Mayo Clinic research has identified a powerful new way to improve predictions of a patient’s long-term cardiovascular disease risk by enhancing routine imaging tests with artificial intelligence (AI). Heart disease develops over time and remains the leading cause of death worldwide, so identifying risks early is important to prevent heart attacks, strokes, and other serious consequences.
This study highlights the growing role of AI in helping experts discover new insights from existing medical data. The findings were presented at the 2026 American College of Cardiology Scientific Sessions and published concurrently. American Journal of Preventive Cardiology.
The study followed approximately 12,000 adults for approximately 16 years. The researchers applied AI to participants’ standard coronary artery calcium scans to measure fat around the heart. They compared the predictive value of this measure in conjunction with two standard risk assessment approaches. The American Heart Association’s PREVENT equation, which incorporates traditional factors such as age, gender, blood pressure, cholesterol, diabetes, and other variables, and the Coronary Calcium Score, which measures calcified plaque within the coronary arteries.
The results of this study demonstrate that cardiac fat volume can be independently used to predict cardiovascular events. When combined with the coronary artery calcium score and the PREVENT equation, the overall accuracy of long-term risk prediction was significantly improved, especially in patients in the low-risk category.
“Pericardial fat has long been recognized as a marker of cardiovascular risk, and this study shows how pericardial fat can be automatically measured and used to meaningfully improve risk prediction, particularly in patients at borderline or intermediate risk, where clinical judgment is often unclear,” said lead author and researcher Zahra Esmaili, of Mayo Clinic’s Department of Cardiovascular Medicine. “This opens the door to more individualized prevention strategies.”
Key findings:
- Almost 10% of participants developed cardiovascular disease during follow-up.
- Even after accounting for traditional risk factors and coronary artery calcium scores, increased circumcardial fat mass was independently associated with increased risk of cardiovascular events.
- Participants with the highest coronary artery fat mass had increased risk across all coronary artery calcium levels.
- Adding coronary artery fat measurements improved the accuracy of predicting cardiovascular events over established models.
Coronary artery calcium scores are widely used to assess cardiovascular risk. This study shows that additional information can be extracted from the same scan without additional testing or cost.
“This measurement is derived from the imaging that many patients already undergo, making it a practical and scalable way to enhance cardiovascular risk assessment,” said Francisco López Jiménez, MD, preventive cardiologist, co-director of Mayo Clinic’s AI in Cardiology program, and senior author. “It could help clinicians intervene earlier and more effectively.”
The researchers note that further research will help determine how best to incorporate coronary artery fat measurements into routine clinical care and whether it can guide treatment decisions.
The paper, “Deep Learning–Derived Pericardial Adipose Tissue by ECG-Gated Computer Tomography Predicts Cardiovascular Events Beyond Coronary Calcium,” has a full list of authors published in the American Journal of Preventive Cardiology.
This article has been reprinted from the following material: Note: Materials may be edited for length and content. Please contact the citation source for details. You can access our press release publishing policy here.
