Google AI device could predict a person's risk of a heart attack

Georgia Reed
February 20, 2018

Looking at deep-learning models on data from more than a quarter of a million patients, scientists were able to predict the cardiovascular risk factors that were not previously thought to be present.

THEY SAY the eyes are the window to the soul, but in the case of Google's artificial intelligence (AI), they offer the means to predict heart disease. Eye factors like blood vessels and lines in the ocular disc can give away things like that to the very well-trained eye, and this AI was very well-trained to look for discrepancies of just those sorts.

Researchers at Google and Verily used machine learning to analyze data of almost 300,000 patients and accurately predicted cardiovascular risk factors using retinal images in two datasets of 12,026 and 999 patients.

"Our approach uses deep learning to draw connections between changes in the human anatomy and disease, akin to how doctors learn to associate signs and symptoms with the diagnosis of a new disease".

The model was created using deep-learning models trained on data from 284 335 patients and validated on two independent datasets of 12 026 and 999 patients.

Philippe Coutinho back playing at Liverpool? Brazil set for Anfield friendly
I don't like talking about the round after the round you are playing, in fact I hate it. "He's a very important player and he doesn't always have to be the standout player".

With technological advances in medical and health industry, there are several breakthrough techniques to monitor one's health in a more seamless fashion than what we follow today. Information included the results of the eye screening and General health information. Learning whether you are prone to heart disease can prevent millions of deaths every year as heart disease is the top killer worldwide. By analyzing scans of the back of a patient's eye, the company's software is able to accurately deduce data, including an individual's age, blood pressure, and whether or not they smoke.

The researchers concluded: "The opportunity to one day readily understand the health of a patient's blood vessels, key to cardiovascular health, with a simple retinal image could lower the barrier to engage in critical conversations on preventive measures to protect against a cardiovascular event". What's interesting is that the blog entry claimed that the algorithm could detect whether the patient smoked or not and assess their systolic blood pressure based on image analysis.

Verily's head of cardiovascular health innovations, Michael McConnell, said it is promising but early research. In addition, this technique could help generate hypotheses for future scientific investigations into CV risk and the retina.

Further, the algorithm was "fairly accurate" at predicting the risk of a cardiovascular event directly, Peng wrote.

Other reports by

Discuss This Article