Automatic heart sound analysis for tele-cardiac auscultation

This paper presents heart sound signal processing that is a part of an automatic tele-auscultation system. Segmentation of the heart sound is performed using ECG signal as reference. Feature vector is constructed for each cardiac cycle by analyzing the systole and diastole of each cycle by applying discrete wavelet transform. Features are classified using pattern recognition neural network. The study incorporates four types of valve-related cardiac disorder that are normally diagnosed by auscultation: aortic regurgitation, aortic stenosis, mitral regurgitation and mitral stenosis. The result shows that for limited set of heart sounds, correct classification can be achieved.