Application of Large Language Models in Complex Clinical Cases: Cross-Sectional Evaluation Study
GPTo1 and Deepseek-R1 show strong clinical potential, boosting efficiency, maintaining accuracy, and reducing costs. GPT4o and Kimi performed moderately, indicating suitability for broader clinical tasks. Further research is needed to validate LLaMa3 series and Gemini in clinical decision.
Authors
- Jiannan Xu (ORCID: https://orcid.org/0000-0003-0586-6703)
- Weibin Wu (ORCID: https://orcid.org/0000-0002-2272-8735)
- Yuanheng Huang (ORCID: https://orcid.org/0000-0003-3357-8645)
- Yeyu Shen
- Jian Zhang (ORCID: https://orcid.org/0000-0001-5000-6142)
- Kai Zhang (ORCID: https://orcid.org/0000-0002-7877-4538)
- Guozhen Yang
- Xiaojun Li (ORCID: https://orcid.org/0000-0001-7078-8241)
- Yonghui Wu (ORCID: https://orcid.org/0000-0003-2392-1382)
- H D Chen (ORCID: https://orcid.org/0000-0003-3905-5095)
Institutions
- Sun Yat-sen University (CN)
- Third Affiliated Hospital of Sun Yat-sen University (CN)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2025-08-14
- DOI
- https://doi.org/10.2196/73941
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00