SMART STETH

Abstract

Heart valves, which are responsible for the proper pumping of blood to the whole body generate some sounds during its functionality called as heart sounds. Listening and interpretation of these sounds using stethoscope is known as auscultation. Heart sounds commonly known as phonocardiogram signal provide valuable information for correct identification of any heart disease, if interpreted correctly. These sounds though audible but need an extensive practice and skills to be correctly understood. Any disease of heart valves like murmurs though appear in these sounds but are very difficult to be correctly identified by the cardiologist. These murmurs are even further having many types. Phonocardiogram signals can be utilized more efficiently by the cardiologists and medical officers when they are converted into some easily interpretable form rather through a conventional stethoscope. This research work is carried out with an aim to classify normal and abnormal heart sounds and further identify Mitral stenosis, Aortic Stenosis, Aortic Regurgitation heart diseases. For this preprocessing, Feature generation, feature selection have been carried out on PCG (Phonocardiogram) signal. For correct classification of heart diseases (Mitral stenosis, Aortic Stenosis, Aortic Regurgitation) we have used SVM classifier. We have also developed an android application, all work have been done first in MATLAB and then it has been prototyped into android application. Our system(“smart steth”)which is a smartphone connected to a stethoscope will take three inputs Heart sounds using stethoscope ,vital signs and medical history of subject (human) using android application. On basis of these it will decide whether the subject (human) is having HS (heart sound) normal or HS (heart sound) abnormal. If HS is abnormal then further it will identify it into whether subject is having Mitral stenosis or Aortic Stenosis or Aortic Regurgitation