Identifying pediatric heart murmurs and distinguishing innocent from pathologic using deep learning.

OBJECTIVE: To develop a deep learning algorithm to perform multi-class classification of normal pediatric heart sounds, innocent murmurs, and pathologic murmurs. METHODS: We prospectively enrolled children under age 18 being evaluated by the Division of Pediatric Cardiology. Parents provided consent for a deidentified recording of their child's heart sounds with a digital stethoscope. Innocent murmurs were validated by a pediatric cardiologist and pathologic murmurs were validated by echocardiogram. To augment our collection of normal heart sounds, we utilized a public database of pediatric heart sound recordings (Oliveira, 2022). We propose two novel approaches for this audio classification task. We train a vision transformer on either Markov transition field or Gramian angular field image representations of the frequency spectrum. We benchmark our results against a ResNet-50 CNN trained on spectrogram images. RESULTS: Our final dataset consisted of 366 normal heart sounds, 175 innocent murmurs, and 216 pathologic murmurs. Innocent murmurs collected include Still's murmur, venous hum, and flow murmurs. Pathologic murmurs included ventricular septal defect, tetralogy of Fallot, aortic regurgitation, aortic stenosis, pulmonary stenosis, mitral regurgitation and stenosis, and tricuspid regurgitation. We find that the Vision Transformer consistently outperforms the ResNet-50 on all three image representations, and that the Gramian angular field is the superior image representation for pediatric heart sounds. We calculated a one-vs-rest multi-class ROC curve for each of the three classes. Our best model achieves an area under the curve (AUC) value of 0.92 ± 0.05, 0.83 ± 0.04, and 0.88 ± 0.04 for identifying normal heart sounds, innocent murmurs, and pathologic murmurs, respectively. CONCLUSION: We present two novel methods for pediatric heart sound classification, which outperforms the current standard of using a convolutional neural network trained on spectrogram images. To our knowledge, we are the first to demonstrate multi-class classification of pediatric murmurs. Multiclass output affords a more explainable and interpretable model, which can facilitate further model improvement in the downstream model development cycle and enhance clinician trust and therefore adoption.

Ross-Konno Operation in an Infant With a Quadricuspid Pulmonary Valve and Anomalous Aortic Origin of the Right Coronary Artery.

Anomalous aortic origin of the right coronary artery from the left aortic sinus is a rare congenital anomaly that is generally repaired during adolescence when the condition is associated with symptoms. It is rarely diagnosed in infancy. Similarly, a quadricuspid pulmonary valve is also a rare finding, and there are scant data to evaluate whether this malformation of the pulmonary valve is suitable to be used for a Ross operation. This report describes a case in which both these anomalies coexisted in an infant who underwent a successful Ross-Konno operation.

The differential affinity of the usher for chaperone-subunit complexes is required for assembly of complete pili.

Attachment to host cells via adhesive surface structures is a prerequisite for the pathogenesis of many bacteria. Uropathogenic Escherichia coli assemble P and type 1 pili for attachment to the host urothelium. Assembly of these pili requires the conserved chaperone/usher pathway, in which a periplasmic chaperone controls the folding of pilus subunits and an outer membrane usher provides a platform for pilus assembly and secretion. The usher has differential affinity for pilus subunits, with highest affinity for the tip-localized adhesin. Here, we identify residues F21 and R652 of the P pilus usher PapC as functioning in the differential affinity of the usher. R652 is important for high-affinity binding to the adhesin whereas F21 is important for limiting affinity for the PapA major rod subunit. PapC mutants in these residues are specifically defective for pilus assembly in the presence of PapA, demonstrating that differential affinity of the usher is required for assembly of complete pili. Analysis of PapG deletion mutants demonstrated that the adhesin is not required to initiate P pilus biogenesis. Thus, the differential affinity of the usher may be critical to ensure assembly of functional pilus fibres.