Jan. 22, 2025
Mayo Clinic Cardiovascular Medicine researchers found that an artificial intelligence (AI)-enabled digital stethoscope can help identify peripartum cardiomyopathy in patients. The study, published in Nature Medicine, offers new possibilities for discovering the underdiagnosed condition earlier.
Peripartum cardiomyopathy is a pregnancy-related condition in which the heart's pumping ability is weakened. In the U.S., approximately 1 in 2,000 pregnant people is affected by peripartum cardiomyopathy, and as many as 1 in 700 African American patients experiences this form of heart failure.
The randomized, controlled, open-label clinical trial included nearly 1,200 participants across six hospitals in Nigeria. Worldwide, the highest reported incidence of peripartum cardiomyopathy is in Nigeria. The results of the study were published in a 2024 issue of Nature Medicine.
Identifying cardiomyopathy with AI
The Mayo Clinic study showed that an AI-enabled digital stethoscope helped doctors identify twice as many patients with pregnancy-related heart failure compared with the number identified in a control group that received usual obstetric care and screening.
"This finding is significant. Cardiovascular disease, including cardiomyopathy, is the leading cause of maternal mortality in the U.S.," says Demilade A. Adedinsewo, M.D., a cardiologist at Mayo Clinic in Jacksonville, Florida, and lead investigator of the study. "Timely identification of these conditions can facilitate the prompt initiation of appropriate medical therapy, potentially reducing associated morbidity and mortality rates."
The symptoms of peripartum cardiomyopathy can get progressively worse during pregnancy and postpartum and endanger a patient's life if the heart becomes too weak.
Though early diagnosis is key, pregnancy-related cardiomyopathy or heart failure is underdetected. "It can be challenging to identify women who may be experiencing heart failure. The symptoms associated with heart failure are often those commonly seen with pregnancy, like shortness of breath and swelling in the lower extremities," says Dr. Adedinsewo.
AI-enabled screening results
The trial participants, ages 18 to 49, were randomized to receive either AI-enhanced screening for pregnancy-related cardiomyopathy or usual obstetric care and associated screening. Mayo Clinic researchers previously developed a foundational 12-lead AI-electrocardiogram (ECG) algorithm to predict a weak heart pump, clinically known as low ejection fraction. A version of this algorithm was modified for use with a digital stethoscope to detect heart failure with low ejection fraction.
The study also found that doctors using the AI-enabled digital stethoscope were 12 times more likely than with traditional screening to detect weak heart function at an ejection fraction lower than 45%, which is the cutoff indicating peripartum cardiomyopathy. Within the overall study cohort, the digital stethoscope helped find twice as many patients with ejection fractions lower than 50% compared with regular care.
Advancing patient care
Mayo Clinic Cardiovascular Medicine specialists embrace new tools and technology to help lower pregnancy-related mortality rates. "Innovative technologies powered by artificial intelligence can now be used to improve the diagnosis of peripartum cardiomyopathy," says Dr. Adedinsewo. "Notably, the screening tool, an artificial intelligence-powered digital stethoscope, which was shown to be effective in the randomized clinical trial conducted in Nigeria, has received U.S. Food and Drug Administration (FDA) approval and is now commercially available in the U.S."
What's next
The evidence shows better detection of pregnancy-related cardiomyopathy among women, but there are more questions to be answered.
"Additional validation studies in large, diverse patient populations in the U.S. will be important," says Dr. Adedinsewo. "It's also crucial to determine the most effective ways to integrate these tools into clinical care, considering the variations in workflows and practices among different health systems in the country."
For more information
Adedinsewo DA, et al. Artificial intelligence guided screening for cardiomyopathies in an obstetric population: a pragmatic randomized clinical trial. Nature Medicine. 2024;30:2897.
Refer a patient to Mayo Clinic.