A study presented at the European Society of Cardiology’s annual congress in Munich has demonstrated the potential for artificial intelligence to detect cardiovascular disease in women by analyzing mammogram images obtained during routine breast cancer screening.
Israeli researchers examined approximately 97,364 scans from nearly 30,000 women with an average age of 54. Through cross-referencing with medical records, the team identified that 16% of participants had high blood pressure, 2.5% had coronary heart disease, and 2.5% had experienced a stroke. A machine-learning model was subsequently trained to identify these conditions based on mammogram imagery alone.
The artificial intelligence model achieved varying levels of accuracy across the three conditions tested. It reliably identified women who had suffered a stroke 86% of the time, while achieving 79% reliability for high blood pressure detection and 78% for coronary heart disease identification. The model’s performance remained consistent regardless of patient age or concurrent cancer diagnosis.
Cardiovascular disease remains the leading cause of death among women globally, yet frequently goes undiagnosed or is identified only at advanced stages. Researchers note that many women do not seek medical care for cardiovascular symptoms but regularly attend mammography appointments for breast cancer screening. This presents an opportunity to leverage existing imaging infrastructure to identify additional health risks without requiring additional examinations.
Experts indicated that further work is needed to improve the model’s accuracy, reduce false results, and expand its capacity to detect additional cardiac conditions. If successfully implemented clinically, the approach could transform breast cancer screening programs into a dual-purpose tool for identifying cardiovascular disease risk while maintaining their primary cancer detection function.
Article Attribution | Read More at Article Source
Article summary produced by Claude AI