AI reads mammograms for heart disease risk, study finds

Doctors have found a way to use routine mammograms to spot heart disease, the world's leading and frequently underdiagnosed cause of death in women, by analyzing the scans with an AI model, The Guardian reported.

Doctors in Israel examined 97,364 mammogram scans from 29,921 women with an average age of 54. Cross-referencing medical records showed 16% had high blood pressure, 2.5% had coronary heart disease, and 2.5% had experienced a stroke. A machine-learning model trained on that data reliably identified women who had suffered a stroke 86% of the time, based on the mammogram alone, with 79% reliability for high blood pressure and 78% for coronary heart disease. The results held regardless of a woman's age or whether she also had cancer.

• Scans analyzed: 97,364, from 29,921 women
• Average patient age: 54
• Prevalence found: 16% high blood pressure, 2.5% coronary heart disease, 2.5% stroke history
• Model accuracy: 86% for stroke, 79% for high blood pressure, 78% for coronary heart disease

Dr. Viana Copeland of Tel Aviv University presented the findings at the European Society of Cardiology's annual congress in Munich, the world's largest heart conference. She said many women's cardiovascular disease is already advanced by the time they seek medical help, even though they routinely attend breast cancer screening without having sought care for cardiovascular symptoms. Because mammography is already widespread, reading breast scans for heart-health signals "could potentially offer a scalable approach without requiring an additional imaging examination," she said, adding that mammography also reaches many women during midlife, a key window for catching cardiovascular risk early.

A team of doctors and researchers is now working to improve the model's accuracy, reduce false results, and expand the range of conditions it can detect. Elena Arbelo of the European Society of Cardiology's communication committee called the findings "compelling," noting that a mammogram "may one day do more than look for breast cancer, it may also offer a window on to cardiovascular health," and that the next step is establishing accuracy and reliability before moving from experimentation to clinical use. Dr. Sonya Babu-Narayan, a consultant cardiologist and clinical director of the British Heart Foundation, pushed back on the persistent idea that heart disease is a "man's disease," arguing women remain disproportionately unaware, undertreated, and underrepresented in clinical research despite heart disease killing more women than any other cause.

The approach fits a wider pattern of AI finding new signal in medical data that was already being collected for other reasons. Intokened has covered similar territory in AI tools moving into everyday healthcare faster than the rules meant to govern them, and in how a single missed diagnosis can reshape what doctors screen for. This study hasn't reached clinical practice yet, but the scale of the data behind it, tens of thousands of women already being scanned, is exactly what makes it worth watching.

This article is for informational purposes only and does not constitute investment advice.