94% of researchers rate our articles as excellent or good
Learn more about the work of our research integrity team to safeguard the quality of each article we publish.
Find out more
ORIGINAL RESEARCH article
Front. Artif. Intell.
Sec. Medicine and Public Health
Volume 8 - 2025 | doi: 10.3389/frai.2025.1527010
This article is part of the Research Topic Soft Computing and Machine Learning Applications for Healthcare Systems View all 12 articles
Applied Machine Learning in Intelligent Systems: Knowledge Graph-Enhanced Ophthalmic Contrastive Learning with "Clinical Profile" Prompts
Provisionally accepted
Mini Han Wang 1,2*
Jiazheng Cui 3,4 Simon Ming-Yuen Lee 5
Zhiyuan Lin 6 Peijin Zeng 6,7 Xinyue Li 8 Haoyang Liu 10,9 Yunxiao Liu 10,9 Yang Xu 7
Yapeng Wang 9 José Lopes Camilo Da Costa Alves 11 Guanghui Hou 12* Junbin Fang 13*
Xiangrong Yu 14*
Kelvin Kam-Lung Chong 2*
Yi Pan 15- 1 Zhuhai Precision Medical Center, Zhuhai People's Hospital, Zhuhai, China
- 2 Department of Ophthalmology and Visual Sciences, Faculty of Medicine, The Chinese University of Hong Kong, Shatin, Hong Kong Region, China
- 3 Zhuhai Institute of Advanced Technology, Chinese Academy of Sciences (CAS), Zhuhai, Guangdong Province, China
- 4 Beijing Normal University - Hong Kong Baptist University United International College, Zhuhai, China
- 5 Hong Kong Polytechnic University, Kowloon, Hong Kong, SAR China
- 6 Perspective Technology Group, Zhuhai, Guangdong Province, China
- 7 Beijing Institute of Technology, Zhuhai, Zhuhai, Guangdong Province, China
- 8 Tianjin Medical University, Tianjin, Tianjin Municipality, China
- 9 Macao Polytechnic University, Macau, Macao, SAR China
- 10 Digital Healthcare and Artificial Intelligence Association,macao, Macao, Macao, SAR China
- 11 City University of Macau, Macao, Macao, SAR China
- 12 Zhuhai Aier Eye Hospital, Zhuai, China
- 13 Jinan University, Guangzhou, Guangdong Province, China
- 14 Zhuhai People's Hospital (Zhuhai Clinical Medical College of Jinan University), Zhuhai, Guangdong Province, China
- 15 Shenzhen Key Laboratory of Intelligent Bioinformatics, Shenzhen Institute of Advanced Technology, Shenzhen, China
This study explores the application of machine learning in intelligent systems by integrating knowledge graphs with contrastive learning, supplemented by "clinical profile" prompts, to fine-tune the ophthalmology-specific large model, MeEYE, built on the CHATGLM3-6B architecture. This approach significantly advances AI-driven ophthalmic diagnostic technology, enhancing both the accuracy and interpretability of diagnostic predictions.By incorporating domain-specific knowledge and utilizing contrastive learning, the model effectively captures clinically relevant features, providing transparent and reliable AI recommendations in clinical settings. This method addresses the critical need for explainable AI in medical diagnosis, offering clinicians clear, trustworthy insights that have the potential to improve patient outcomes. Rigorous evaluations and case studies validate the method's superior performance, emphasizing its potential to enhance diagnostic accuracy and optimize clinical decision-making across various healthcare applications. The findings underscore the importance of combining domain-specific knowledge with machine learning techniques to solve complex medical challenges in intelligent systems.
Keywords: machine learning, medical intelligent systems, Ophthalmic Disease Detection, knowledge graph, Contrastive learning, Clinical Profile Prompts, Interpretable artificial intelligence
Received: 12 Nov 2024; Accepted: 26 Feb 2025.
Copyright: © 2025 Han Wang, Cui, Lee, Lin, Zeng, Li, Liu, Liu, Xu, Wang, Alves, Hou, Fang, Yu, Chong and Pan. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Mini Han Wang, Zhuhai Precision Medical Center, Zhuhai People's Hospital, Zhuhai, China
Guanghui Hou, Zhuhai Aier Eye Hospital, Zhuai, China
Junbin Fang, Jinan University, Guangzhou, 510632, Guangdong Province, China
Xiangrong Yu, Zhuhai People's Hospital (Zhuhai Clinical Medical College of Jinan University), Zhuhai, Guangdong Province, China
Kelvin Kam-Lung Chong, Department of Ophthalmology and Visual Sciences, Faculty of Medicine, The Chinese University of Hong Kong, Shatin, Hong Kong Region, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.