Artificial intelligence has learned to predict the likelihood of a heart attack within 5 years

(ORDO NEWS) — A new artificial intelligence (AI)-based tool developed by Cedars-Sinai Medical Center, USA, can accurately measure plaque deposits in coronary arteries and predict a patient’s risk of heart attack within five years.

Alas, even when the algorithm is fully established, such a procedure will not be available to everyone.

Computed tomographic angiography (CT angiography) is one of the best tools doctors currently have for evaluating patients with heart disease.

It has recently been found that studying plaque deposits in the coronary arteries in this way can predict the likelihood of a patient having a heart attack in the near future.

The problem is that today there is no fully automated way to check for plaque deposits, and it also takes experts at least 25-30 minutes to perform such a procedure. But AI can do it in 5-6 seconds!

How the tool was developed

Artificial intelligence has learned to predict the likelihood of a heart attack within 5 years 2

To create a working model, the researchers first trained an algorithm to recognize plaque deposits using a CT angiography image dataset from 921 patients.

The tool was then tested on a test set of images of several hundred patients. AI conclusions almost completely coincided with the opinions of expert doctors.

After that, scientists had to teach AI to predict future heart attacks. By setting a series of plaque volume thresholds for the instrument to work, the researchers found that it could accurately categorize patients as high-risk and low-risk for heart attack up to five years after CT angiography.

Of course, these are only the first steps towards the introduction of such a system in healthcare. Larger studies will be needed to train algorithms for different patient populations.

And even when the technology is optimized, there will still be significant barriers to access for patients, because CT angiography is not a cheap or easily accessible diagnostic method.


Contact us: [email protected]

Our Standards, Terms of Use: Standard Terms And Conditions.