A Novel Deep Learning CNN for Heart Valve Disease Classification Using Valve Sound Detection

Valve sounds are mostly a result of heart valves opening and closing. Laminar blood flow is interrupted abruptly transforms into turbulent flow, causing some sounds, explained by improper valve operation. It has been feasible to demonstrate that the typical compulsive instances different for both chronological spatial aspects through examination phono-cardiographic signals. The current work presents development application deep convolutional neural networks binary multiclass categorization multiple prevalent diseases sounds. Three alternative methods were taken consideration feature extraction: mel-frequency cepstral coefficients discrete wavelet transform. precision models accomplished F1 scores more than 98.2% specificities 98.5%, which reflects can be wrongly classified as regular. These experimental results prove proposed model highly accurate assisted diagnosis model.