A novelartificial intelligence(AI) algorithm using only routine mammogram images and age can predict a woman's risk of major cardiovascular disease as accurately as standard clinical tools, according to a new study published online in the journal Heart. The research suggests that mammography, traditionally used to detectbreast cancercould serve as a cost-effective “two-for-one” screening tool to also assessheart diseaserisk in women. Cardiovascular disease (CVD) remains underdiagnosed and undertreated in women, in part because traditional risk assessment models often perform poorly in female populations. While newer algorithms have improved accuracy, they typically rely on detailed clinical data, which is not always readily available. The study analyzed data from 49,196 women, with an average age of 59, who were part of the Lifepool cohort registry in Australia, between 2009 and 2020. At the time of enrollment, participants provided basic health data, including lifestyle factors, menopausal status, and medical history. Over an average follow-up period of nearly nine years, 3,392 women experienced a major cardiovascular event such as coronary artery disease,heart attack,stroke, or heart failure. The researchers developed an AI model that analyzed mammogram images alongside age to predict 10-year CVD risk. The algorithm performed as well as established clinical tools like the New Zealand PREDICT tool and the American Heart Association’s PREVENT calculator. Adding clinical factors to the AI model resulted in only a slight performance improvement. “A key advantage of the mammography model we developed is that it did not require additional history taking or medical record data and leveraged an existing risk screening process widely used by women,” the researchers noted. While challenges in implementation remain, the study presents a promising step toward more holistic preventive care through existing screening infrastructure. Reference:Predicting cardiovascular events from routine mammograms using machine learning. Heart. doi.org/10.1136/heartjnl-2025-325705