Mayo Clinic researchers announced on Mar. 30 that using artificial intelligence to measure fat around the heart can improve long-term cardiovascular disease risk prediction. The findings were presented at the 2026 American College of Cardiology Scientific Session and published in the American Journal of Preventive Cardiology.
Heart disease is a leading cause of death worldwide, making early identification of risk factors important for prevention. The study followed nearly 12,000 adults over about 16 years, applying AI to standard coronary artery calcium scans to measure pericardial fat. Researchers compared this new measurement with traditional assessment tools such as the American Heart Association PREVENT equation and the coronary artery calcium score.
Results showed that measuring heart fat could independently predict cardiovascular events and improved overall accuracy when combined with existing methods, particularly for patients considered low-risk by traditional measures. "Pericardial fat has been recognized as a marker of cardiovascular risk, but this study shows how we can now measure it automatically and use it to meaningfully improve risk prediction, especially in patients at borderline or intermediate risk where clinical decisions are often less clear," said Zahra Esmaeili, first author and researcher in Mayo Clinic's Department of Cardiovascular Medicine. "This opens the door to more personalized prevention strategies."
The research suggests that additional information can be extracted from routine imaging without extra tests or costs since coronary artery calcium scoring is already widely used for assessing cardiovascular risk. "Because this measurement comes from imaging that many patients are already receiving, it represents a practical and scalable way to enhance cardiovascular risk assessment," said Francisco Lopez-Jimenez, M.D., senior author and co-director of Mayo Clinic's AI in Cardiology program. "It could help clinicians intervene earlier and more effectively."
Researchers indicated further studies are needed to determine how best to include coronary fat measurements into regular clinical care and whether these results will influence treatment decisions.
