在眼科问题答案中,GPT-4,GPT-o3,GPT-5,Gemini-3-Flash和DeepSeek-R1的比较性能
Ping Zhang1, Jiaoman Wang2, Xinya Hu3
1Department of Ophthalmology, Shenzhen People's Hospital, The Second Clinical Medical College of Jinan University, Shenzhen, Guangdong, China.
Frontiers in cell and developmental biology
|February 16, 2026
概括
双子座-3-Flash和GPT-o3在眼科AI问答方面表现出最佳表现,显示出高精度和一致性. DeepSeek-R1也显得有前途,特别是在复杂的医学问题上.
科学领域:
- 人工智能在医学中的应用
- 眼科人工智能 眼科人工智能
- 大型语言模型 (LLM)
背景情况:
- 大型语言模型 (LLM) 在眼科等专业医疗领域显示出巨大的潜力.
- 目前的研究主要验证了个别的LLM,缺乏对表现最好的模型进行系统比较.
研究的目的:
- 系统地评估和比较眼科领域领先的LLM (GPT-4,GPT-o3,GPT-5,Gemini-3-Flash,DeepSeek-R1) 的表现.
- 评估不同LLM和提示策略的响应一致性和事实准确性.
主要方法:
- 使用了来自StatPearls的300个眼科多选题,按难度分类.
- 每个LLM都通过直接和基于角色的提示三次回答问题.
- 弗莱斯的kappa (κ) 测量了响应的一致性;整体准确度是主要指标.
主要成果:
- 双子座-3-Flash获得了最高的精度 (83.3%),其次是GPT-o3 (79.2%) 和DeepSeek-R1 (74.4%).
- GPT-o3显示出最高的一致性 (κ = 0.966),其次是DeepSeek-R1 (κ = 0.904) 和双子星-3-Flash (κ = 0.860).
- 促使策略的影响最小;DeepSeek-R1和GPT-o3在复杂的任务中表现出色.
结论:
- 双子座-3-Flash和GPT-o3为眼科临床决策支持提供了卓越的准确性和稳定性.
- 开源的DeepSeek-R1表现出了竞争力的表现,特别是在具有挑战性的问题上.
- 为了提高临床实用性,LLM需要进一步验证和多式联络整合.
相关概念视频
Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Sensitivity, Specificity, and Predicted Value
In healthcare diagnostics, laboratory tests play a crucial role in identifying and diagnosing a wide range of medical conditions. However, interpreting test results is not always straightforward. An abnormal test result does not always confirm the presence of a disease, just as a normal result does not guarantee its absence. To assess the reliability of these diagnostic tools, healthcare practitioners rely on two key statistical indicators: sensitivity and specificity.
Sensitivity is the...
Sensitivity is the...


