Now Google AI Predicts Heart Disease From Retina Scan

The algorithm could distinguish the retinal images of a smoker from that of a non-smoker 71 per cent of the time.

(Photo: iStockphoto)

Your eyes are indeed the windows to your heart!

Researchers at Google have developed a new artificial intelligence system that can accurately predict the risk of heart attack, high BP or stroke by scanning images of people's retina, according to a new study published in the Nature Biomedical Engineering journal.

The algorithm, which has been created by Google AI and Verily Life Sciences, was fairly accurate at predicting the risk of a cardiovascular event.

While doctors can typically distinguish between the retinal images of patients with severe high blood pressure and normal patients, the algorithm could go further to predict the systolic blood pressure within 11 milimetre Hg on average for patients overall, including those with and without high blood pressure.

The discovery may point to more ways to diagnose health issues from retinal images, researchers said.

The algorithm could distinguish the retinal images of a smoker from that of a non-smoker 71 per cent of the time.

Our algorithm used the entire image to quantify the association between the image and the risk of heart attack or stroke. 

Lily Peng, Google Brain Team

Given the retinal image of one patient who later experienced a major cardiovascular event (such as a heart attack) and the image of another patient who did not, the algorithm could pick out the heart patient 70 per cent of the time.

This matches the accuracy levels of tests that require a blood draw to measure cholesterol.

Traditionally, doctors diagnose patients based on a sophisticated form of guess and test - making hypotheses from observations and then designing and running experiments to test the hypotheses.

However, with medical images, observing and quantifying associations can be difficult because of the wide variety of features, patterns, colours, values and shapes that are present in real images.

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.

Lily Peng, Google Brain Team

Retinal scanning can in future help scientists generate more targeted hypotheses and drive a wide range of research.

(With inputs from PTI)