Retinal photo foundation model RetiME predicts mortality risk across 4 cohorts
EricTopol · x · 2026-11-02
A Nature Biomedical Engineering study introduces RetiME (Retinal Mortality Equivalent), a deep-learning biomarker built on retinal foundation models that maps low-cost, non-invasive retinal photographs directly to individual mortality risk. Trained on a European cohort and validated in three independent cohorts across Southeast Asia, Eurasia, and North America.
Chart data shows RetiME generally outperforms traditional biomarkers like telomere length and hand-grip strength across endpoints including asthma, COPD, dementia, Alzheimer's, myocardial infarction, and stroke. Eric Topol notes retinal photos will become a gateway to predict and prevent disease—a cheap screening tool for ageing populations.
More from Research
- Mentorship workshop on AI and the future of learning theory, Nov 16, ft. Scott Aaronson — thegautamkamath · 2026-11-03
- Frank Calegari essay: mathematics has changed with AI — mathematicians should act like it — littmath · 2026-11-03
- Rohan Anil's CoreAuto trains MoE across two global clusters over a 25 Gbps link — _arohan_ · 2026-11-03
- LLM4Code 2027 workshop at ICSE Dublin opens CFP with Nov 13 deadline — LingmingZhang · 2026-11-03
- Blogger claims AI refuted the Exponential Time Hypothesis, neared crypto key curves — on paper — LeviTurk · 2026-11-03
- Amazon-led HULK framework gives Unitree G1 humanoid the strength to pull a 300 kg cart — CyberRobooo · 2026-11-02