Assessing the possibility of using large language models in ocular surface diseases
GPT-4 model exhibits excellent performance in both answer relevance and confidence. PaLM2 shows a positive correlation (up to 0.8) in terms of answer accuracy during the exam. In terms of answer confidence, PaLM2 is second only to GPT4 and surpasses Claude 2, SenseNova, and GPT-3.5. Despite the fact that ocular surface disease is a highly specialized discipline, GPT-4 still exhibits superior performance, suggesting that its potential and ability to be applied in this field is enormous, perhaps with the potential to be a valuable resource for medical students and clinicians in the future.
Authors
- Hong Qi
- Qian Ling
- Jie Zou (ORCID: https://orcid.org/0000-0002-4735-6413)
- Wei Hong (ORCID: https://orcid.org/0000-0002-9236-9790)
- Chong-Gang Pei
- Xiaoyu Wang (ORCID: https://orcid.org/0000-0001-5477-1570)
- Yan-Mei Zeng
- Zhenkai Wu (ORCID: https://orcid.org/0009-0000-0613-0584)
- Jin‐Yu Hu (ORCID: https://orcid.org/0000-0003-2562-7304)
- Yi Shao
- Xian-Zhe Qian
- Xu Chen (ORCID: https://orcid.org/0000-0001-9925-2598)
- Cheng Chen (ORCID: https://orcid.org/0009-0001-6411-0394)
Institutions
- Central South University (CN)
- Nanchang University (CN)
- Maastricht University Medical Centre (NL)
- Maastricht University (NL)
- Shanghai Eye Disease Prevention & Treatment Center (CN)
- First Affiliated Hospital of Jiangxi Medical College (CN)
- The First People's Hospital of Changde (CN)
- First Affiliated Hospital of Nanchang University (CN)
Publication Details
- Journal
- International Journal of Ophthalmology
- Published
- 2024-12-18
- DOI
- https://doi.org/10.18240/ijo.2025.01.01
- Citations
- 10
- Primary Topic
- Syphilis Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 3.27
Funders
- National Natural Science Foundation of China