Robust feature extraction from ECG signals based on nonlinear dynamical modeling

The early detection of abnormal heart conditions is vital for intensive care unit patients. The detection of such conditions is possible through continuous monitoring of electrocardiographic (ECG) signals to detect the presence of arrhythmia. Conventional methods of arrhythmia detection rely on observing morphological features of the signal in the time domain or after applying a certain transformation. Even though these techniques have been fairly successful in detecting such conditions, they are limited by the fact that they treat the heart as a linear system. In this paper, we present a comprehensive study of the nonlinear dynamics of ECG signals. The correlation dimension and largest Lyapunov exponent are used to model the chaotic nature of five different classes of ECG signals. The model parameters are evaluated for a large number of real ECG signals within each class and the results are reported. The proposed algorithms allow automatic calculation of the features. The statistical analysis of the calculated features indicates that they differ significantly among different arrhythmia types and hence can be rather useful in ECG signal classification. The results of this work show the potential of such features for use in arrhythmia detection in clinical cardiac monitoring.