Google and Verily, one of its subsidiaries, have determined a new way to predict heart diseases in people. The company is using machine learning algorithms to scan the back of a patient’s eye, and gather data on blood pressure, age and whether they are smokers. The same can then be used to predict the possibility of a major cardiac disease in the patient’s future. The method is apparently almost as accurate as means that are currently available.
Google is using machine learning algorithms to scan the back of a patient’s eye, and gather data on blood pressure, age and whether they are smokers.
However, Google’s method could also be quicker and easier than current methods. It also doesn’t require a blood test to be conducted, though more thorough testing will be required before doctors can make it a staple test. The method was detailed in a paper published in the Nature journal Biomedical Engineering today. It had first been heard of in a peer review in September last year.
According to Luke Oakden-Rayner, a medical researcher who spoke to The Verge, Google’s technology is “solid, and shows how AI can help improve existing diagnostic tools.” Scientists at Google and Verily apparently used medical data from almost 300,000 patients to train the algorithm.