Google can now detect heart disease through an eye scan

Google can now detect heart disease through an eye scan

Ronald Pratt
February 21, 2018

Those scans helped train the networks on which telltale signs tended to indicate long-term health dangers.

Alun Hughes, a professor at University College London thinks Google may be on to something due to a "long history of looking at the retina to predict cardiovascular risk", but he still thinks the algorithm merits further tests to be certain, The Verge reported. But no one taught the algorithms what to look for: Instead, the systems taught themselves, by reviewing enough data to learn the patterns often found in the eyes of people at risk. "This discovery is particularly exciting because it suggests we might discover even more ways to diagnose health issues from retinal images". Increasingly, however, researchers have been using eye scans to screen for high blood pressure and all of the cardiovascular ailments that go along with it. Other disease factors such as diabetes significantly increases risk.

Krumholz cautioned that an eye scan isn't ready to replace more conventional approaches. "These techniques allow us to generate a heatmap that shows which pixels were the most important for a predicting a specific cardiovascular risk factor", said Peng.

The tech predicts risk while being noninvasive, fast, and convenient.

In the gray retinal image used by the deep-learning algorithm, blood pressure is highlighted in shades of green.

Google's algorithm isn't flawless.

Google to bring Allo's Smart Reply feature to third party apps
The project is still in very early stages of development, and not much is known about it, other than the fact that it exists. Like all other projects within Area 120 , it's a very early experiment so there aren't many details to share right now .

For this study the team used the machine to look into the eyes of 284,335 patients.

According to the researchers, the study results demonstrate "not only that these [heart attack risk] signals are present in the retina, but that they are also quantifiable to a degree of precision not reported before".

Given that the algorithm could accurately predict risk factors, the scientists also trained the algorithm to predict the onset of a major cardiovascular event, such as a heart attack within five years.

"Explaining how the algorithm is making its prediction gives doctor more confidence in the algorithm itself", Peng wrote.

A promising start, this research is still in its early days, with Verily noting that "more work must be done to develop and validate these findings on larger patient cohorts before this can arrive in a clinical setting".

The idea that the hallmarks of disease could be detected through computational analysis has been alluring to engineers. Learning whether you are prone to heart disease can prevent millions of deaths every year as heart disease is the top killer worldwide.