A Biomarker of Aging Based on Retinal Images
Researchers here discuss analysis of images of the retina as a way to produce biomarkers of aging. Older people with a predicted age that is higher than their chronological age, based on retinal imagery, exhibit a higher mortality rate. The growing diversity of clocks estimating biological age illustrate that just about every sizable set of biological data can mined to produce algorithmic combinations of data that correlate with mortality and incidence of age-related disease. Producing these clocks is the easy part of the task. It will be harder to calibrate and understand the clocks well enough to use them to assess the effectiveness of potential age-slowing and age-reversing therapies.
A growing body of evidence suggests that the network of small vessels (microvasculature) in the retina might be a reliable indicator of the overall health of the body's circulatory system and the brain. While the risks of illness and death increase with age, it's clear that these risks vary considerably among people of the same age, implying that 'biological ageing' is unique to the individual and may be a better indicator of current and future health, say the researchers.
Researchers turned to deep learning to see if it might accurately predict a person's retinal age from images of the fundus, the internal back surface of the eye, and to see whether any difference between this and a person's real age, referred to as the 'retinal age gap', might be linked to a heightened risk of death. The researchers drew on 80,169 fundus images taken from 46,969 adults aged 40 to 69, all of whom were part of the UK Biobank, a large, population-based study of more than half a million middle aged and older UK residents. Some 19,200 fundus images from the right eyes of 11,052 participants in relatively good health at the initial Biobank health check were used to validate the accuracy of the deep learning model for retinal age prediction.
This showed a strong association between predicted retinal age and real age, with an overall accuracy to within 3.5 years. The retinal age gap was then assessed in the remaining 35,917 participants during an average monitoring period of 11 years. During this time, 1,871 (5%) participants died: 321 (17%) of cardiovascular disease; 1018 (54.5%) of cancer; and 532 (28.5%) of other causes including dementia. The proportions of 'fast agers' - those whose retinas looked older than their real age - with retinal age gaps of more than 3, 5, and 10 years were, respectively, 51%, 28%, and 4.5%. Each 1 year increase in the retinal age gap was associated with a 2% increase in the risk of death from any cause.