A quick and pain-free scan of the human eyeball could one day help doctors identify 'fast agers', who are at greater risk of early mortality.
Getting older obviously has an impact on everybody's body, but just because two people have the same number of years under their belt doesn't mean they are physically declining at the same rate.
Looking deep into a person's eyes could be a far better way to measure their true biological age, and this could provide a glimpse into the future health of patients.
A machine learning model has now been taught to predict a person's years of life simply by looking at their retina, which is the tissue at the back of the eye.
The algorithm is so accurate, it could predict the age of nearly 47,000 middle-aged and elderly adults in the United Kingdom within a bracket of 3.5 years.
Just over a decade after these retinas were scanned, 1,871 individuals had died, and those who had older-looking retinas were more likely to fall in this group.
For instance, if the algorithm predicted a person's retina was a year older than their actual age, their risk of death from any cause in the next 11 years went up by 2 percent. At the same time, their risk of death from a cause other than cardiovascular disease or cancer went up by 3 percent.
The findings are purely observational, which means we still don't know what is driving this relationship at a biological level.
Nevertheless, the results support growing evidence that the retina is highly sensitive to the damages of aging. Because this visible tissue hosts both blood vessels and nerves, it could tell us important information about an individual's vascular and brain health.
Previous studies have suggested the cells at the back of the human eye can help us predict the onset of cardiovascular disease, kidney disease, and other signs of aging. But this is the first study to present the 'retinal age gap' as a strong predictor of mortality as a whole.
"The significant association between retinal age gap and non-cardiovascular/non-cancer mortality, together with the growing evidence of the link between eye and brain, may support the notion that the retina is the 'window' of neurological diseases," the authors write.
Because only 20 people in the study died due to dementia, the authors were unable to link this specific brain disorder to retinal health.
They also point out that cardiovascular-related deaths have gone down in recent years, as medicine continues to prevent what would once have been fatal events.
This means that retinal health could still be an important lens into cardiovascular health, despite the fact that it was not linked to cardiovascular mortality.
Previous studies, for instance, have shown photographs of the retina can help predict cardiovascular risk factors.
"This body of work supports the hypothesis that the retina plays an important role in the aging process and is sensitive to the cumulative damages of aging which increase the mortality risk," the authors conclude.
Other existing predictors of biological age, like neuroimaging, the DNA methylation clock, and the transcriptome aging clock, are not as accurate as the retinal age gap appears to be. These methods can also be costly, time-consuming and invasive.
The retina, meanwhile, can be easily scanned in less than 5 minutes. If we can learn more about how this layer of tissue is connected to the rest of the body, clinicians could have an excellent new tool on their hands.
The study was published in the British Journal of Ophthalmology.