Mel-frequency cepstral based heart sound signal segmentation for decision support system

Abstract

The classification of heart diseases depends on the correct identification of S1 and S2 segments. Without the ECG reference signal, segmentation methods become naturally more complicated. In the hospital environment, the heart sounds collected from the patients through the stethoscope carry unrequired environmental sounds such as ambient noise, speech, wheezing, and friction. Besides, depending on the heart condition, noise like murmur is also included in these heart sounds. Discrete Wavelet Transform and Mel-Frequency Cepstral Coefficient (MFCC) have been used as a hybrid solution for the filtering of the noise content of basic heart sounds. In order to determine S1-S2 locations, heart rate and systolic time intervals were predicted by using signal autocorrelation. As a result of this proposed algorithm, S1 and S2 sounds were detected with 98.19% precision and 98.52% recall for normal heart sounds, while S1 and S2 were detected with precision of 94.31% and recall of 96.92% for abnormal heart sounds.