Artificial intelligence (AI) can identify patients at risk of developing atrial fibrillation (AF) within the next five years, according to a recent study.
AF, where the heart beats irregularly and abnormally fast, is a leading cause of stroke around the world.
The study, led by researchers at Harvard-affiliated Massachusetts General Hospital and the Broad Institute of MIT and Harvard, was published in the journal Circulation.
The research team trained the AI using 12-lead electrocardiograms (ECGs) to predict AF risk in 45,770 patients receiving primary care at Massachusetts General Hospital.
The scientists then applied their method to three large data sets totalling 83,162 individuals.
The pool included one internal test set and external test sets from Brigham and Women’s Hospital and UK Biobank.
The AI method successfully predicted five-year AF risk on its own and was syngergistic when combined with known clinical factors for predicting AF risk.
The method was also highly predictive in groups who had previously had a stroke.
Senior author Steven A. Lubitz said: “We see a role for electrocardiogram-based artificial intelligence algorithms to assist with the identification of individuals at greatest risk for atrial fibrillation.”
The algorithm could be used to screen patients for AF and lead to new stroke prevention measures, Lubitz added.
Co-author Anthony Philippakis, chief data officer at the Broad and co-director of the institute’s Eric and Wendy Schmidt Center, said:
“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.
“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.”
People with AF are five times more likely than the rest of the population to have a stroke.
AF contributes to around a fifth of strokes in the UK, according to the Stroke Association.
