An Efficient Computational Approach for Phonocardiogram Signals Analysis and Normal/Abnormal heart sounds diagnosis

In the present work, we proposed an intelligent approach for the examination and classification of cardiac sound signals “phonocardiogram (PCG)”. In this approach, artificial neural network (ANN) is executed as indicator and classifier of PCG abnormalities using the features extracted from PCG acoustic signals via the discrete wavelet transform (DWT). To develop and validate the proposed approach, the PASCAL CHSC 2011 dataset was utilized. The k-fold cross validation was utilized to assess the efficiency of the proposed intelligent approach. The results demonstrate that the approach achieves high performance compared to other classification techniques for PCG datasets. The obtained results showed an overall accuracy of 99.89%. Moreover, the proposed approach results are compared with the ones that achieved utilizing different machine learning (ML) approaches recently published. The achieved results showed that our proposed system has ability for efficient diagnosis and classifications of PCG acoustic signals also; it can also assist the clinicians to take accurate decisions in detecting cardiovascular abnormalities.