AI-driven analysis of retinal images may support earlier risk stratification for dementia and stroke, but evidence for improved clinical outcomes is insufficient.
2
Nearly half of dementia cases may be preventable or delayed through risk factor modification, and up to 80% of strokes can be prevented with timely detection.
3
The retina's shared characteristics with the central nervous system make it a potential site for assessing brain health through AI-driven 'oculomics'.
4
Most oculomics models are in early clinical evaluation and have been judged by technical performance metrics, which may not establish clinical usefulness.
5
The authors call for clearer definitions and regulatory standards for oculomics tools, emphasizing they should complement existing screening strategies.
At ARVO, Cecilia S. Lee, MD, MS, and Aaron Y. Lee, MD, MSCI, discuss barriers to AI deployment in ophthalmology, including interoperability and model development.
