Oculomics and AI: the eye as a biomarker for health span

AI Generated Summary*

Review of how ocular structures and molecular signals may indicate biological aging and health span, framed around the eye as part of the central nervous system. Topics include retinal vessel caliber, OCT layer thickness, OCT-angiography, corneal and lens changes, pupil and eye movement measures, flavoprotein fluorescence, NAD+, taurine, cytokines, GFAP, and proteomics of lens, cornea, vitreous and tears. AI models for retinal, lens and aqueous humor aging are surveyed. A fundus-based age gap carried a mortality hazard ratio of 1.02 per year, while higher RetiPhenoAge values had a ratio of 1.92; these use different scales and are not directly comparable. Limits include training on healthy eyes, limited ethnic diversity, opaque models, privacy, and scarce multimodal datasets.

*This summary was generated by AI and is published unedited. Oku does not alter these summaries. It may contain errors or omissions and is provided for general informational purposes only. Oku does not guarantee its accuracy, completeness, or reliability. For authoritative information, please refer to the original, peer-reviewed article.