Tuesday, September 27, 2022
HomeDigit NewsArtificial intelligence trained to predict heart attack risk faster than doctors Several...

Artificial intelligence trained to predict heart attack risk faster than doctors Several times

A new AI tool developed by researchers at Cedars-Sinai Medical Center can accurately measure plaque deposits in coronary arteries and predict a patient’s heart attack risk within five years.

The examination, known as computed tomography angiography (CTA), is one of the best tools doctors have at their disposal to evaluate patients with heart disease. It has recently been found that CTA imaging of plaque deposits in the coronary arteries is the best way to predict the likelihood of a patient having a heart attack in the near future.


When plaques are measured, it takes at least 25-30 minutes for an expert, but now we can use this program (which scientists created – ed.) to quantify plaques from CTA images in five to six seconds

Senior author of the new study
Damini Day

To create the tool, the researchers first trained a plaque recognition algorithm using a CTA image data set of 921 patients. The tool was then tested on a test set of images from several hundred patients, with results almost identical to those of the experts.

The researchers then tested the tool’s ability to predict future heart attacks. By setting several thresholds for plaque volume, the researchers found that the tool could accurately categorize patients as high-risk and low-risk patients within five years of having a CTA.
- Advertisement -


Two Wheeler


Digit News