Issue |
ITM Web Conf.
Volume 70, 2025
2024 2nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)
|
|
---|---|---|
Article Number | 01003 | |
Number of page(s) | 8 | |
Section | Traffic Prediction and Analysis | |
DOI | https://doi.org/10.1051/itmconf/20257001003 | |
Published online | 23 January 2025 |
Application and Comparative Study of Large Language Model in Early Prediction of Glaucoma
Electrical and Electronic Engineering, Liverpool Jolin Moores University, Rodney House, 70 Mount Pleasant, Liverpool, L35UX, UK
Corresponding author: SBC-22-8096@sbc.usst.edu.cn
Glaucoma is an important problem in global public health. However, the symptoms of glaucoma are not obvious in the early stages, and the correct diagnosis of glaucoma is very challenging. This paper aims to explore and compare the application effects of several advanced large language models in the early prediction of glaucoma. The study selected a variety of large language models, including Chat Generative Pre-trained transformer (ChatGPT), to build a glaucoma prediction model and analyze clinical data, genetic information, and lifestyle data of patients. The results of empirical studies show that ChatGPT and other models show high accuracy and good generalization ability in predicting the risk of glaucoma, especially in identifying high-risk patients. In addition, the performance of different models on specific data sets is different, suggesting that model selection should be optimized according to actual application scenarios and data characteristics. This study not only provides a new technical means for the early screening of glaucoma but also expands a new direction for the application of large language models in the medical field.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.