Google’s new AI algorithm can predict heart disease by looking into your eyes
Google’s health subsidiary, Verily, announced yesterday that their new AI algorithm can assess heart disease risk by analyzing scans of the back of a patient’s eyes.
The new software purportedly can determine a person’s age, blood pressure, and smoking habits and use the data to predict the risk of a major cardiac event.
Ok… how does it work?
The scan takes place on the rear interior wall of the eye (AKA the fundus), where a large number of blood vessels that reflect the body’s health exist. Doctors can make inferences about a person’s cardiovascular health by studying these vessels with a camera.
To “train” the algorithm, Verily’s scientists used machine learning to study medical data from almost 300k patients — some with cardiovascular issues, some without.
The algorithm was able to tell which patients had heart issues with 70% accuracy (just shy of the 72% accuracy of traditional blood testing).
Health tech: the new “it” initiative
Whether it’s insurtech, biotech, or some other new sexytech we’ve never heard of, companies are chomping at the bit to get into the healthcare industry.
Last month alone, Amazon decided to create their own company health insurance free from “profit-making incentives,” while Apple announced their new effort to sync user medical records with their health app on the iPhone as part their new iOS.
Google’s heart disease pre-cog has a lot of promise, but many physicians feel the work needs to continue before it should achieve acceptance on a broader level. Nonetheless, it is a huge breakthrough for “non-invasive” health evaluations.