Analysis and classification of wrist pulse using sample entropy

The cardiovascular system is complex system containing many nonlinearities. Pulse signals are nonlinear reflecting the status of the heart and the vascular system. Sample entropy analysis can quantify signal regularity or the system complexity generating the signal. In this paper the wrist pulse signals of healthy group and coronary heart disease group are analyzed and studied with sample entropy analysis, and the selection of parameters is discussed. The pulse signals of two groups are classified using support vector machine (SVM), the classification results are analyzed. The results indicate there was difference between the sample entropy of two groups of wrist pulse signals; SVM classifiers have good performance for classification of the two groups. Sample entropy analysis of wrist pulse was helpful for non-destructive inspection of coronary heart disease.