Google has developed an algorithm that can tell if someone is at risk for a heart attack or stroke just by looking at the patient's eyes, said Drew Harwell and Carolyn Johnson at The Washington Post. Google researchers took retina scans, which can be used to gauge an individual's blood pressure, age, and whether or not they smoke, from more than 280,000 U.S. and U.K. patients and fed them into a neural network. The AI spotted patterns in the scans associated with cardiovascular risk factors.
"When presented images of the eyes of two different people — one who suffered a major cardiac event such as a heart attack or stroke within five years of the photo and the other who did not — the algorithms could correctly pick the patient who fell ill 70 percent of the time." Even though that accuracy rate doesn't outperform other approaches such as blood tests, the algorithm could "flag risk with a fast, cheap, and noninvasive test."