Researchers Have Developed An AI Tool To Help Predict Heart Attacks

Cedars-Sinai Medical Center researchers claim to have developed an artificial intelligence-enabled tool that can forecast if a person will have a heart attack.

According to Cedars researchers, the tool, which was initially published in The Lancet Digital Health, effectively identified which patients will have a heart attack within five years based on the volume and composition of plaque in arteries carrying blood to the heart.

AI Tool That Predicts Heart Attacks, Developed By Researchers - India Ahead

According to medical experts, plague clots can limit blood flow, raising the risk of a heart attack.  While doctors have used a test called coronary computed tomography angiography to take 3D images of the heart and arteries, there has never been a clear and concise method to evaluate the plaque shown in those scans, according to the researchers.

“Coronary plaque is often not measured because there is not a fully automated way to do it,” according to a statement from Damini Dey, director of the quantitative image analysis lab in the Biomedical Imaging Research Institute at Cedars-Sinai and senior author of the study.

“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.”

AI is getting smarter and creepier, and it can even predict when a person  will die | by Richard van Hooijdonk | Towards Data Science

Dey and colleagues created an artificial intelligence system using coronary CTA pictures from over 900 patients – images that clinicians had previously reviewed.

Researchers reported that after “training”, the algorithm correctly predicted the five-year risk of heart attack for 1,611 participants.

AI in Cardiology: Where We Are Now and Where to Go Next | tctmd.com

“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,” Dey said.

The study was published in the journal The Lancet Digital Health.

Source: Cedars Sinai

Leave a Reply

Your email address will not be published. Required fields are marked *