Detection and Classification of Abnormities of First Heart Sound Using Empirical Wavelet Transform

• Published in: IEEE access Vol. 7; pp. 139643 - 139652
• Main Authors: Li, Haixia, Ren, Yongfeng, Zhang, Guojun, Wang, Renxin, Cui, Jiangong, Zhang, Wendong
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: abnormities; Algorithms; Amplitudes; Artificial intelligence; Classification; Classification algorithms; Clusters; Decision trees; Decomposition; empirical wavelet transform (EWT); First heart sound (S1); Heart; Hilbert transformation; Instantaneous frequency (IF); Mathematical analysis; mitral component (M1); Resampling; Segmentation; Signal processing; Sound; Stethoscope; Time-frequency analysis; tricuspid component (T1); Valves; Wavelet transforms
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2943705

It is expected that an automatic detection and classification algorithm for the abnormities of first heart sound (S1) can realize computer artificial intelligence diagnosis of some relative cardiovascular disease. Few studies have focused on the detection and classification of the abnormities of S1 and given out in detail the essential differences between abnormal and normal S1. This work applied Empirical Wavelet Transform (EWT) to decompose S1 and extracted the instantaneous frequency (IF) of mitral component (M1) and tricuspid component (T1) by using Hilbert Transform. Firstly, the heart sound signal is preprocessed following these processes: filtering, resampling, normalization and segmentation. Secondly, S1 is decomposed into several modes based on EWT. First two maximal points with a distance greater than 20Hz in Fourier Spectrum of S1 are selected and the nearest minimal points on both sides of the maximal points are found out as the boundaries for segmentation of the spectrum. S1 is decomposed into 5 modes and every mode's IF are calculated through Hilbert transformation. At last, a k-mean cluster algorithm is applied to cluster the IF of different modes. TD and A peak_ratio are calculated for decision tree classifier and S1s are divided into three categories: normal S1, S1 with abnormal split and S1with abnormal amplitude change. When the proposed method is applied to detect normal S1, Se=94.6%, Pp=98.6% and Oa=93.3%; When it is applied to detect S1 with abnormal split, Se=92.6%, Pp=96.9% and Oa=90%; When it is applied to detect S1 with abnormal amplitude change, Se=94.4%, Pp=95.7% and Oa=90.6%; Comparison experiments are carried out between the proposed method and HVD method. The results show Oa of the proposed method is higher than HVD method when detecting the three different S1s.