AI-Enabled Stethoscopes Enhance Cardiomyopathy Detection in Pregnancy & Postpartum


Summary:

AI-based tool surpasses traditional methods in detecting peripartum cardiomyopathy.

Title: Detecting Cardiomyopathies in Pregnancy and the Postpartum Period with an Electrocardiogram-Based Deep Learning Model

Authors: Demilade A. Adedinsewo, Patrick W. Johnson, Erika J. Douglass, et al.

Journal: European Heart Journal Digital Health, 2021

This study describes an early version of the Eko Low EF AI, initially developed by Mayo Clinic and later licensed to Eko Health. It evaluated a 12-lead ECG-based artificial intelligence model to detect peripartum cardiomyopathy (PPCM), a serious form of pregnancy-related heart failure. In a cohort of over 1,800 women, the AI tool demonstrated high accuracy in identifying heart function decline, outperforming traditional clinical diagnostics. Notably, it was especially effective in Black and Hispanic women, who have higher PPCM rates.

The AI model was subsequently adapted to use a single-lead ECG and heart sound data, as detailed in a follow-up study published in Nature Medicine.

View Research -->