Breast cancer screening could serve as a tool to detect cardiovascular disease.
This is according to research published in the European Heart Journal that suggests AI analysis of mammograms can predict the risk of serious or fatal heart disease.
The study demonstrates that AI can evaluate calcium deposits in breast arteries from routine X-ray mammography scans used in breast cancer screening.
Researchers suggest this method could assist the many women with undiagnosed and untreated cardiovascular disease.
Led by Dr Hari Trivedi from Emory University, Atlanta, US, the team said: ‘Heart disease is the leading cause of death in women worldwide, yet women are consistently underdiagnosed and undertreated compared to men. Mammograms, which women already attend for breast cancer screening, can also detect calcium deposits in breast arteries, linked to heart disease. We aimed to test whether AI could identify women at risk of cardiovascular disease without any added cost or inconvenience.’
The study involved 123,762 women who had participated in breast screening and had no known cardiovascular disease.
AI was used to analyse the level of calcium deposits in the arteries of the breast tissue.
This ‘arterial calcification’ signals artery hardening and indicates an increased risk of conditions such as heart attack, heart failure, stroke, and death. The calcium deposit levels were categorised as severe, moderate, mild or absent.
Researchers compared this categorisation with information on whether the women developed serious cardiovascular events, including stroke, heart attack, or death from cardiovascular causes.
They discovered that women with mild calcification had approximately a 30% higher chance of experiencing serious cardiovascular disease compared to women with no calcification. In women with moderate calcification, the risk increased by more than 70%, and in those with severe calcification, it was two to three times higher.
Dr Trivedi explained: ‘We found that the more calcium visible in the breast arteries on a mammogram, the greater a woman's risk of serious heart events such as a heart attack, stroke, or heart failure. This was true even for women under 50 – a group often considered low-risk – and remained significant after adjusting for other risk factors like diabetes and smoking. This is the largest study of its kind, spanning multiple racial groups and drawing on data from two major US health systems.
‘For women, this could mean that a mammogram they are already getting may also offer vital information about heart health, encouraging discussions with their doctor about preventive measures such as cholesterol testing or medication. For clinicians, it provides a practical approach to identifying women at risk of cardiovascular disease who might otherwise be missed.
‘Policymakers could consider integrating this into existing mammography programmes, potentially reaching tens of millions of women each year without requiring extra infrastructure. The main steps involve adding the AI tool into current imaging workflows and establishing clear guidelines for informing patients and healthcare providers. We are now planning a clinical trial to test these procedures.’
The authors conclude: ’This approach may provide an opportunistic cardiovascular risk assessment during routine mammography screening without additional radiation exposure to guide earlier and more effective preventive care for women’.
