Diagnosis and Classification of Systolic Murmur in Newborns

Amir Mohammad Amiri and Giuliano Armano

Keywords

Bispectral, Winger distribution, Artificial neural network, Newborns, systolic murmurs, innocent murmur

Abstract

The problem addressed in this paper is the detection and classification of systolic murmurs in newborns. As the estimates of higher-order spectra have been shown to be useful in various signal processing problems, this paper uses bispectra and Wigner distribution for systolic murmurs detection. The diagnostic system that has been implemented is based on artificial neural networks, can be used for detecting and classifying systolic murmurs. The system outputs the classification of the sound as either normal (innocent murmurs) or a type of pathological systolic murmurs. The ultimate goal of this research is to implement a heart sounds diagnostic system that can be used to help physicians in the auscultation of patients, so to reduce number of unnecessary echocardiograms and prevent the release of newborns that are in fact patients. In this study, 96.4% accuracy, 97% sensitivity, and 97% specificity were obtained on a dataset of 56 samples.

Important Links:

Go Back