Could retinal scans be used to track human ageing?

Researchers have developed a ‘clock’ for tracking human ageing on the basis of retinal scans.

The study, which was published in eLife, found that the retinal ageing clock, eyeAge was capable of predicting an individual’s chronological age with a margin of error of 3.3 years when analysing retinal scans from the UK Biobank cohort.

Senior co-author of the study, Buck Institute professor Pankaj Kapahi, highlighted that retinal imaging could be valuable in tracking the efficacy of interventions aimed at slowing the ageing process.

“The results suggest that potentially, in less than one year we should be able to determine the trajectory of ageing with 71% accuracy by noting discernible changes in the eyes of those being treated,” he said.

Kapahi added that retinal scans are less prone to fluctuation than other biomarkers within the blood that are more dynamic – and may be influenced by factors such as eating a meal or a current infection.

Google researchers trained and tuned the retinal ageing model using the EyePACS data set of more than 100,000 patients.

The model was then applied to images within the UK Biobank cohort of more than 64,000 patients.