Predicting Arterial Stiffness from radial Pulse Waveform using support vector machines

Cardiovascular disease (CVD) is a larger cause of mortality in the developed country; hence, the early detection of its onset is vital for effective prevention. Arterial stiffness as measured by radial augmentation index (AIx) has been shown to be an independent predictor of CVD; however, the measurement of AIx is complex and not easily obtained precisely. A new approach based on the implementation of support vector machine (SVM) is presented for classification of radial pulse waveform. The radial pulse signals was decomposed into time-frequency representations using discrete wavelet transform (DWT) and wavelet scale-energy were calculated to represent the signals. The purpose is to predict an optimum classification scheme. The result demonstrated that the wavelet scale-energy are the features which well represent the radial Pulse Waveforms and the SVM trained on these features achieved high classification accuracies.