Scientists at Alphabet, Google’s parent company, have successfully used artificial intelligence to tell how great a person’s risk is of having a heart attack based on his or her retinal scan.
The procedure for this involves analyzing blood vessels in a region of the eye called the retinal fundus, Newsweek reports. The scientists work at Verily, formerly known as Google Life Sciences, and came up with the algorithm with the hope that it can make accurate evaluations of cardiovascular health more efficiently and easily compared to current methods.
The scientists trained deep-learning models on data gathered from over 250,000 patients. This way, they were able to predict the cardiovascular risk factors that science did not previously think was present in retinal fundus images. These risk factors included gender, blood pressure, smoking habits and an estimate of age to within four years of a person’s actual age.
The study stated,
Most cardiovascular risk calculators use some combination of these parameters to identify patients at risk of experiencing either a major cardiovascular event or cardiac-related mortality within a pre-specified time period, such as 10 years.
It added, “However, some of these parameters may be unavailable… We therefore explored whether additional signals for cardiovascular risk can be extracted from retinal images, which can be obtained quickly, cheaply and non-invasively in an outpatient setting.”
Deep-learning networks have already been used before to come up with algorithms that are able to diagnose diseases such as melanoma and blindness resulting from diabetes.
However, further tests are needed before this new method can be applied in a clinical setting. The study authors said, “The opportunity to one day readily understand the health of a patient’s blood vessels, key to cardiovascular health, with a simple retinal image could lower the barrier to engage in critical conversations on preventive measures to protect against a cardiovascular event.”
The study was published in the Nature journal Biomedical Engineering.