A deep learning-based algorithm combining three standard echocardiographic views achieved a total error rate of 12.9% for the automated detection of coarctation of the aorta in neonates.
Observational (n=90)
No
Does a deep learning-based machine learning framework accurately detect coarctation of the aorta from two-dimensional echocardiograms in neonates?
A deep learning framework using standard 2D echocardiogram views can automatically detect coarctation of the aorta in neonates with a low error rate of 12.9%, potentially improving upon current screening methods.
Coarctation of aorta (CoA) is a critical congenital heart defect (CCHD) that requires accurate and immediate diagnosis and treatment. Current newborn screening methods to detect CoA lack both in sensitivity and specificity, and when suspected in a newborn, it must be confirmed using specialized imaging and expert diagnosis, both of which are usually unavailable at tertiary birthing centers. We explore the feasibility of applying machine learning methods to reliably determine the presence of this difficult-to-diagnose cardiac abnormality from ultrasound image data. We propose a framework that uses deep learning-based machine learning methods for fully automated detection of CoA from two-dimensional ultrasound clinical data acquired in the parasternal long axis view, the apical four chamber view, and the suprasternal notch view. On a validation set consisting of 26 CoA and 64 normal patients our algorithm achieved a total error rate of 12.9% (11.5% false-negative error and 13.6% false-positive error) when combining decisions of classifiers over three standard echocardiographic view planes. This compares favorably with published results that combine clinical assessments with pulse oximetry to detect CoA (71% sensitivity).
Pereira et al. (Tue,) conducted a observational in Coarctation of aorta (CoA) (n=90). Deep learning-based automated detection algorithm vs. Normal patients (classification task) was evaluated on Total error rate for three-view combination (PSLAX + AC4 + SSNA) (95% CI 12.3-13.9). A deep learning-based algorithm combining three standard echocardiographic views achieved a total error rate of 12.9% for the automated detection of coarctation of the aorta in neonates.