Heart failure during pregnancy can be a serious and often overlooked issue, as its common signs—like shortness of breath, extreme tiredness, and difficulty breathing when lying down—are often confused with typical pregnancy discomforts. Recent research presented at the European Society of Cardiology Congress, involving a study by the Mayo Clinic, indicated that an AI-enabled digital stethoscope allowed physicians to detect double the cases of heart failure compared to a control group receiving standard obstetric care and screenings. Detailed findings from this study are available in Nature Medicine.
This study took place in Nigeria, a country where the incidence of pregnancy-related heart failure is the highest globally. The findings revealed that using the AI-powered digital stethoscope was 12 times more effective in identifying weak heart function than traditional methods when assessed using an ejection fraction threshold lower than 45%. This threshold is critical as it pertains to a type of heart failure known as peripartum cardiomyopathy.
“Early detection of this heart failure type is crucial for the health and safety of the mother,” stated Demilade Adedinsewo, M.D., a cardiologist at Mayo Clinic and the study’s lead investigator. “Symptoms of peripartum cardiomyopathy can worsen as the pregnancy progresses or often after childbirth, and if the mother’s heart becomes too weak, it can be life-threatening. Medications can mitigate the issue if identified early, but in more severe cases, treatment might escalate to intensive care, mechanical heart pumps, or even a heart transplant if medical management fails.”
The randomized, controlled, open-label clinical trial encompassed nearly 1,200 participants who were assessed for heart issues using either standard obstetric care or AI-enhanced methods. The Mayo Clinic researchers previously devised a primary 12-lead AI-electrocardiogram (ECG) algorithm for predicting low heart function, known as low ejection fraction. Eko Health then enhanced this algorithm for their FDA-approved digital stethoscope designed to detect heart failure related to low ejection fraction.
The investigators found that doctors employing AI-assisted screenings with the digital stethoscope and 12-lead ECG were highly accurate in detecting weakened heart function. Within the study group, the digital stethoscope identified twice as many instances of low ejection fraction under 50%, and its users were 12 times more likely to detect an ejection fraction below 45% compared to standard care.
The AI-driven tools were tested at three distinct ejection fraction levels used in clinical diagnoses. An ejection fraction of less than 45% is the benchmark for diagnosing peripartum cardiomyopathy, while below 40% indicates heart failure with reduced ejection fraction, which significantly benefits from specific medications aimed at alleviating symptoms and lowering mortality risk. An ejection fraction of under 35% signals critically low heart pump function that typically necessitates more rigorous treatment, which may include advanced heart failure therapies and an implantable defibrillator if the heart function does not improve. At the start of the study, participants in the intervention group underwent an echocardiogram to validate the AI findings.
“This research demonstrates our improved ability to identify peripartum cardiomyopathy in women in Nigeria. Nevertheless, there remain many unanswered questions,” Dr. Adedinsewo remarked. “Our forthcoming steps will involve assessing how usable and accepted this tool is among healthcare practitioners in Nigeria, including doctors and nurses, and its overall effect on patient care. Peripartum cardiomyopathy impacts around 1 in 2,000 women in the U.S. and up to 1 in 700 African American women. Testing this AI tool in the U.S. will allow us to further evaluate its effectiveness across diverse populations and healthcare environments.”
This clinical trial was funded by Mayo Clinic, which includes the Centers for Digital Health and Community Health and Engagement Research; the Building Interdisciplinary Research Careers in Women’s Health (BIRCWH) Program at Mayo Clinic, which is supported by the National Institutes of Health (NIH); and the Center for Clinical and Translational Sciences (CCATS) at Mayo Clinic, also funded by the NIH.
