AI-Powered ECG Technology Enhances Early Heart Disease Detection in Women

Every year, an alarming number of maternal deaths occur due to undiagnosed heart conditions. Many of these fatalities could potentially be avoided with timely screening for heart health prior to pregnancy. Researchers at the Mayo Clinic have pioneered a new approach utilizing artificial intelligence (AI) to analyze electrocardiogram (ECG) data and recordings from a digital stethoscope, aiming to identify previously undetected heart issues in women of childbearing age.

The findings of this study, published in the Annals of Family Medicine, highlight the impressive diagnostic capabilities of these AI technologies in detecting reduced left ventricular ejection fraction--an indicator of heart muscle weakness. The research included two groups of women aged between 18 and 49 years.

The first group comprised 100 women who were already scheduled for an echocardiogram, the gold standard for assessing heart function. Alongside this, participants underwent a standard clinical ECG and digital stethoscope recordings to capture their heart activity.

The second group consisted of 100 women attending routine primary care appointments, enabling researchers to evaluate how frequently the AI tools would reveal underlying heart conditions.

The AI-ECG demonstrated a remarkable area under the curve (AUC) of 0.94, while the AI digital stethoscope, Eko DUO, achieved an even higher AUC of 0.98, reflecting exceptional diagnostic precision. In the second group, the prevalence of positive AI screening results was noted at 1% for the AI-ECG and 3.2% for the AI digital stethoscope.

Research indicates that nearly half of all pregnancies in the United States are unplanned, and approximately 1% to 2% of women may be living with undiagnosed heart conditions. The results suggest that implementing AI screening tools could significantly enhance preconception care, allowing for better pregnancy planning, early intervention, and improved health outcomes for mothers and their children.

This research builds on prior studies, including a pilot study assessing AI tools for detecting pregnancy-related cardiomyopathy among obstetric patients in the U.S., as well as a randomized clinical trial involving women in Nigeria who were either pregnant or had recently given birth. Collectively, these findings underscore the transformative potential of AI in advancing cardiovascular health screening and promoting earlier detection and management of heart issues in women of reproductive age.

The Mayo Clinic has licensed this innovative technology to EKO Health for its digital stethoscope, which now incorporates embedded ECG electrodes, and to Anumana for the 12-lead ECG. The Mayo Clinic and certain authors of the study have a financial stake in these technologies, with any revenue generated being directed to support its nonprofit mission in patient care, education, and research.