Dynamics Analysis of Heart Sound Signal by Sample Entropy Fast Algorithm
WANG Xin-pei1; YANG Jing2; LI Yuan-yang1; LIU Chang-chun1; LI Li-ping1
1. School of Control Science and Engineering, Shandong University, Ji/nan 250061, China;2. Department of Computer Science and Technology, Shandong University, Ji/nan 250101, China
Abstract: The diastolic heart sound analysis method based on sample entropy fast algorithm was proposed to exactly describe the change of hemodynamic character caused by coronary artery stenosis. Firstly, the heart sound signal was preprocessed by wavelet to eliminate the respiratory interference. Then, the diastolic segments were segmented automatically using segmentation algorithm based on 3-order Shannon entropy. Finally, the average sample entropy of diastolic heart sounds was estimated by sample entropy fast algorithm. The nonlinear dynamical analysis (sample entropy) measures of the diastolic heart sounds recorded from 25 normal subjects and 25 patients with coronary artery disease (CAD) were estimated. Results show that there are significant differences on the sample entropy values between subjects with and without CAD. This method led to a sensitivity of 80% and a specificity of 84%.