcid.org/0000-0002-7912-1790)
- Xinyu Zhang (ORCID: https://orcid.org/0009-0000-2893-3986)
- Dan Pu (ORCID: https://orcid.org/0000-0002-1669-1649)
Institutions
- Sichuan University (CN)
- West China Medical Center of Sichuan University (CN)
- Chengdu Institute of Information Technology (China) (CN)
- West China Hospital of Sichuan University (CN)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2024-11-11
- DOI
- https://doi.org/10.2196/59435
- Citations
- 34
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 4.09