AI Predicts Heart Disease Risk From Mammograms

A groundbreaking study published in the European Heart Journal on March 9, 2026, has demonstrated that artificial intelligence (AI) can predict the risk of serious heart disease from mammograms. The research showcases a method where AI analyzes mammography images, already widely used for breast cancer screening, to quantify calcification in the breast arteries, thereby predicting the risk of future cardiovascular events such as heart attacks and strokes.

The study was led by a team of researchers headed by Dr. Hari Trivedi from Emory University in Atlanta, USA. The researchers utilized AI to analyze the mammograms of 123,762 women with no prior history of cardiovascular disease. The AI quantified the amount of breast arterial calcification (BAC) and categorized it as severe, moderate, mild, or absent. The women were then followed to track the incidence of subsequent cardiovascular disease.

The findings revealed a strong correlation between the degree of calcification and cardiovascular risk. Compared to women with no calcification, those with mild calcification had an approximately 30% higher risk of serious cardiovascular disease. The risk was over 70% higher for women with moderate calcification, and two to three times higher for those with severe calcification. This association held true even in younger women under 50, a group often considered low-risk, and remained a significant predictor after accounting for other risk factors like diabetes and smoking.

Dr. Trivedi stated, "We found that the more calcium visible in the breast arteries on a mammogram, the higher a woman's risk of a serious heart event such as a heart attack, stroke or heart failure. For women, this means a mammogram you're already having could also provide important information about your heart health - prompting a conversation with your doctor about preventive steps."

The primary advantage of this approach is its ability to screen for cardiovascular risk within the existing breast cancer screening framework, incurring no additional cost, examination time, or radiation exposure. The research team is now planning a clinical trial to integrate the AI tool into clinical workflows and establish clear guidelines for patient and physician notification. This technology holds the promise of significantly improving early detection and prevention of cardiovascular disease for millions of women worldwide.