Automated AI algorithm uses routine imaging to predict cardiovascular risk

January 29, 2021

Coronary artery calcification -- the buildup of calcified plaque in the walls of the heart's arteries -- is an important predictor of adverse cardiovascular events like heart attacks. Coronary calcium can be detected by computed tomography (CT) scans, but quantifying the amount of plaque requires radiological expertise, time and specialized equipment. In practice, even though chest CT scans are fairly common, calcium score CTs are not. 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) teamed up to develop and evaluate a deep learning system that may help change this. The system automatically measures coronary artery calcium from CT scans to help physicians and patients make more informed decisions about cardiovascular prevention. The team validated the system using data from more than 20,000 individuals with promising results. Their findings are published in Nature Communications.

"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," said corresponding author Hugo Aerts, PhD, director of the Artificial Intelligence in Medicine (AIM) Program at the Brigham and Harvard Medical School. "We've developed an algorithm that can identify high-risk individuals in an automated manner."

Working with colleagues, lead author Roman Zeleznik, MSc, a data scientist in AIM, developed the deep learning system described in the paper to automatically and accurately predict cardiovascular events by scoring coronary calcium. While the tool is currently only for research purposes, Zeleznik and co-authors have made it open source and freely available for anyone to use.

"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."

The team began by training the deep learning system on data from the Framingham Heart Study (FHS), a long-term asymptomatic community cohort study. Framingham 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 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). All told, the team validated the deep learning system in over 20,000 individuals.

Udo Hoffmann, MD, director of CIRC@MGH who is the principal investigator of CT imaging in the FHS, PROMISE and ROMICAT, emphasized 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 generalizability of these results to clinical settings.

The automated calcium scores from the deep learning system highly correlated with the manual calcium scores from human experts. The automated scores also independently predicted who would go on to have a major adverse cardiovascular event like a heart attack.

The coronary artery calcium score plays an important role in current guidelines for who should take a statin to prevent heart attacks. "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, 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."
-end-
Funding for this work was provided by the National Institutes of Health (NIH-USA U24CA194354, NIHUSA U01CA190234, NIH-USA U01CA209414, NIH-USA R35CA22052, 5R01-HL109711, NIH/NHLBI 5K24HL113128, NIH/NHLBI 5T32HL076136, NIH/NHLBI 5U01HL123339), the European Union--European Research Council (866504), as well as the German Research Foundation (1438/1-1, 6405/2-1), American Heart Association Institute for Precision Cardiovascular Medicine (18UNPG34030172), Fulbright Visiting Researcher Grant (E0583118), and a Rosztoczy Foundation Grant.

Paper cited: Zeleznik et al. "Deep convolutional neural networks to predict cardiovascular risk from computed tomography" Nature Communications DOI: 10.1038/s41467-021-20966-2

Brigham and Women's Hospital

Related Chest Pain Articles from Brightsurf:

New approach helps EMTs better assess chest pain en route to hospital
A study conducted at Wake Forest Baptist Health shows that on-scene use of a new protocol and advanced diagnostic equipment can help paramedics better identify patients at high risk for adverse cardiac events.

Brain activity during psychological stress may predict chest pain in people with heart disease
The brain's reaction to stress could be an important indicator of angina (chest pain) among people with known heart disease.

Chest pain, stress tests warrant attention even if arteries are clear
Patients who experience chest pain and have abnormal results on a cardiac stress test but who do not have blocked arteries often experience changes in their symptoms and stress test results over time, according to research presented at the American College of Cardiology's Annual Scientific Session Together with World Congress of Cardiology (ACC.20/WCC).

Women carry heavier burden of chest pain, but less artery narrowing
Women with coronary artery disease that reduces blood flow and oxygen to the heart muscle (ischemia) have significantly more chest pain caused by plaque build-up, yet less extensive disease as compared with men, according to new research presented at the American College of Cardiology's Annual Scientific Session Together with World Congress of Cardiology (ACC.20/WCC).

More isn't better when it comes to evaluating chest pain
New and more effective tests are needed to help predict heart attacks and other major cardiac events in patients with chest pain, the second most common reason for emergency department visits in the US.

Artificial intelligence could prevent unneeded tests in patients with stable chest pain
Artificial intelligence (AI) could prevent unnecessary diagnostic tests in patients with stable chest pain, according to research presented today at ICNC 2019.

Kaiser Permanente improves emergency care for patients with chest pain
Emergency physicians at Kaiser Permanente hospitals in Southern California reduced hospital admissions and cardiac stress testing by using new criteria to assess the level of risk patients with chest pain have for subsequent cardiac events.

Treatment for underdiagnosed cause of debilitating chest pain
Researchers find an effective way to treat an underdiagnosed condition that can cause heart attack and heart-attack-like symptoms.

Diagnostic protocol effective in identifying ED patients with acute chest pain
A relatively new accelerated diagnostic protocol is effective in identifying emergency department patients with acute chest pain who can be safely sent home without being hospitalized or undergoing comprehensive cardiac testing, according to researchers at Wake Forest Baptist Medical Center.

Chest pain drug falls short in preventing first episode of ventricular arrhythmia or death
A trial of more than 1,000 patients with implantable cardioverter defibrillators found that the drug ranolazine (used to treat chest pain; brand name Ranexa®) was safe but didn't decrease the likelihood of the first occurrence of ventricular arrhythmias or death in this high-risk population.

Read More: Chest Pain News and Chest Pain Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.