Breakthrough AI tool predicts when heart attacks will strike

An AI-enabled tool that can predict when heart attacks will strike has been devised by researchers at Cedars-Sinai Medical Center, Los Angeles.

In tests, the tool accurately indicated which patients would experience a heart attack in five years, based on the amount and composition of plaque in arteries that supply blood to the heart. The breakthrough technique was first described in The Lancet Digital Health.

Images from 1,196 people who underwent a coronary computed tomography angiography (CTA) in Australia, Germany, Japan, Scotland and the United States were analysed by an AI algorithm to measure plaque levels. It ‘learnt’ to recognise plaque from coronary CTA images previously analysed by trained doctors.

Measurements made by the AI algorithm from CTA images accurately predicted heart attack risk within five years for 1,611 people as part of the SCOT-HEART trial. The study was funded by the US National Heart, Lung, and Blood Institute.

The algorithm first outlined coronary arteries in 3D images, then identified the blood and plaque deposits within the coronary arteries. The AI tool’s measurements corresponded with plaque amounts seen in coronary CTAs.

They also matched results with images taken by two invasive tests considered to be highly accurate in assessing coronary artery plaque and narrowing: intravascular ultrasound and catheter-based coronary angiography.

Plaque build-up can cause arteries to narrow, which makes it difficult for blood to get to the heart, increasing the likelihood of a heart attack. A CTA takes 3D images of the heart and arteries and can give doctors an estimate of how much a patient’s arteries have narrowed. Until now, however, there has not been a simple, automated and rapid way to measure the plaque visible in the CTA images.

Damini Dey, PhD, director of the quantitative image analysis lab in the Biomedical Imaging Research Institute at Cedars-Sinai and senior author of the study explained: “Coronary plaque is often not measured because there is not a fully automated way to do it. When it is measured, it takes an expert at least 25 to 30 minutes, but now we can use this program to quantify plaque from CTA images in five to six seconds.

“More studies are needed, but it’s possible we may be able to predict if and how soon a person is likely to have a heart attack based on the amount and composition of the plaque imaged with this standard test,” added Dey.