Researchers at the Mayo Clinic in Rochester have just announced the results of a new study which used Artificial Intelligence to predict heart disease.
When you think of fat, most of us look at our bodies and how much we weigh. But there is also "fat" around the heart, and that can be a sign of heart disease.
"It is very important to know who is going to develop heart disease in the future," says Mayo Clinic cardiologist, Dr. Francisco Lopez-Jimenez.
He says they have now used artificial intelligence to measure fat around the heart, and found that the more fat, the higher the risk.
However, a person's physical weight didn't match up with their heart fat.
"So a person might be very thin and have a lot of fat around the heart and vice versa," explains Lopez-Jimenez. "A person might be significantly overweight and have little or no fat around the heart."
He says heart disease develops over time and remains the leading cause of death worldwide, so identifying risk early is critical to preventing heart attack, stroke and other serious outcomes.
"The most important piece of information we get from this is that by knowing who is at the higher risk for heart attacks and strokes, then we can target preventive therapies to those individuals," Dr. Lopez-Jimenez adds. "And when we target those individuals at the highest risk, we know that people are more likely and more willing to change behavior, to undergo therapies that reduce heart disease risk. And also, those therapies become more cost effective because we are targeting those at the highest risk."
The study followed nearly 12,000 adults for approximately 16 years. Lopez-Jimenz says artificial intelligence played a critical role.
"Well, AI was critical for us to, do the measurement of the fat around the heart because fat around the heart cannot be measured very easily," he adds. "It will take about half an hour to one hour for a technician or a doctor to measure the amount of fat if this is done manually. Now, because for this research study, we have done this in thousands and thousands of scans. We have to create a system using artificial intelligence to measure the fat within a fraction of a second for each study."
The findings were presented in the 2026 American College of Cardiology Scientific Session with simultaneous publications in the American Journal of Preventative Cardiology.
Key findings:
- Nearly 10% of participants developed cardiovascular disease during follow-up.
- Higher fat volume around the heart was independently associated with increased risk of cardiovascular events, even after accounting for traditional risk factors and coronary calcium scores.
- Participants with the highest coronary fat volume had elevated risk across all coronary calcium levels.
- Adding coronary fat measurements improved the accuracy of predicting cardiovascular events beyond established models.
Coronary artery calcium scoring is widely used to assess cardiovascular risk. This study shows that additional information can be extracted from the same scan without extra testing or cost.
"Because this measurement comes from imaging that many patients are already receiving, it represents a practical and scalable way to enhance cardiovascular risk assessment," says Lopez-Jimenez. "It could help clinicians intervene earlier and more effectively."
Researchers note that further studies will help determine how best to incorporate coronary fat measurement into routine clinical care and whether it can guide treatment decisions.
