AI identifies heart disease in women using routine mammograms

AI for Cardiovascular Disease Detection

A new study presented at the European Society of Cardiology’s annual congress demonstrated that artificial intelligence can identify signs of heart disease in women using routine mammograms. This approach could allow breast cancer screenings to also serve as a tool for detecting cardiovascular conditions, which are frequently underdiagnosed in women.

Study Methodology and Results

Doctors in Israel analyzed 97,364 mammogram scans from 29,921 women, with an average age of 54. By cross-referencing medical records, researchers found that 16% of the women had high blood pressure, 2.5% had coronary heart disease, and 2.5% had experienced a stroke. A machine-learning model was trained on these scans to identify women with these conditions.

The AI model reliably identified women who had suffered a stroke with 86% accuracy based solely on their mammogram. For high blood pressure and coronary heart disease, the model achieved 79% and 78% reliability, respectively, in distinguishing between women with and without these conditions. These results were consistent across different age groups and regardless of whether a woman also had cancer.

Implications for Women's Health

Cardiovascular disease is the leading cause of death in women globally, yet it is often underdiagnosed or detected at late stages. Dr. Viana Copeland from Tel Aviv University noted that many women attend routine breast cancer screenings even if they haven't sought care for cardiovascular symptoms. Utilizing mammography for heart health screening could offer a scalable approach without requiring additional imaging examinations, reaching many women in midlife, a critical period for early detection.