ECG feature extraction using principal component analysis for studying the effect of diabetes.

The condition of cardiac health is given by Electrocardiogram (ECG). ECG analysis is one of the most important aspects of research in the field of Biomedical and healthcare. The precision in the identification of various parameters in ECG is of great importance. Many algorithms have been developed in the last few years for this purpose. Since diabetes is the major chronic illness prevailing today, recently there has been increasing interest in the study of the relationship between diabetes and cardiac health. This paper presents an algorithm based on Principal Component Analysis (PCA) for 12 lead ECG feature extraction and the estimation of diabetes-related ECG parameters. The data used for our purpose is acquired by XBio Aqulyser unit from TMI systems. The baseline wander is removed from the acquired data using the FFT approach and the signal is de-noised using wavelet transform and then the PCA method is employed to extract the R-wave. The other waves are then extracted using the window method. Later, using these primary features, the diabetes mellitus (DM)-related features like corrected QT interval (QTc), QT dispersion (QTd), P wave dispersion (PD) and ST depression (STd) are estimated. This study has taken 25 diabetic patients data for study.