Retinal age gap as a predictive biomarker of stroke risk

AI Generated Summary*

In UK Biobank, a deep learning algorithm trained on fundus photographs from 11,052 disease-free participants estimated retinal age; the gap between predicted and chronological age was tested against incident stroke in 35,304 people without prior stroke. Over a median 5.83 years, 282 participants (0.80%) had a stroke. After full adjustment, each extra year of gap carried a 4% higher hazard (HR 1.04, 95% CI 1.00 to 1.08), and the top quintile had more than twice the risk of the lowest (HR 2.37, 95% CI 1.37 to 4.10). For 10-year prediction, retinal age alone gave an AUC of 0.676, not significantly different from a conventional risk factor model (0.662). Limitations include no external validation and a relatively young cohort.

*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.