More than 600,000 cardiac arrests occur in the United States each year, and survival rates remain low both in and out of the hospital, according to the American Heart Association. A new research project funded by the Association will investigate whether artificial intelligence and multiple types of health data can help identify people whose risk of out-of-hospital cardiac arrest may be rising in the hours or days before it occurs.
The project, titled A Personalized and Scalable Early Warning System for Prediction of Imminent Out-of-Hospital Cardiac Arrest, is the newest scientific research grant awarded through the Cardiac Arrest Research Team (CART) Network, a collaboration between the American Heart Association and Heart & Stroke, the Heart and Stroke Foundation of Canada. The research will be conducted by a team from Cedars-Sinai Medical Center in Los Angeles, led by principal investigator Sumeet Chugh, M.D., vice-dean and chief AI health research officer, and co-principal investigator Kyndaron Reinier, M.P.H., Ph.D., a research associate professor.
Originally launched in June 2026, the CART Network was established to advance the prediction, detection, treatment of and recovery from cardiac arrest. The network brings together teams from both countries to share expertise, resources and approaches to accelerate scientific discoveries and translate findings into practice to improve survival and outcomes.
For this project, the California team will develop an early warning system designed to identify signs that may emerge in the hours or days before cardiac arrest. The system will combine multiple types of health information, including symptoms such as chest pain or trouble breathing, Fitbit activity tracker data, medical history, blood tests and electrocardiogram data. Artificial intelligence will be used to bring those clues together and update a person’s risk level in real time. The team will be known as The K. Scott Gordon Memorial Research Team for Cardiac Arrest Prediction and Prevention, made possible through a generous gift from a donor to the Association.
“This new project is intended to support a more personalized and scalable approach to identifying people whose risk of cardiac arrest may be increasing,” said Manesh R. Patel, M.D., FAHA, the American Heart Association's 2026-2027 volunteer president and chief of the division of cardiology at Duke University. “Cardiac arrest is a profound and tragic occurrence, and we know seconds matter in making sure people get the right lifesaving treatment at the right time. Our collaboration with the Heart and Stroke Foundation of Canada is an important step in our global work for a world of longer, healthier lives.”
The announcement matters because out-of-hospital cardiac arrest remains one of the most lethal cardiovascular events, and current tools cannot reliably flag imminent risk. An AI system that fuses wearable data, symptoms and clinical records could give patients and clinicians a critical window to intervene, potentially shifting survival curves. The project also signals a growing emphasis on personalized, data-driven prevention in cardiovascular medicine.
Funding scientific research through initiatives like this is a cornerstone of the American Heart Association’s mission. The Association has now funded more than $6.3 billion in cardiovascular, cerebrovascular and brain health research since 1949, making it the single largest non-profit, non-government supporter of heart and brain health research in the U.S. For more information about cardiac arrest, visit heart.org.
