A device could make it more simple to predict if a person will have a heart attack

Researchers from Cedars-Sinai, Los Angeles, have designed an artificial-intelligence-enabled device that could make it more simple to predict if a person will have a heart attack. The team’s tool predicted which patients could experience a heart attack in five years based on the composition and amount of plaque in arteries supplying blood to the heart, and described their results in The Lancet Digital Health.

Plaque build-up can restrict arteries, making blood flow to the heart more difficult and raising the risk of a heart attack. A medical test called coronary computed tomography angiography (CTA) uses 3D images of the heart and arteries to evaluate how narrowed a patient’s arteries are. There hasn’t been an automatic or quick approach to measure the plaque seen in CTA photos before now.

PhD, director of the quantitative image analysis lab in the Biomedical Imaging Research Institute at Cedars-Sinai and senior author of the study, Damini Dey and colleagues analysed CTA images from 1,196 people who had a coronary CTA at 11 sites in Australia, Germany, Japan, Scotland, and the United States. The researchers taught the AI programme to assess plaque by teaching it from 921 coronary CTA pictures that clinicians had already analysed.

The programme initially creates 3D pictures of the coronary arteries before identifying the blood and plaque deposits. The measurements of the tool corresponded to plaque quantities seen in coronary CTAs, according to the researchers. They also compared the results to intravascular ultrasonography and catheter-based coronary angiography pictures. These two invasive techniques are extremely accurate in detecting plaque and constriction in coronary arteries. Finally, the researchers discovered that measurements taken from CTA images by the AI algorithm accurately predicted heart attack risk within five years for 1,611 participants in the SCOT-HEART experiment.

Dey, stated: “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 twenty five to thirty 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.”