Google plans to use artificial intelligence to detect eye diseases

Google is planning to teach a computer to detect certain kinds of eye diseases, including diabetic retinopathy and macular degeneration.

"Teach" is not just a tech buzzword used by Google. The company plans to use artificial intelligence to actually teach machines to detect patterns in the records of 1.6 million London patients, according to USA Today. It’ll access the patient records through an ongoing agreement with the U.K.’s National Health Service.

The plan is to diagnose the diseases earlier and more accurately than human doctors, whose own accuracy in that area is only between 10 and 20 percent, USA Today said. The machines will learn to detect the disease better by having access to such a large number of patient records. They will be able to analyze what one researcher involved in the project described as “10,000 lifetimes’” worth of data, instead of the only one lifetime’s worth of experience afforded to an individual physician.

Google’s offshoot called DeepMind will manage the operation, reviewing retina scans taken at London's Moorfields Eye Hospital between 2007 and 2016, Newsweek reported.

“There’s so much at stake, particularly with diabetic retinopathy,” DeepMind’s co-founder Mustafa Suleyman told the Guardian. "If you have diabetes, you’re 25 times more likely to go blind. If we can detect this, and get in there as early as possible, then 98 percent of the most severe visual loss might be prevented."