ECG fiducial points extraction by extended Kalman filtering

Most of the clinically useful information in Electrocardiogram (ECG) signal can be obtained from the intervals, amplitudes and wave shapes (morphologies). The automatic detection of ECG waves is important to cardiac disease diagnosis. In this paper, we propose an efficient method for extraction of characteristic points of ECG. The method is based on a nonlinear dynamic model, previously introduced for generation of synthetic ECG signals. For estimating the parameters of model, we use an Extendend Kalman Filter (EKF). By introducing a simple AR model for each of the dynamic parameters of Gaussian functions in model and considering separate states for ECG waves, the new EKF structure was constructed. Quantitative and qualitative evaluations of the proposed method have been done on Physionet QT database (QTDB). This method is also compared with a method based on Partially Collapsed Gibbs Sampler (PCGS). Results show that the proposed method can detect fiducial points of ECG precisely and mean of estimation error of all FPs (except Ton) do not exceed five samples (20 msec).