An Australian study suggests an artificial intelligence system trained on routine mammogram images could help identify cardiovascular risk in women. The researchers say the approach could provide a cost-effective, two-for-one screening option for both breast cancer and heart disease. In the UK, women aged 50 to 71 are invited for breast screening every three years, with two X-ray images taken at each appointment.

Data for the study came from Lifepool, an Australian breast cancer research initiative, comprising 49,196 women. The average age was 59; around a third were taking cholesterol-lowering medication and 27% had high blood pressure. The researchers set out to predict the risk of major cardiovascular disease over 10 years and developed a deep learning model based on routine mammography images. They said: “Many women undergo screening mammography in midlife when the risk of cardiovascular disease rises.” “Mammographic features such as breast arterial calcification and tissue density are associated with cardiovascular risk.” “We developed and tested a deep learning algorithm for cardiovascular risk prediction based on routine mammography images.”

During about nine years of follow-up, 2,383 women experienced a heart attack, 731 had heart failure and 656 had a stroke. The study, published in Heart, found the AI approach performed as well as traditional calculators that use age and clinical variables to assess heart risk. The researchers added: “A deep learning algorithm utilising 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.”