Artificial intelligence-guided detection of under-recognized cardiomyopathies on point-of-care cardiac ultrasound.

Link: https://doi.org/10.1101/2024.03.10.24304044
Authors: Oikonomou, Evangelos K; Holste, Gregory; Coppi, Andreas; McNamara, Robert L; Nadkarni, Girish N; Baloescu, Cristiana; Krumholz, Harlan M; Wang, Zhangyang; Khera, Rohan

Abstract: Point-of-care ultrasonography (POCUS) enables access to cardiac imaging directly at the bedside but is limited by brief acquisition, variation in acquisition quality, and lack of advanced protocols. To develop and validate deep learning models for detecting underdiagnosed cardiomyopathies on cardiac POCUS, leveraging a novel acquisition quality-adapted modeling strategy. We define and validate an AI framework that enables scalable, opportunistic screening of under-diagnosed cardiomyopathies using POCUS.