Retinal Age as a Predictive Biomarker for Mortality Risk

Background Ageing varies substantially, thus an accurate quantification of ageing is important. We developed a deep learning (DL) model that predicted age from fundus images (retinal age). We investigated the association between retinal age gap (retinal age-chronological age) and mortality risk in a population-based sample of middle-aged and elderly adults. Methods The DL model was trained, validated and tested on 46,834, 15,612 and 8,212 fundus images respectively from participants of the UK Biobank study alive on 28th February 2018. Retinal age gap was calculated for participants in the test (n=8,212) and death (n=1,117) datasets. Cox regression models were used to assess association between retinal age gap and mortality risk. A restricted cubic spline analyses was conducted to investigate possible non-linear association between retinal age gap and mortality risk. Findings The DL model achieved a strong correlation of 0.83 (P<0.001) between retinal age and chronological age, and an overall mean absolute error of 3.50 years. Cox regression models showed that each one-year increase in the retinal age gap was associated with a 2% increase in mortality risk (hazard ratio=1.02, 95% confidence interval:1.00-1.04, P=0.021). Restricted cubic spline analyses showed a non-linear relationship between retinal age gap and mortality (Pnon-linear=0.001). Higher retinal age gaps were associated with substantially increased risks of mortality, but only if the gap exceeded 3.71 years. Interpretation Our findings indicate that retinal age gap is a robust biomarker of ageing that is closely related to risk of mortality.