Artificial intelligence (AI)-guided screening using digital stethoscopes has doubled the detection rate of left ventricular systolic dysfunction (LVSD) in pregnant and postpartum women in Nigeria. This innovative approach addresses the challenges of diagnosing cardiomyopathy during pregnancy, where symptoms often overlap with normal pregnancy changes.
According to the study authors, "Delays in the diagnosis of cardiomyopathy during the peripartum period are associated with poorer outcomes. It is imperative that we identify cardiac dysfunction early to initiate appropriate care and reduce adverse maternal and infant outcomes."
The study, led by Demilade A. Adedinsewo from the Mayo Clinic in Jacksonville, Florida, was published online on September 2 in Nature Medicine. It highlights the significant improvement in diagnosis rates compared to standard care.
However, the study's design and participant selection may limit its generalizability. Two-thirds of participants were in the third trimester or postpartum at study entry, which restricted follow-up visits. Additionally, the cutoff for LVSD did not align with the original model specifications, potentially affecting the results.
Adedinsewo has received grants from the Mayo Clinic BIRCWH program, funded by the National Institutes of Health. Co-authors Zachi I. Attia and Paul A. Friedman hold patents for AI algorithms licensed to several health technology companies.