Doctors have unveiled a pioneering approach that uses artificial intelligence to detect cardiovascular disease in women during routine mammograms, potentially transforming the world’s most common cancer screening programme into a dual-purpose tool for saving lives.
Researchers in Israel trained a machine-learning model to analyse breast scans for signs of heart disease, high blood pressure and stroke. The findings, presented at the European Society of Cardiology’s annual congress in Munich, suggest that hundreds of millions of mammograms carried out each year could soon flag the world’s biggest killer of women far earlier than current methods allow.
Cardiovascular disease (CVD) remains the leading cause of death among women globally, yet it is consistently underdiagnosed and often missed until it has reached an advanced stage. The new research offers a tantalising solution: piggybacking heart-health screening onto appointments women are already attending.
How the study worked
The team, led by Dr Viana Copeland of Tel Aviv University, examined a staggering 97,364 mammograms taken from 29,921 women with an average age of 54. By cross-referencing the images with medical records, they established baseline conditions within the group.
Some 16% of the women had high blood pressure, 2.5% had coronary heart disease, and a further 2.5% had suffered a stroke. The researchers then fed the scans into a machine-learning model and tested whether it could identify those conditions from the images alone.
The results were striking. The AI correctly identified women who had suffered a stroke based on their mammogram 86% of the time. For high blood pressure it achieved 79% accuracy, and for coronary heart disease 78%. Crucially, the findings held firm regardless of age and regardless of whether the woman also had cancer.
A “scalable” opportunity for women’s health
Copeland told delegates in Munich that the potential of the approach lay in its reach.
“Despite being the leading cause of death in women worldwide, CVD is consistently underdiagnosed and undertreated,” she said. “A common finding in our medical centre, and around the world, is that when women do seek medical help, their CVD is already advanced. On the other hand, many women do attend routine breast cancer screening, even when they haven’t sought care for cardiovascular symptoms.”
Because mammography is already embedded in healthcare systems across the globe, analysing breast scans for cardiovascular information “could potentially offer a scalable approach without requiring an additional imaging examination,” Copeland added.
She also pointed to the demographic sweet spot of mammography. “Mammography also reaches many women in midlife, an important period for recognising and addressing cardiovascular risk.”
The team is now working to refine the model, reduce false results and broaden the range of heart conditions it can detect.
Experts hail “compelling” findings
The reaction from leading cardiologists was enthusiastic. Elena Arbelo, a member of the European Society of Cardiology’s communication committee, called the findings “compelling”.
“A mammogram may one day do more than look for breast cancer – it may also offer a window on to cardiovascular health,” she said. “That matters because CVD in women is still too often recognised late.” The next hurdle, she added, was establishing accuracy and reliability, “to move from experimentation to clinical implementation”.
In London, Dr Sonya Babu-Narayan, consultant cardiologist and clinical director of the British Heart Foundation, said the breakthrough could challenge the stubborn myth that heart disease is a man’s illness.
“Heart disease is the world’s biggest killer of not only men, but also women,” she said. “Despite this, the myth persists that it’s only a ‘man’s disease’, meaning that when it comes to the heart, women are disproportionally unaware, unheard, underdiagnosed, undertreated and typically underrepresented in clinical research.”
Babu-Narayan said it was “exciting” to consider the implications if the Israeli approach proved robust in further trials. “AI could one day allow breast cancer screening programmes to become dual-purpose, helping to flag women with the highest risk of dangerous cardiovascular disease, as well as spotting breast cancer early.”
Why it Matters
For decades, women’s heart health has suffered from a catastrophic blind spot. Women are slower to be investigated, slower to be diagnosed and slower to receive treatment for cardiovascular disease, with devastating consequences. This study offers something rare: a chance to repurpose a screening tool that already reaches hundreds of millions of women, at exactly the stage of life when heart risk begins to climb. If the AI model can be refined and validated, a single appointment could soon detect not just a tumour but a ticking time bomb in the chest, potentially saving countless lives that might otherwise be lost to a disease too many do not even realise they are at risk of.
