Google’s DeepMind artificial intelligence project famously used machine learning to develop AlphaGo, a boardgame-playing AI that managed to successfully defeat one of the top Go players in the world. Now, Google is turning its AI powerhouse toward a somewhat more meaningful cause by teaming up with the UK’s National Health Service (NHS) to tackle eye disease with machine learning.

The idea behind DeepMind’s new project is to train an AI to look at eye scans and recognize patterns consistent with various forms of eye disease, allowing doctors to catch and treat a number of conditions before they become serious. For example, according to DeepMind, early detection could prevent up to 98 percent of sight loss caused by diabetes.

Mustafa Suleyman, Google DeepMind co-founder and head of DeepMind Health, explained that the new project builds on some of the same concepts DeepMind used when it trained an AI to play classic Atari games.

“What we want to do is train an algorithm to classify a potential diagnosis in an image in the same way that we’ve trained algorithms to classify, say, chairs or plants in photos, or that we’ve trained algorithms to perform well in the Atari [game] simulator,” Suleyman said in a recent interview with Business Insider. “Essentially, what it’s doing is learning that a particular cluster of pixels are correlated with a particular outcome or action or object that we’re looking for.”

Google DeepMind’s project will be conducted at Moorfields Eye Hospital, an NHS hospital in London that specializes in researching and treating eye-related ailments. All of DeepMind’s findings, including its algorithms and end results, will be published in peer-reviewed journals for other researchers to view.

“Other researchers can benefit from the insight and also potentially other commercial partners can see that these sorts of algorithms are really successful,” Suleyman said.

According to Suleymna, Google DeepMind may have more NHS partnerships to announce in the near future.

Photo by Helena Jacoba