The Diagnostic Ability of GPT-3.5 and GPT-4.0 in Surgery: Comparative Analysis
This study demonstrates that ChatGPT, particularly GPT-4.0, possesses significant diagnostic potential, with GPT-4.0 exhibiting higher accuracy than GPT-3.5. However, GPT-4.0 still has limitations, particularly in recognizing patient symptoms and laboratory data, indicating a need for more research in real-world clinical settings to enhance its diagnostic capabilities.
Authors
- D. Fang
- Jianning Zhang (ORCID: https://orcid.org/0000-0003-1943-7045)
- Hui Xie (ORCID: https://orcid.org/0000-0002-6219-1696)
- Chengliang Yin (ORCID: https://orcid.org/0000-0001-8262-5749)
- Xiaochun Sun
- Ping Hu (ORCID: https://orcid.org/0009-0004-4820-5360)
- Yue Tong (ORCID: https://orcid.org/0009-0009-8163-8367)
- Bingxian Wang
- Yanteng Li (ORCID: https://orcid.org/0000-0003-0613-8898)
- Hebin Che (ORCID: https://orcid.org/0009-0007-3060-0014)
- Gang Cheng (ORCID: https://orcid.org/0009-0003-5341-5808)
- Jiqi Zheng (ORCID: https://orcid.org/0009-0001-9070-9894)
- Jiayu Liu (ORCID: https://orcid.org/0000-0001-6976-4568)
- Yuanyuan Chen
- Xiuting Liang
- Fan Yang (ORCID: https://orcid.org/0000-0003-4017-4577)
Institutions
- Fujian Medical University (CN)
- Peking University (CN)
- Chinese PLA General Hospital (CN)
- Xian Central Hospital (CN)
- People's Liberation Army No. 150 Hospital (CN)
- First Affiliated Hospital of Fujian Medical University (CN)
- Chinese People’s Liberation Army 263 hospital (CN)
- Peking University Sixth Hospital (CN)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2024-09-10
- DOI
- https://doi.org/10.2196/54985
- Citations
- 20
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 2.41