February 10, 2026European Heart Journal
Artificial intelligence–based quantification of breast arterial calcifications to predict cardiovascular morbidity and mortality
Key result
Severe breast arterial calcification linked to ~3.3-fold higher MACE risk on screening mammography.
- HR 3.29
- 95% CI 2.15-5.05
- P<0.001
- n=123,762
Why the study?
Does AI-based automatic quantification of breast arterial calcification predict major adverse cardiovascular events and mortality beyond PREVENT scores in women undergoing screening mammography?
Key Points
- To determine whether artificial intelligence-based automatic quantification of breast arterial calcification from routine screening mammograms predicts cardiovascular disease and mortality beyond standard PREVENT scores.
- Analyzed a retrospective cohort of 123 762 women from two healthcare systems who underwent screening mammography, with a median follow-up of 7 years.
- Quantified breast arterial calcification using a transformer-based neural network segmentation model and categorized severity into zero (0 mm2), mild (>0-10 mm2), moderate (>10-25 mm2), and severe (>25 mm2).
- Evaluated associations with major adverse cardiovascular events (MACE) and mortality using Kaplan-Meier survival curves, multivariable Cox proportional hazards models, and Fine-Gray competing risk models.
- Breast arterial calcification was identified in 16.1% of women in the internal cohort and 20.6% in the external cohort, demonstrating incremental prognostic value over the PREVENT score.
- Compared with zero calcification, adjusted hazard ratios for MACE were 1.32 (95% CI 1.10-1.59) and 1.28 (95% CI 1.17-1.39) for mild, 1.75 (95% CI 1.23-2.50) and 1.79 (95% CI 1.55-2.06) for moderate, and 3.29 (95% CI 2.15-5.05) and 2.80 (95% CI 2.36-3.32) for severe calcification across internal and external cohorts, respectively.
- Each 1 mm2 increase in breast arterial calcification area independently conferred an additional 2%-3% increased risk for MACE (P < .001).
Study Design
Type
Cohort (n=123,762)
Multicenter
Yes
Structured PICO
Does AI-based automatic quantification of breast arterial calcification predict major adverse cardiovascular events and mortality beyond PREVENT scores in women undergoing screening mammography?
P
Population
123,762 women aged 40-79 years without prior cardiovascular disease who underwent screening mammography, followed for a median of 7 years.
E
Exposure
Artificial intelligence-based automatic quantification of breast arterial calcification (BAC) severity (mild, moderate, severe) from routine screening mammograms using a transformer-based neural network.
C
Comparator
Zero BAC (0 mm2) and established clinical risk scores (PREVENT score).
O
Outcome
Major adverse cardiovascular events (MACE) and all-cause mortality over a median follow-up of 7 years.hard clinical
Main Result
Hazard Ratio: 3.29 (95% CI 2.15–5.05)
Absolute Event Rate: 48.89% vs 9.58%
p-value: p=<0.001
Automatically quantified breast arterial calcification from routine screening mammograms is an independent predictor of MACE and mortality that adds incremental prognostic value to established clinical risk models like the PREVENT score.
Limitations
- Retrospective observational study design cannot establish causality.
- Evaluation of BAC's additive value with PREVENT scores was limited to a smaller subset of the population due to missing data, potentially introducing selection bias.
- Limited representation of Asian, Hispanic, and Native American patients, which may affect generalizability.
- Potential misclassification of events due to reliance on EHR ICD codes for major adverse cardiovascular events.
- Missing data on important potential confounders such as menopause status, reproductive history, and social deprivation index.
- The AI model currently functions on full-field digital mammography and requires adaptation for digital breast tomosynthesis (DBT).
Key expert perspectives
Captured external expert commentary on this paper, strongest first. Original sources are linked where available.
“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.”
“Women are very under-screened and under-detected for cardiovascular disease.”
“We see an opportunity for women to get screened for cancer and also additionally get a cardiovascular screen from their mammograms. Our study showed that breast arterial calcification is a good predictor for cardiovascular disease, especially in patients younger than age 60. If we are able to screen and identify these patients early, we can refer them to a cardiologist for further risk assessment.”
Implication
Should not yet change practice in mammography screening; leaves open whether BAC quantification improves outcomes beyond PREVENT in prospective trials.
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.
Discussion
No takes yet. Share an insight, caveat, or question.
Cite This Study
Dapamede et al. (2026) conducted a cohort in Cardiovascular risk in women (asymptomatic) (n=123,762). Severe breast arterial calcification (>25 mm2) vs. Zero breast arterial calcification (0 mm2) was evaluated on Major adverse cardiovascular events (MACE) (HR 3.29, 95% CI 2.15-5.05, p=<0.001). Automatically quantified severe breast arterial calcification on screening mammography was associated with a significantly increased risk of major adverse cardiovascular events (HR 3.29) compared to zero calcification, adding prognostic value to the PREVENT score.