NextFin news, Researchers in Australia developed and tested a deep learning artificial intelligence (AI) algorithm that predicts the risk of major cardiovascular diseases such as heart attacks and strokes by analyzing routine mammogram images. The study was published this Tuesday in the journal Heart.
The AI model was trained on mammogram images from 49,196 women enrolled in the Lifepool cohort registry, an Australian breast cancer research initiative. The average age of participants was 59, with about one-third taking medication for high cholesterol and 27% for high blood pressure.
The research was conducted in Victoria, Australia, where mammograms are routinely performed for breast cancer screening. The AI algorithm leverages mammographic features, including breast arterial calcification and tissue density, which are associated with cardiovascular risk, combined with patient age to predict cardiovascular events over a 10-year period.
During an average follow-up period of nearly nine years, 2,383 women experienced a heart attack, 731 had heart failure, and 656 suffered a stroke. The AI algorithm's predictive performance was comparable to traditional cardiovascular risk calculators that use age and clinical variables.
Researchers highlighted that many women undergo mammography screening in midlife, coinciding with an increased risk of cardiovascular disease. They emphasized that this AI technology could provide a cost-effective, dual-purpose screening tool to identify risks for both breast cancer and cardiovascular disease, potentially broadening cardiovascular risk screening coverage among women.
The study authors stated, "A deep learning algorithm utilizing routine mammograms and age shows promise as a cardiovascular risk prediction tool. Mammography may offer a cost-effective ‘two for one’ opportunity to screen women for both breast cancer and cardiovascular risk, enabling broader cardiovascular risk screening for women than is currently achieved."
The Lifepool cohort registry, which supported this research, was established by the Peter MacCallum Cancer Centre in collaboration with the University of Melbourne and Royal Melbourne Hospital. It has enrolled over 54,000 women across metropolitan and rural Australia since 2009, providing a valuable resource for longitudinal breast health and cardiovascular research.
This advancement addresses a critical gap in women's health, as cardiovascular disease remains a leading cause of mortality among women worldwide, often underdiagnosed compared to men. By integrating cardiovascular risk assessment into routine breast cancer screening, the AI tool could enhance early detection and prevention efforts without requiring additional clinical visits or tests.
Explore more exclusive insights at nextfin.ai.