THURSDAY, March 12, 2026 (HealthDay News) -- Breast arterial calcification (BAC) on screening mammograms is an independent predictor of major adverse cardiovascular events (MACE) and mortality, according to a study published online March 9 in the European Heart Journal.
Theodorus Dapamede, M.D., Ph.D., from Emory University in Atlanta, and colleagues examined whether artificial intelligence (AI)-based automatic quantification of BAC from screening mammograms predicts cardiovascular disease (CVD) and mortality beyond PREVENT scores in a retrospective cohort study involving 123,762 women from two health care systems with screening mammograms. A transformer-based neural network for segmentation was used to quantify BAC. The severity of BAC was categorized as zero, mild, moderate, or severe (0, >0 to 10, >10 to 25, and >25 mm2, respectively).
The researchers found that BAC was detected in 16.1 and 20.6 percent of women in an internal and external cohort, respectively, and provided significant prognostic value in addition to the PREVENT score. In models adjusted for PREVENT, there was a clear dose response. Mild, moderate, and severe BAC were all prognostic for any MACE compared with zero BAC (internal hazard ratios, 1.32, 1.75, and 3.29, respectively; external hazard ratios, 1.28, 1.79, and 2.80, respectively). An additional 2 to 3 percent risk for MACE was conferred by each 1-mm2 increase in BAC.
"Policymakers could consider integrating this into existing mammography programs, potentially reaching tens of millions of women annually without any additional infrastructure," lead author Hari Trivedi, M.D., also from Emory University, said in a statement. "The main steps needed are integrating the AI tool into existing imaging workflows and establishing clear guidelines for notifying patients and doctors."