Automated detection of neonatal pulmonary hypertension in echocardiograms with a deep learning model

This study presents a deep learning model that enables accurate, automated detection of pulmonary hypertension in infants using standard echocardiography videos, enhanced and evaluated with eccentricity index, an established and prognostically relevant echocardiographic parameter. The parasternal short-axis view showed the best single-view performance, combined views further improved accuracy. Explainability through saliency maps supports clinical acceptance, highlighting physiologically relevant regions in the decision process. It adds novel evidence to the literature, demonstrating the utility of spatio-temporal convolutional neural networks for early, non-invasive diagnosis. The model provides a scalable and reproducible tool for routine PH screening, potentially improving early detection and outcomes.