AI and the World's Hard Problems · Medicine & drug discovery · Nature (computational biology) · 2026-10-22
Estimating chronological age from flicker-induced retinal vascular reactivity: a machine learning approach
The researchers tested machine learning and deep learning models, including an Extra Trees Regressor, to estimate chronological age non-invasively from retinal artery and vein diameter changes across three flicker-light cycles. The best-performing model achieved a mean absolute error of 9.3 and a mean absolute percentage error of 17.7%. LIME analysis identified key features influencing the age predictions.