A team of researchers at the Cedars-Sinai Medical Center in California, USA, has created an artificial intelligence-based tool capable of predicting one’s risk of a heart attack in the next five years. The tool does so on the basis of the composition and amount of plaque in the artery contributing blood to the heart.
Due to the formation of plaque, the artery becomes narrow. It causes difficulty in reaching the blood to the heart and increases the probability of heart failure. Coronary Computed Tomography Angiography (CCTA) is a medical test that creates 3D images of the heart and arteries. Following this test, doctors examine the exact condition of the artery.
But there is still no fast and simple way to measure the plaque from CTA images. This study has been published in The Lancet Digital Health.
According to Damini Dey, the author of this study and director of the Quantitative Image Analysis Lab at the Biomedical Imaging Research Institute at Cedars-Sinai, due to the lack of a fully automatic method, the measurement of coronary plaque is often not done. It usually takes 20 to 30 minutes. But this new invention can detect the amount of plaque from the CCTA image in 5 to 6 seconds, the author says.
After analysing CCTA images of 1196 people at 11 different locations in Australia, Germany, Japan, Scotland, and the US, researchers were able to identify blood and plaque using the AI algorithm. The doctors also examined the reports of 921 people.
What happened in the study:
Researchers ensured that the measurements made with this tool matched the amount of plaque observed in the coronary CCTA. They also confirmed this with the results of tests such as intravascular ultrasound and catheter-based coronary angiography. Both the tests are accurate methods of estimating plaque in the artery but take more time. In the end, researchers found that the CCTA image assessment using the AI algorithm gave an accurate prediction of the risk of a heart attack in 1,611 people over five years.
