Artificial Intelligence Predicts Heart Attack Risk

Coronary artery calcification is the buildup of calcified plaque in the walls of the heart's arteries. It is an important predictor of adverse cardiovascular events like heart attacks. By using computed tomography (CT) scans, coronary calcium can be detected. The amount of plaque can be quantified by radiological expertise, time and specialized equipment. Chest CT scans are fairly common but calcium score CTs are not. The investigators have developed and evaluated a deep learning system that may help change this. The study conducted by investigators from Brigham and Women's Hospital's Artificial Intelligence in Medicine (AIM) Program and the Massachusetts General Hospital's Cardiovascular Imaging Research Center (CIRC) is published in the journal Nature Communications.

For this study, data from more than 20,000 individuals was collected and it showed promising results.

Corresponding author Hugo Aerts, PhD, director of the Artificial Intelligence in Medicine (AIM) Program at the Brigham and Harvard Medical School said, “Coronary artery calcium information could be available for almost every patient who gets a chest CT scan, but it isn't quantified simply because it takes too much time to do this for every patient. We've developed an algorithm that can identify high-risk individuals in an automated manner."

Along with his colleagues, lead author Roman Zeleznik, MSc, a data scientist in AIM developed the deep learning system to automatically and accurately predict cardiovascular events by scoring coronary calcium. Though the tool is currently used only for research purposes, the investigators have made it open source and freely available for anyone to use.

Zeleznik said that the deep learning system does a lot of what a human would do to quantify calcium.

By using data from Framingham Heart Study (FHS), a long-term asymptomatic community cohort study, the team trained the deep learning system. Additionally, deep learning system was then applied to three other study cohorts including the heavy smokers having lung cancer screening CT (NLST: National Lung Screening Trial), patients with stable chest pain having cardiac CT (PROMISE: the Prospective Multicenter Imaging Study for Evaluation of Chest Pain), and patients with acute chest pain having cardiac CT (ROMICAT-II: the Rule Out Myocardial Infarction using Computer Assisted Tomography trial).

Advertisement

The principal investigator of CT imaging in the FHS, PROMISE and ROMICAT, Udo Hoffmann, MD, director of CIRC at MGH said that one of the unique aspects of this study is the inclusion of three National Heart, Lung, and Blood Institute-funded high-quality image and outcome trials that strengthen the generalization ability of these results to clinical settings.

The automated calcium scores obtained from the deep learning system highly correlated with the manual calcium scores from human experts. The automated scores also independently predicted the risk of a major adverse cardiovascular event like a heart attack.

Advertisement

In the current guidelines, the coronary artery calcium score plays an important role for who should take a statin to prevent heart attacks.

Co-author of the study, Michael Lu, MD, MPH, director of artificial intelligence at MGH's Cardiovascular Imaging Research Center said, “This is an opportunity for us to get additional value from these chest CTs using AI. The coronary artery calcium score can help patients and physicians make informed, personalized decisions about whether to take a statin. From a clinical perspective, our long-term goal is to implement this deep learning system in electronic health records, to automatically identify the patients at high risk."

Source-Medindia