Routine Mammograms That Also Flag CVD: Two Birds With One Stone?

With the help of artificial intelligence (AI), routine screening mammograms could identify women at higher cardiovascular risk, a retrospective cohort study suggested.

A greater amount of AI-calculated breast arterial calcification (BAC) on imaging was associated with an increased risk of major adverse cardiovascular events (MACE) in both internal and external validation cohorts. For example, in the older, higher-risk external validation cohort, women who had progressed beyond zero BAC had greater risks of MACE over a median 7 years of follow-up:

• Mild BAC (>0-10 mm²): adjusted HR 1.28 (95% CI 1.17-1.39)
• Moderate BAC (>10-25 mm²): adjusted HR 1.79 (95% CI 1.55-2.06)
• Severe BAC (>25 mm²): adjusted HR 2.80 (95% CI 2.36-3.32)

“Our study demonstrates that an automated, AI-driven quantification of BAC on routine screening mammograms is a strong, independent predictor of adverse cardiovascular events in a large, multiracial population,” Hari Trivedi, MD, of Emory University in Atlanta, and colleagues wrote in the European Heart Journal.

“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,” they concluded.

Trivedi and team reported that each 1-mm² increase in BAC indicated an additional, significant 2%-3% increased risk of MACE. Findings were significant across all age groups, including women under age 50, and were independent of traditional risk factors and the PREVENT risk score, which was recently promoted as a general-purpose cardiovascular risk stratification tool.

“It is important to note that BAC quantification is not intended to replace comprehensive risk models like PREVENT,” the authors explained. “Rather, BAC may function as a powerful opportunistic identifier of at-risk patients who may otherwise be overlooked and drive formal cardiovascular risk assessment by their primary care physician.”

“For women, this means a mammogram you’re already having could also provide important information about your heart health — prompting a conversation with your doctor about preventive steps such as cholesterol testing or medication,” said Trivedi in a press release. “For clinicians, it offers a practical way to identify women at cardiovascular risk who are currently being missed.”

An opportunistic screen is appealing, since cardiovascular disease (CVD) — the leading cause of death in the U.S. — is consistently underdiagnosed and undertreated in women. The use of mammograms for the early detection of breast cancer approaches 70% in women over 40.

In practice, a finding of BAC on mammography should trigger CVD risk factor optimization and heart failure prevention in parallel, suggested Lori Daniels, MD, of the University of California San Diego, in an accompanying editorial.

She emphasized the link between BAC and heart failure in particular.

“Importantly, BAC is not merely a surrogate for coronary artery calcification,” she wrote. “While correlated, the two differ pathologically. BAC, present predominantly in the arterial media, reflects vascular ageing and arterial stiffness.”

“This distinction matters clinically because these same comorbidities are strongly linked to ventricular stiffening and, ultimately, incident heart failure — particularly heart failure with preserved ejection fraction,” she added.

For their retrospective study, Trivedi and colleagues included women from two healthcare systems who underwent screening mammography: an internal validation cohort from Emory Healthcare (n=74,124; mean age 55.5 years) and an external validation cohort from the Mayo Clinic (n=49,638; mean age 59.5 years).

MACE and PREVENT risk variables were extracted from electronic health records. MACE events included acute myocardial infarction, stroke, heart failure, and all-cause death.

The BAC analysis included both left and right breasts, but only the side with the maximum BAC detected was used as the final BAC result for each patient. BAC was ultimately detected in 16.1% (internal cohort) and 20.6% (external cohort) of study participants.

“We designed our study to validate the prognostic value of the BAC quantification across different populations, in contrast to developing a single, comprehensive risk model at one site that was externally validated at a second site,” the authors noted. “In other words, our goal was not to create a ‘best fit’ risk model that generalizes across populations, but rather to demonstrate the additive value of BAC as an independent predictor even in populations with differing baseline risk.”

“The challenge of developing a universal risk model is reflected in data demonstrating that the atherosclerotic CVD and PREVENT risk calculators do not generalize well to certain populations,” they added.

Of note, the study was fairly racially diverse, but was still limited in Asian, Hispanic, and Native American representation.

Additionally, the amount of missing data on risk factors made it hard to say how much the AI-BAC approach adds to risk stratification, Trivedi and colleagues cautioned.

Nevertheless, as a whole, the literature linking BAC to incident CVD is “mounting,” Daniels noted.

“A key contribution of this work is its practical, intuitive reporting metric: BAC quantified as an area (mm²) analogous in spirit to a standardized ‘Agatston-like’ construct for mammography,” she wrote. “This is not merely aesthetic. A physical unit has the potential to accelerate standardization across vendors, facilitate reproducible thresholds, and enable implementation workflows.”

“Regardless of the reporting metric ultimately adopted, it is time to shift BAC from observation to implementation, leveraging a touchpoint women already trust, to advance prevention for what remains the leading cause of death among women,” she concluded.