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

Abstract

Background: In infants, pulmonary hypertension (PH) increases morbidity and mortality. Echocardiography, though standard, is time- and expertise-demanding. We propose a deep learning approach for automated PH detection using standard echocardiography videos, validated by the systolic eccentricity index (EIs).

Methods: The training and validation set comprised 975 videos and the held-out set 378 videos, including five echocardiographic standard views from infants aged 3-90 days, taken between 2018-2021 and 2021-2022, respectively. Echocardiograms were labeled as PH (EIs < 0.82) and healthy (EIs ≥ 0.87). After preprocessing and random segmentation of all videos into 13.530 frames, spatial and spatio-temporal convolutional neural network architectures were used for training of a PH prediction model and gradient-weighted class activation mapping for explainability.

Results: The best single-view performance was achieved using parasternal short axis view (AUROC spatial and spatio-temporal: 0.91 and 0.94 in validation set, 0.93 and 0.88 in held-out set, respectively). Combination of three standard views improved accuracy with AUROC 0.96 and 0.90 in validation (spatio-temporal) and held-out set (spatial), respectively. Saliency maps revealed model focus on clinically relevant regions, including interventricular septum and left atrial filling.

Conclusions: The presented deep learning model for automated detection of PH in neonates shows high accuracy, explainability, and reproducibility.

Impact: 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.