Application of a deep-learning marker for morbidity and mortality prediction derived from retinal photographs: a cohort development and validation study

Abstract

Background: Biological ageing markers are useful to risk stratify morbidity and mortality more precisely than chronological age. In this study, we aimed to develop a novel deep-learning-based biological ageing marker (referred to as RetiPhenoAge hereafter) using retinal images and PhenoAge, a composite biomarker of phenotypic age.

Methods: We used retinal photographs from the UK Biobank dataset to train a deep-learning algorithm to predict the composite score of PhenoAge. We used a deep convolutional neural network architecture with multiple layers to develop our deep-learning-based biological ageing marker, as RetiPhenoAge, with the aim of identifying patterns and features in the retina associated with variations of blood biomarkers related to renal, immune, liver functions, inflammation, and energy metabolism, and chronological age. We determined the performance of this biological ageing marker for the prediction of morbidity (cardiovascular disease and cancer events) and mortality (all-cause, cardiovascular disease, and cancer) in three independent cohorts (UK Biobank, the Singapore Epidemiology of Eye Diseases [SEED], and the Age-Related Eye Disease Study [AREDS] from the USA). We also compared the performance of RetiPhenoAge with two other known ageing biomarkers (hand grip strength and adjusted leukocyte telomere length) and one lifestyle factor (physical activity) for risk stratification of mortality and morbidity. We explored the underlying biology of RetiPhenoAge by assessing its associations with different systemic characteristics (eg, diabetes or hypertension) and blood metabolite levels. We also did a genome-wide association study to identify genetic variants associated with RetiPhenoAge, followed by expression quantitative trait loci mapping, a gene-based analysis, and a gene-set analysis. Cox proportional hazards models were used to estimate the hazard ratios (HRs) and corresponding 95% CIs for the associations between RetiPhenoAge and the different morbidity and mortality outcomes.

Findings: Retinal photographs for 34 061 UK Biobank participants were used to train the model, and data for 9429 participants from the SEED cohort and for 3986 participants from the AREDS cohort were included in the study. RetiPhenoAge was associated with all-cause mortality (HR 1·92 [95% CI 1·42-2·61]), cardiovascular disease mortality (1·97 [1·02-3·82]), cancer mortality (2·07 [1·29-3·33]), and cardiovascular disease events (1·70 [1·17-2·47]), independent of PhenoAge and other possible confounders. Similar findings were found in the two independent cohorts (HR 1·67 [1·21-2·31] for cardiovascular disease mortality in SEED and 2·07 [1·10-3·92] in AREDS). RetiPhenoAge had stronger associations with mortality and morbidity than did hand grip strength, telomere length, and physical activity. We identified two genetic variants that were significantly associated with RetiPhenoAge (single nucleotide polymorphisms rs3791224 and rs8001273), and were linked to expression quantitative trait locis in various tissues, including the heart, kidneys, and the brain.

Interpretation: Our new deep-learning-derived biological ageing marker is a robust predictor of mortality and morbidity outcomes and could be used as a novel non-invasive method to measure ageing.

Funding: Singapore National Medical Research Council and Agency for Science, Technology and Research, Singapore.

Figure 1

Kaplan-Meier curves showing the time to event across the quartiles of RetiPhenoAge in UK Biobank. A. All-cause mortality, B. CVD mortality, C. cancer mortality, D. CVD events, and E. cancer events.

Figure 2:

Risk of mortality and morbidity associated with RetiPhenoAge, right hand grip strength, telomere length and physical activity in the UK Biobank study. All these biomarkers were considered as continuous. Their distributions were log transform, and center scale to make the comparison possible. The hazard ratios were considered for an increase in 1 standard deviation. All the models were adjusted for chronological age and sex. For right hand grip strength, telomere length and physical activity, we inversed the distribution (1 – the actual value) to get the same direction of effect that RetiPhenoAge (increased values thus corresponded to increased risk). The numbers at the right side of the plot correspond to the p-values for the difference between the HRs of right hand grip strength, telomere length and physical activity, versus the HR of RetiPhenoAge (one-sided Z-tests).

Figure 3:

associations between RetiPhenoAge and different systemic & metabolic characteristics in UK Biobank. The pie chart represents the effect over range in %. These effects were obtained using a linear regression model adjusted for chronological age.