Eyes on AI: Advancing Ophthalmic Imaging and Oculomics for Systemic Health Insights

Ophthalmic imaging is rapidly becoming a cornerstone of both precision medicine and AI-driven disease prediction, offering unprecedented insight into ocular and systemic health. Advances in fundus photography, OCT, and deep learning have expanded the clinical and research potential of retinal biomarkers—supporting early detection of eye disease, forecasting systemic conditions, and enabling large-scale population health studies. This session explores these emerging opportunities through the NIH Eyes on Health Partnered Research Study and recent breakthroughs in AI for retinal analysis.

The Eyes on Health initiative—developed in partnership with the All of Us Research Program, the National Eye Institute (NEI), and the National Institute of Biomedical Imaging and Bioengineering (NIBIB)—demonstrates how multimodal eye imaging collected from 5,000 diverse participants can be integrated with clinical records, genomic data, and social determinants of health to advance discovery in precision medicine.

Complementing this population-level perspective, the session will examine cutting-edge AI applications that leverage retinal imaging for disease prediction, including early identification of glaucoma and other major causes of vision loss. Presenters will discuss study design, imaging workflows, data harmonization, interoperability, and FAIR data principles, alongside real-world challenges in building generalizable and interpretable AI models for ophthalmic care.

Attendees will gain insight into the technical, clinical, and participant-centered considerations that shape large-scale imaging research and how advanced AI tools can be responsibly incorporated into operational ophthalmic workflows.

Objectives

• Describe how multimodal ocular imaging can be leveraged within large-scale research programs to identify systemic and ophthalmic disease biomarkers.
• Explain how AI and computer vision methods are applied to retinal imaging for disease prediction and clinical decision support.
• Identify workflow, interoperability, and data governance challenges involved in scaling ophthalmic imaging studies and deploying AI tools in real-world environments.
• Discuss strategies for enhancing reproducibility, standardization, and scalability when integrating machine learning approaches into oculomics research and clinical care.