AI-Powered Mammography Expands Beyond Cancer Detection to Predict Cardiovascular Risk
Key Insights
AI model quantifies breast arterial calcifications (search) on routine mammograms, correlating severity with up to eightfold increased cardiovascular event risk.
DeepHealth (search) receives FDA clearance for automated BAC detection, enabling opportunistic heart disease screening without additional radiation, time, or cost.
Severe BAC levels linked to fourfold to eightfold increases in heart attack and stroke; BAC under age 50 signals elevated 10-year cardiovascular risk.
A routine mammogram—long established as a cornerstone of breast cancer screening—may soon double as a powerful predictor of cardiovascular disease (search) risk, thanks to advances in artificial intelligence. Researchers have developed an AI model that scans mammograms to quantify breast arterial calcifications (search) (BAC), bright streaks of calcium buildup that signal stiffened breast artery tissues and, by extension, heightened heart disease risk. The findings, published in the European Heart Journal, arrive alongside FDA clearance for DeepHealth (search)'s automated BAC detection technology, marking a significant step toward integrating cardiovascular risk assessment into standard mammography workflows.
From Incidental Finding to Quantifiable Risk Marker
Breast arterial calcifications (search) appear on mammograms as distinctive "railroad-track" stripes zigzagging through breast tissue—strikingly different from the small clusters of calcium deposits that can indicate early breast cancer. BAC itself does not harm breast tissue or increase breast cancer risk, but it may signify that calcification is developing elsewhere in the body, stiffening vessels and impairing circulation.
"Other research groups have investigated using mammograms to assess heart disease risk, and some radiologists look out for BAC during screenings," said study co-author Hari Trivedi, an Emory University radiologist. "But our model offers the first way to measure and track the amount of BAC and tie that amount to higher disease risk."
The model can be deployed on every mammogram without additional work—a critical advantage given that more than 40 million mammograms are conducted annually in the United States.
Quantifying Risk Across Two Large Cohorts
Trivedi's team analyzed mammograms from two populations: 74,124 individuals at Emory Healthcare in Atlanta and 49,638 individuals at Mayo Clinic sites across Arizona, Florida, Minnesota, and the upper Midwest. The results revealed a clear dose-response relationship: even small increases in BAC correlated with slightly raised cardiovascular risk, while severe levels of BAC were associated with fourfold to eightfold increases in events such as heart attack and stroke compared with those who have no calcification.
The clinical implications are particularly striking for younger women. "If you have BAC and are under 50, you are at a higher risk of a cardiovascular event within the next 10 years," Trivedi noted.
FDA Clearance and Clinical Integration
DeepHealth (search) has now received FDA clearance for automated BAC detection on routine screening mammograms. Matthew Kurian, Assistant Professor of Medicine at the University of Kentucky College of Medicine, emphasized the broader significance: large meta-analyses show BAC is associated with approximately twofold higher risk of future cardiovascular events, roughly fourfold higher odds of coronary artery disease (search), and elevated risks of stroke, heart failure, cardiac death, and all-cause mortality.
"AI-quantified BAC adds cardiovascular risk information beyond traditional risk calculators, with higher BAC burden linked to progressively higher rates of major adverse cardiovascular events," Kurian stated.
Reducing Radiologist Burden and Improving Outcomes
The automated approach could also alleviate pressure on radiologists. Laurie Margolies, a breast imaging specialist at Mount Sinai (search) in New York City who was not involved in the study, noted that the model helps "take the burden off the radiologist" to spot BAC and choose to evaluate and report risk. Margolies and colleagues are currently studying whether people will pursue cardiovascular care if a BAC assessment is included with mammogram results—and, critically, whether heart health outcomes improve as a result.
Mary Ann McLaughlin, a cardiologist at Mount Sinai (search), underscored the population-level potential: given how many people get mammograms, "a lot of people could really benefit from this."
One Exam, Two Diseases
Widespread routine mammography has helped dramatically reduce breast cancer deaths in the U.S., with screening recommended for most women every other year beginning at age 40. The dual-purpose approach is particularly compelling because it requires no additional radiation, no extra time, and no separate appointment.
"You come looking for breast cancer, but you also get this information," Margolies said. "It's no extra radiation; it's no extra time. It's not another appointment. It's on your regular, routine mammogram."
As Kurian summarized: "One mammogram. Two major diseases. Countless opportunities to improve women's health and slow the leading cause of death amongst women in the United States."