Google develops AI software that can read retina to predict heart attack risk

Representative image Pixabay

In a major breakthrough, Google researchers have discovered an advanced way to assess a person's risk of cardiovascular events with machine learning. The new software developed by them is capable of predicting an individual's age, blood pressure, and his or her lifestyle habits by just looking at the retina.

The software can be used to predict the risk of a major cardiac event with roughly the same accuracy as the currently used traditional methods, said the team in the study titled 'Prediction of Cardiovascular Risk Factors from Retinal Fundus Photographs via Deep Learning', which has been published in the journal Nature Biomedical Engineering.

"Using deep-learning models trained on data from 284,335 patients and validated on two independent datasets of 12,026 and 999 patients, we predicted cardiovascular risk factors not previously thought to be present or quantifiable in retinal images, such as age, gender, smoking status, systolic blood pressure and major adverse cardiac events," wrote Google researchers in the study report.

Even though the idea of predicting heart's health by looking at the eyes seem a bit naive, it is a reality that the rear interior wall of the eye is loaded with blood vessels which reflects the overall health of a person's body. Analyzing these blood vessels will help to predict various factors contributing to cardiovascular events like age, smoking habit and blood pressure.

This new method will help doctors to analyze the health of an individual quickly and easier as it does not involve a blood test. However, the new method requires to undergo clinical trials before it can be used in hospitals.

In a recent talk with the Verge, Luke Oakden-Rayner, a medical researcher at the University of Adelaide said Google's work was solid, and it clearly shows how the implementation of artificial intelligence will prove existing diagnostic tools.

"They're taking data that's been captured for one clinical reason and getting more out of it than we currently do. Rather than replacing doctors, it's trying to extend what we can actually do," Luke Oakden-Rayner told the Verge.

Related topics : Artificial intelligence