An automated Artificial Intelligence (AI) algorithm is using deep learning to predict damaging cardiovascular events such as heart attacks.
Using CT imaging scans, the AI system automatically measures coronary artery calcium to help physicians and patients make more informed decisions about cardiovascular prevention. The system has been developed 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) as quantifying the amount of plaque shown in CT scans requires radiological expertise, time, and specialised equipment.
The team hope the findings from the AI system, which have been published in Nature Communications will improve the identifications of individuals at high risk of cardiovascular events. While the tool is currently only for research purposes, lead author Roman Zeleznik, MSc, a data scientist in Artificial Intelligence in Medicine (AIM) and his team, have made it open source and freely available for anyone to use.
Assessing risk with AI
The team trained the deep learning system on data from the Framingham Heart Study (FHS), a long-term asymptomatic community cohort study, where participants received dedicated calcium scoring CT scans which were manually scored by expert human readers and used to train the deep learning system.
The deep learning system was then applied to three additional study cohorts, which included heavy smokers having lung cancer lung cancer screening CT, patients with stable chest pain having cardiac CT, and patients with acute chest pain having cardiac CT. The scores from the AI system correlated with the manual calcium scores from human experts and also independently predicted who would go on to have a major adverse cardiovascular event like a heart attack.
Corresponding author Hugo Aerts, PhD, director of the AIM programme 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.”
“In theory, the deep learning system does a lot of what a human would do to quantify calcium,” said Zeleznik. “Our paper shows that it may be possible to do this in an automated fashion.”
“This is an opportunity for us to get additional value from these chest CTs using AI,” said co-author Michael Lu, MD, MPH, director of artificial intelligence at MGH’s Cardiovascular Imaging Research Center. “The coronary artery calcium score can help patients and physicians make informed, personalised 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.”
Udo Hoffmann, MD, director of CIRC@MGH, who is the principal investigator of CT imaging in the FHS, PROMISE and ROMICAT, emphasised 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 generalisability of these results to clinical settings.
