Peripartum cardiomyopathy (PPCM), a potentially life-threatening form of heart failure during pregnancy, often goes undiagnosed due to its symptoms—such as shortness of breath, extreme fatigue, and difficulty breathing when lying down—being mistaken for normal pregnancy discomforts. The condition can worsen as pregnancy progresses or postpartum, posing serious risks if the heart weakens significantly. Effective treatments are available, ranging from medications to more extreme measures like heart pumps or transplants in severe cases. Early detection is crucial for managing the condition and safeguarding maternal health. Now, late-breaking research presented at ESC Congress 2024 underscores the benefits of an AI-enabled digital stethoscope, which identified twice as many PPCM cases as traditional screening methods used in usual obstetric care.

This innovative approach was tested by researchers from the Mayo Clinic (Rochester, MN, USA) in Nigeria, where pregnancy-related heart failure rates are the highest globally. The study demonstrated that using AI-enhanced tools, including a digital stethoscope, was twelve times more likely than conventional methods to detect heart pump weakness at an ejection fraction below 45%—a critical threshold for PPCM diagnosis. The randomized, controlled, open-label trial involved nearly 1,200 participants who were screened either through standard obstetric care or with the aid of AI technologies. The Mayo Clinic had developed a 12-lead AI-electrocardiogram (ECG) algorithm to predict weak heart pumps that was adapted by Eko Health (Oakland, CA, USA) for its FDA-cleared digital stethoscope to identify low ejection fraction heart failure.

Published in Nature Medicine, the study results show that the AI-based screening tools, including the digital stethoscope and 12-lead ECG, effectively detected reduced heart function. In the study, the use of these AI tools resulted in identifying twice as many cases with an ejection fraction under 50%, and were twelve times more likely to detect ejection fractions under 45% compared to the usual care group. The AI tools were assessed at three diagnostic thresholds for ejection fraction: under 45% for PPCM, under 40% for heart failure with reduced ejection fraction, and under 35% for severe heart pump dysfunction, necessitating intensive management and possibly an implantable defibrillator if conditions do not improve. An initial echocardiogram was performed on each patient in the intervention group to verify the AI predictions.

"This study provides evidence that we can better detect peripartum cardiomyopathy among women in Nigeria. However, there are more questions to be answered," said Demilade Adedinsewo, M.D., a cardiologist at Mayo Clinic and lead investigator of the study. "Our next steps would be to evaluate usability and adoption of this tool by Nigerian healthcare providers (including doctors and nurses) and importantly, its impact on patient care. Peripartum cardiomyopathy affects approximately 1 in 2,000 women within the U.S. and as many as 1 in 700 African American women. Evaluating this AI tool in the U.S. will further test its abilities in varied populations and healthcare settings." 

http://www.gzjiayumed.com/en/index.asp .