Hamilton Eye Institute, Department of Ophthalmology, University of Tennessee Health Science Center (X.H., H.R., Y.M., M.D., S.Y.), Memphis, Tennessee.
Department of Biomedical Engineering, University of Memphis and University of Tennessee Health Science Center (A.P.), Memphis, Tennessee.
Am J Ophthalmol. 2024 Oct;266:289-299. doi: 10.1016/j.ajo.2024.05.022. Epub 2024 May 31.
To investigate the capability of ChatGPT for forecasting the conversion from ocular hypertension (OHT) to glaucoma based on the Ocular Hypertension Treatment Study (OHTS).
Retrospective case-control study.
A total of 3008 eyes of 1504 subjects from the OHTS were included in the study.
We selected demographic, clinical, ocular, optic nerve head, and visual field (VF) parameters 1 year before glaucoma development from the OHTS participants. Subsequently, we developed queries by converting tabular parameters into textual format based on both eyes of all participants. We used the ChatGPT application program interface (API) to automatically perform ChatGPT prompting for all subjects. We then investigated whether ChatGPT can accurately forecast conversion from OHT to glaucoma based on various objective metrics.
Accuracy, area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and weighted F1 score.
ChatGPT4.0 demonstrated an accuracy of 75%, AUC of 0.67, sensitivity of 56%, specificity of 78%, and weighted F1 score of 0.77 in predicting conversion to glaucoma 1 year before onset. ChatGPT3.5 provided an accuracy of 61%, AUC of 0.62, sensitivity of 64%, specificity of 59%, and weighted F1 score of 0.63 in predicting conversion to glaucoma 1 year before onset.
The performance of ChatGPT4.0 in forecasting development of glaucoma 1 year before onset was reasonable. The overall performance of ChatGPT4.0 was consistently higher than ChatGPT3.5. Large language models (LLMs) hold great promise for augmenting glaucoma research capabilities and enhancing clinical care. Future efforts in creating ophthalmology-specific LLMs that leverage multimodal data in combination with active learning may lead to more useful integration with clinical practice and deserve further investigations.
基于眼高压治疗研究（OHTS），探讨 ChatGPT 预测眼高压（OHT）向青光眼转化的能力。
回顾性病例对照研究。
本研究共纳入了 OHTS 中的 1504 名受试者的 3008 只眼。
我们从 OHTS 参与者中选择了发展为青光眼前 1 年的人口统计学、临床、眼部、视神经头和视野（VF）参数。随后，我们基于所有参与者的双眼，将表格参数转换为文本格式来创建查询。我们使用 ChatGPT 应用程序接口（API）自动为所有受试者执行 ChatGPT 提示。然后，我们研究了 ChatGPT 是否可以基于各种客观指标准确预测 OHT 向青光眼的转化。
准确性、接受者操作特征曲线下面积（AUC）、敏感性、特异性和加权 F1 评分。
ChatGPT4.0 在预测发病前 1 年向青光眼转化方面的准确率为 75%，AUC 为 0.67，敏感性为 56%，特异性为 78%，加权 F1 评分为 0.77。ChatGPT3.5 在预测发病前 1 年向青光眼转化方面的准确率为 61%，AUC 为 0.62，敏感性为 64%，特异性为 59%，加权 F1 评分为 0.63。
ChatGPT4.0 预测发病前 1 年青光眼发展的性能合理。ChatGPT4.0 的整体性能始终高于 ChatGPT3.5。大型语言模型（LLMs）有望增强青光眼研究能力并改善临床护理。未来在创建眼科专用 LLM 方面的努力，结合多模态数据和主动学习，可能会导致与临床实践更有用的整合，值得进一步研究。
