Diagnosing heart abnormality from PCG signals Using K -Means Clustering

Diagnosingcardiovascular diseases are now a days getting very critical , though there may be several classical methods like electrocardiography and ultrasound imaging to identify the abnormality in the functioning of heart , processing the PCG signals gives a lot of value added information in classifying the murmurs separately from S1(lub) and S2(dub). It is a cheap and non-invasive method which provides better information regarding the mechanism of heart valves and [login to view URL] has been known that the presence of the heart murmurs in one's heart sound indicates that there is a potential heart problem. Thus, the goal of this paper is to develop a technique for detecting and classifying murmurs. Such a technique can be used as part of an automatic heart diagnostic system. Initially we developed an algorithm to detect S1 and S2 heart sounds, we extracted several features from the PCG signals and tested it with pathological and non-pathological heart sounds. The k- Means clustering concept was implemented , which is used to classify the signals based on the obtained [login to view URL] obtained results had an overall efficiency of 86.67 % and sensitivity of 92.857 % from a total of 52 PCG signals that were obtained from clinical database. The algorithm was implemented in Matlab programming language version R2013b.