Re-timing mortality risk through individualized modelling of lifespan trajectories.

RetiME, a deep learning biomarker from low-cost retinal photographs, robustly predicts all-cause and cause-specific mortality and reconstructs personalized lifespan trajectories linked to observed outcomes.

• Why it matters: Affordable, large-scale screening is needed to improve preventive care in ageing populations, but existing risk tools often provide static estimates rather than timing of mortality risk.
• What they did: Trained on a European cohort, RetiME was externally validated across three independent cohorts in Southeast Asia, Eurasia, and North America, mapping retinal features to mortality risk and reconstructing individual lifespan trajectories.
• The result: Trajectory clustering revealed distinct mortality patterns (cancer-predominant, cardiometabolic, and neurodegenerative), and interpretability and genome-wide analyses identified biological and genetic signals tied to RetiME.

AI summary of the abstract · may contain errors · not medical advice · read the paper.