A new study presented at the European Society of Cardiology’s annual congress suggests that artificial intelligence can detect cardiovascular disease in women by analyzing mammograms used for breast cancer screening. Researchers analyzed 97,364 scans from 29,921 women with an average age of 54, cross-referencing medical records to identify those with heart conditions. The study 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 to identify these cardiovascular conditions based on mammogram images alone. The AI system reliably identified women who had suffered a stroke 86% of the time. For high blood pressure and coronary heart disease, the model demonstrated 79% and 78% reliability respectively in distinguishing between women with and without these conditions. Results remained consistent across different age groups and regardless of whether women also had cancer.
Dr. Viana Copeland from Tel Aviv University, who presented the findings, emphasized that cardiovascular disease remains the leading cause of death in women worldwide yet is frequently underdiagnosed and undertreated. She noted that many women do not seek medical help for cardiovascular symptoms until the disease is already advanced. However, millions of women routinely attend breast cancer screening mammograms, making this approach potentially scalable without requiring additional imaging examinations.
Medical experts have called the findings compelling and noted the significant implications. Hundreds of millions of women undergo mammograms annually, providing an opportunity to screen for heart health at the same time. However, specialists emphasized that further research is needed to establish the accuracy and reliability of the approach before moving from experimentation to clinical implementation. A team is currently working to improve the AI model’s accuracy, reduce false results, and expand the range of heart conditions it can detect.
Article Attribution | Read More at Article Source
Article summary produced by Claude AI