Multiscale sample entropy analysis of wrist pulse blood flow signal for disease diagnosis

3rd Sino-Foreign-Interchange Workshop on Intelligent Science and Intelligent Data Engineering, IScIDE 2012, Nanjing, 15-17 October 2012Recent study reported that wrist pulse blood flow signal is effective for disease diagnosis. The multiscale entropy, which was developed for quantifying the complexity of a time series of physiological signals over a range of scales, had been widely applied for feature extraction from medical signals. In this paper, using the multiscale sample entropy (Multi-SampEn) algorithm, we compute the value of SampEn of wrist pulse blood flow signal that includes 83 samples healthy persons, 45 samples of patients with liver diseases (LD), and 45 with sugar diabetes (SD). Then we use the values of SampEn as the feature input of the support vector machine classifier for disease diagnosis. Experimental results show that the proposed method could achieve the classification accuracy of 76.30% with the dimension m = 2 and the threshold r = 0.6, which is promising in diagnosing the healthy subjects, liver diseases, and sugar diabetes.Department of Computin