Construction and Applications of Knowledge Graphs in Ophthalmology

Area of Science:

• Ophthalmology
• Artificial Intelligence
• Medical Informatics

Background:

• Knowledge Graphs (KGs) offer structured medical data representation, aiding information integration and reasoning.
• KGs have shown promise in ophthalmology for disease understanding, clinical decision support, and image analysis.

Purpose of the Study:

• To review methodologies for constructing medical KGs.
• To highlight KG applications in ophthalmology, emphasizing integration with medical imaging and large language models (LLMs).
• To discuss challenges and provide insights for advancing ophthalmology KGs.

Main Methods:

• Review of KG construction processes: acquisition, extraction, fusion, inference, visualization, and evaluation.
• Analysis of current ophthalmology KG applications.
• Exploration of integration strategies with medical imaging and LLMs.

Main Results:

• KGs facilitate disease understanding, clinical decision-making, ophthalmic image analysis, and intelligent question answering in ophthalmology.
• Integration of ophthalmic KGs with medical imaging and LLMs shows significant potential.
• Key challenges include data privacy, costs, multimodal data fusion, rare disease coverage, and limited application in education/research.

Conclusions:

• Ophthalmology KGs are valuable tools for advancing eye care research and clinical practice.
• Addressing identified challenges is crucial for deeper research and clinical translation of KGs.
• Future directions include enhanced multimodal data fusion and broader application in education and basic research.