Using a deep learning model, which is a form of machine learning, the researchers estimated a "retinal age gap" between the actual biological health of the eye and the person's age since birth.
There was a 2% increase in the risk of death from any cause for each year of difference between a person's actual age and the older biological age identified in the eye, the study found.That might be due to a smaller number of such cases in the population studied, the researchers said, or to improvements in cancer and heart disease treatments.
"Our novel findings have determined that the retinal age gap is an independent predictor of increased mortality risk, especially of non-cardiovascular disease and non-cancer mortality," wrote He and his team.