Diagnosing Glaucoma Based on the Ocular Hypertension Treatment Study Dataset Using Chat Generative Pre-Trained Transformer as a Large Language Model

Abstract

Purpose: To evaluate the capabilities of Chat Generative Pre-Trained Transformer (ChatGPT), as a large language model (LLM), for diagnosing glaucoma using the Ocular Hypertension Treatment Study (OHTS) dataset, and comparing the diagnostic capability of ChatGPT 3.5 and ChatGPT 4.0. Design: Prospective data collection study. Participants: A total of 3170 eyes of 1585 subjects from the OHTS were included in this study. Methods: We selected demographic, clinical, ocular, visual field, optic nerve head photo, and history of disease parameters of each participant and developed case reports by converting tabular data into textual format based on information from both eyes of all subjects. We then developed a procedure using the application programming interface of ChatGPT, a LLM-based chatbot, to automatically input prompts into a chat box. This was followed by querying 2 different generations of ChatGPT (versions 3.5 and 4.0) regarding the underlying diagnosis of each subject. We then evaluated the output responses based on several objective metrics. Main Outcome Measures: Area under the receiver operating characteristic curve (AUC), accuracy, specificity, sensitivity, and F1 score. Results: Chat Generative Pre-Trained Transformer 3.5 achieved AUC of 0.74, accuracy of 66%, specificity of 64%, sensitivity of 85%, and F1 score of 0.72. Chat Generative Pre-Trained Transformer 4.0 obtained AUC of 0.76, accuracy of 87%, specificity of 90%, sensitivity of 61%, and F1 score of 0.92. Conclusions: The accuracy of ChatGPT 4.0 in diagnosing glaucoma based on input data from OHTS was promising. The overall accuracy of ChatGPT 4.0 was higher than ChatGPT 3.5. However, ChatGPT 3.5 was found to be more sensitive than ChatGPT 4.0. In its current forms, ChatGPT may serve as a useful tool in exploring disease status of ocular hypertensive eyes when specific data are available for analysis. In the future, leveraging LLMs with multimodal capabilities, allowing for integration of imaging and diagnostic testing as part of the analyses, could further enhance diagnostic capabilities and enhance diagnostic accuracy. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Keywords

• ChatGPT
• Diagnosis
• Glaucoma
• Large language models