Heart diseases diagnosis using heart sounds

Heart sound is one of the oldest means for assessing the function of heart valves. It helps, together with echocardiograms and electrocardiographs, to give a clear and proper diagnosis of several diseases. Artificial neural networks are used to classify several valve-related heart disorders. A library of heart sound files, recorded via the traditional stethoscope, are used to extract relevant features using several signal processing tools, e.g., discrete wavelet transform (DWT), fast Fourier transform (FFT) and linear predictive coding (LPC). The achieved recognition rates were around 95.7%.