March 12, 2026European Heart Journal1 citations
View Full PaperArtificial intelligence–based quantification of breast arterial calcifications to predict cardiovascular morbidity and mortality
Key Result
AI-quantified breast arterial calcifications independently predict MACE and mortality, adding prognostic value to the PREVENT score during routine mammography screening.
Key Points
- The study aims to evaluate if AI-based quantification of breast arterial calcifications (BAC) can predict cardiovascular morbidity and mortality beyond existing risk scores.
- Retrospective cohort analysis of 123,762 women with screening mammograms from two healthcare systems.
- BAC quantified using a transformer-based neural network, categorized by severity.
- Kaplan-Meier and Cox proportional hazards models analyzed the association of BAC with major adverse cardiovascular events (MACE).
- BAC was detected in 16.1% of the internal cohort and 20.6% of the external cohort, showing significant prognostic value beyond the PREVENT score.
- Relative to zero BAC, mild, moderate, and severe BAC had hazard ratios indicating increased risk for MACE, with severe BAC having HR of 3.29 (95% CI 2.15-5.05).
- Each 1 mm2 increase in BAC correlated with an additional 2%-3% risk for MACE (P < .001).
Structured PICO
Does artificial intelligence-based quantification of breast arterial calcifications improve prediction of MACE and mortality beyond the PREVENT score in women undergoing routine mammography?
P
Population
Women undergoing routine mammography screening
I
Intervention
Artificial intelligence-based quantification of breast arterial calcifications (BAC)
C
Comparator
PREVENT score alone
O
Outcome
Major adverse cardiovascular events (MACE) and mortalityhard clinical
AI-based quantification of breast arterial calcifications during routine mammography provides opportunistic cardiovascular risk assessment, independently predicting MACE and mortality beyond the PREVENT score.
Main Result
Absolute Event Rate: 0% vs 0%
Abstract
BACKGROUND AND AIMS: Women are underdiagnosed and undertreated for cardiovascular disease (CVD). Automatic quantification of breast arterial calcification (BAC) on screening mammography can identify women at risk for CVD. This study aimed to determine whether artificial intelligence-based automatic quantification of BAC from screening mammograms predicts CVD and mortality beyond PREVENT scores in a large, racially diverse, multi-institutional population. METHODS: This retrospective cohort study included 123 762 women from two healthcare systems who had screening mammograms. Breast arterial calcification was quantified using a transformer-based neural network for segmentation. Breast arterial calcification severity was categorized as zero (0 mm2), mild (>0-10 mm2), moderate (>10-25 mm2), and severe (>25 mm2). Kaplan-Meier analysis, Cox proportional hazards, and Fine-Gray competing event models were used to examine the association between BAC and major adverse cardiovascular events (MACE). RESULTS: Breast arterial calcification was detected in 16.1% (internal cohort) and 20.6% (external cohort) of women and provided significant prognostic value incremental to the PREVENT score. In PREVENT adjusted models, a clear dose-response was observed. Compared with zero BAC, mild internal: hazard ratio (HR) 1.32, 95% confidence interval (CI) 1.10-1.59; external: HR 1.28, 95% CI 1.17-1.39, moderate (internal: HR 1.75, 95% CI 1.23-2.50; external: HR 1.79, 95% CI 1.55-2.06), and severe BAC (internal: HR 3.29, 95% CI 2.15-5.05; external: HR 2.80, 95% CI 2.36-3.32) were all prognostic for any MACE. Each 1 mm2 increase in BAC conferred an additional 2%-3% risk for MACE (P < .001). CONCLUSIONS: Automatically quantified BAC is an independent predictor of MACE and mortality, adding prognostic value to the PREVENT score. 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.
Expert Takes4 quotes
1/4
“Policymakers could consider integrating this into existing mammography programs, potentially reaching tens of millions of women annually without any additional infrastructure. The main steps needed are integrating the AI tool into existing imaging workflows and establishing clear guidelines for notifying patients and doctors.”
Hari Trivedi, Associate professor of radiology, Emory UniversityEmory Universityauto_pipelineView source