AI Promotes Preventive Care For At-Risk Atrial Fibrillation Patients

Massachusetts General Hospital, the Broad Institute of MIT, and Harvard researchers created an artificial intelligence-based approach to identifying patients at risk of developing atrial fibrillation, promoting prevention care.

Atrial fibrillation is a common condition that can cause clots in the heart that can then travel to the brain and lead to a stroke. The research team created the artificial intelligence-based method to predict the risk of atrial fibrillation within the next five years based on data from electrocardiograms in 45,770 patients receiving primary care at MGH.

The researchers then applied the method to three different datasets from studies featuring a total of 83,162 individuals. The AI-based method determined atrial fibrillation risk on its own and was synergistic when combined with known clinical risk factors for predicting atrial fibrillation. The method was also highly predictive in individuals with prior heart failure or stroke.

“We see a role for electrocardiogram-based artificial intelligence algorithms to assist with the identification of individuals at greatest risk for atrial fibrillation,” senior author, a cardiac electrophysiologist at MGH, and associate member at the Broad Institute, Steven A. Lubitz, MD, MPH, said in a press release.

Co-lead author and electrophysiology clinical and research fellow at MGH, Shaan Khurshid, MD, MPH, also added, “The application of such algorithms could prompt clinicians to modify important risk factors for atrial fibrillation that may reduce the risk of developing the disease altogether.”

According to Lubitz, the algorithm could act as a pre-screening tool for patients who may currently experience undetected atrial fibrillation, promoting stroke prevention measures. The study also demonstrated artificial intelligence’s ability to improve medical practices.

 “With the explosion of data science technologies and the vast amounts of clinical data now available, machine learning is poised to help clinicians and researchers make great strides in enhancing cardiology care,” co-author Anthony Philippakis, MD, PhD, chief data officer at the Broad and co-director of the institute’s Eric and Wendy Schmidt Center.

“As a data scientist and former cardiologist, I’m excited to see how machine learning-based methods can work with the tests and clinical approaches we use every day to help us improve risk prediction and take care of patients with atrial fibrillation.”

With the use of artificial intelligence, researchers can identify high-risk patients and promotive prevention care methods to improve the overall patient outcome.

The study’s work was supported by the National Institutes of Health, the American Heart Association, the Doris Duke Foundation, and the Leducq Foundation.