BOSTON – Atrial fibrillation, an irregular and often rapid heart rate, is a common condition that often leads to clots in the heart that can travel to the brain to cause a stroke. As described in a study Posted in Circulation, a team led by researchers at Massachusetts General Hospital (MGH) and the Broad Institute at MIT and Harvard developed an artificial intelligence-based method to identify patients at risk of developing atrial fibrillation and who might therefore benefit from preventive measures.
Researchers developed the artificial intelligence-based method to predict the risk of atrial fibrillation over the next five years based on EKG results (non-invasive tests that record electrical signals from the heart) in 45,770 patients receiving primary care at the MGH.
Next, the scientists applied their method to three large datasets from studies comprising a total of 83,162 individuals. The AI-based method predicted the risk of atrial fibrillation on its own and was synergistic when combined with clinical risk factors known to predict atrial fibrillation. The method was also highly predictive in subsets of individuals such as those with previous heart failure or stroke.
“We see a role for EKG-based artificial intelligence algorithms to help identify those most at risk for atrial fibrillation,” says lead author Steven A. Lubitz, MD, MPH, cardiac electrophysiologist at MGH and associate member at the Broad Institut. Co-lead author Shaan Khurshid, MD, MPH, researcher in electrophysiology and researcher at MGH, adds co-lead author: “The application of such algorithms could prompt clinicians to modify important risk factors for fibrillation. little finger, which could completely reduce the risk of developing the disease.
Lubitz adds that the algorithm could serve as a pre-screening tool for patients who may currently have undetected atrial fibrillation, prompting clinicians to look for atrial fibrillation using longer-term heart rate monitors, which in turn could lead to stroke prevention measures. .
The study results also demonstrate the potential power of AI, which in this case involves a specific type called machine learning, to advance medicine. “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 improving patient care. cardiology, ”said co-author Anthony Philippakis, MD, PhD, chief data officer. at Broad and co-director of the institute’s Eric and Wendy Schmidt Center. “As a data scientist and former cardiologist, I am excited to see how machine learning-based methods can work with the tests and clinical approaches we use daily to help us improve risk prediction and take into account supports patients with atrial fibrillation. “
Lubitz is an associate professor of medicine at Harvard Medical School. Co-authors include Samuel Friedman, PhD, Christopher Reeder, PhD, Paolo Di Achille, PhD, Nathaniel Diamant, BS, Pulkit Singh, BS, Lia X. Harrington, PhD, Xin Wang, MBBS, MPH, Mostafa A. Al- Alusi, MD, Gopal Sarma, MD, PhD, Andrea S. Foulkes, ScD, Patrick T. Ellinor, MD, PhD, Christopher D. Anderson, MD, MMSc, Jennifer E. Ho, MD, and Puneet Batra, PhD .
This work was supported by the National Institutes of Health, the American Heart Association, the Doris Duke Foundation, and the Leducq Foundation.
About Massachusetts General Hospital
Massachusetts General Hospital, founded in 1811, is Harvard Medical School’s first and largest teaching hospital. The Institute for General Mass Research leads the largest hospital-based research program in the country, with annual research operations of over $ 1 billion, and includes more than 9,500 researchers working in more than 30 institutes, centers and departments. In August 2021, Mass General was named # 5 in the American News and World Report list of “America’s best hospitals”.
About the Broad Institute at MIT and Harvard
The Broad Institute at MIT and Harvard was launched in 2004 to empower this generation of creative scientists to transform medicine. The Broad Institute seeks to describe the molecular components of life and their connections; discover the molecular basis of the main human diseases; develop new effective approaches for diagnosis and therapy; and disseminate findings, tools, methods and data openly to the entire scientific community.
Founded by MIT, Harvard, Harvard Affiliated Hospitals, and visionary Los Angeles philanthropists Eli and Edythe L. Broad, the Broad Institute includes professors, professional staff, and students from the biomedical research communities of MIT and Harvard and beyond that, with collaborations covering more than a hundred private and public institutions in more than 40 countries around the world.
Computer simulation / modeling
The title of the article
Deep Learning and EKG-Based Clinical Risk Factors to Predict Atrial Fibrillation
Publication date of the article
Dr Lubitz receives sponsored research support from Bristol Myers Squibb / Pfizer, Bayer AG, Boehringer Ingelheim, Fitbit and IBM, and has been a consultant for Bristol Myers Squibb / Pfizer, Bayer AG and Blackstone Life Sciences. Dr Ellinor receives research support sponsored by Bayer AG and IBM, and has been a consultant for Novartis, MyoKardia and Bayer AG. Dr Ho received sponsored research support from Bayer AG and research supplies from EcoNugenics, Inc. Dr Batra received sponsored research support from Bayer AG and IBM, and was a consultant for Novartis and Prometheus Biosciences. Dr Anderson receives research support sponsored by Bayer AG and has been a consultant for ApoPharma.
Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of any press releases posted on EurekAlert! by contributing institutions or for the use of any information via the EurekAlert system.