Classification of Heart Sounds using Random Forests

Abstract

Auscultation is a technique, in which Physicians used the stethoscope to listen to patient‟s heart sounds in order to make a diagnosis. However, the determination of heart conditions by heart auscultation is a difficult task and it requires special training of medical staff. On the other hand, in primary or home health care, when deciding who requires special care, auscultation plays a very important role; and for these situations, an „„intelligent stethoscope‟‟ with decision support abilities is highly needed and it would be a great added value. The system algorithm has been realized in offline data phase, 234 cases of Heart Sounds (HSs) files were collected from ”Physiobank”, and then the background noise is minimized using wavelet transform. After that statistics features vector elements are formed. Finally, classification process was accomplished using random forest algorithm. The implementation of the proposed algorithm produced accuracy of 98.28%, and sensitivity of 98.29%.