A multi-view video-based deep learning approach achieved a mean F1-score of 0.84 for severity prediction and 0.92 for binary detection of pulmonary hypertension in newborns using echocardiograms.
Observational (n=270)
No
Can a multi-view video-based deep learning approach accurately predict and classify the severity of pulmonary hypertension in newborns using echocardiograms?
A deep learning model using echocardiograms can automatically detect and classify the severity of pulmonary hypertension in newborns, focusing on clinically relevant cardiac structures.
Pulmonary hypertension (PH) in newborns and infants is a complex condition associated with several pulmonary, cardiac, and systemic diseases contributing to morbidity and mortality. Thus, accurate and early detection of PH and the classification of its severity is crucial for appropriate and successful management. Using echocardiography, the primary diagnostic tool in pediatrics, human assessment is both time-consuming and expertise-demanding, raising the need for an automated approach. Little effort has been directed towards automatic assessment of PH using echocardiography, and the few proposed methods only focus on binary PH classification on the adult population. In this work, we present an explainable multi-view video-based deep learning approach to predict and classify the severity of PH for a cohort of 270 newborns using echocardiograms. We use spatio-temporal convolutional architectures for the prediction of PH from each view, and aggregate the predictions of the different views using majority voting. Our results show a mean F1-score of 0.84 for severity prediction and 0.92 for binary detection using 10-fold cross-validation and 0.63 for severity prediction and 0.78 for binary detection on the held-out test set. We complement our predictions with saliency maps and show that the learned model focuses on clinically relevant cardiac structures, motivating its usage in clinical practice. To the best of our knowledge, this is the first work for an automated assessment of PH in newborns using echocardiograms.
Ragnarsdóttir et al. (Tue,) conducted a observational in Pulmonary hypertension (n=270). Multi-view spatio-temporal deep learning model was evaluated on Mean F1-score for PH severity prediction (10-fold cross-validation). A multi-view video-based deep learning approach achieved a mean F1-score of 0.84 for severity prediction and 0.92 for binary detection of pulmonary hypertension in newborns using echocardiograms.