ECG fiducial point extraction using switching Kalman filter

• Published in: Computer methods and programs in biomedicine Vol. 157; no. April; pp. 129 - 136
• Main Authors: Akhbari, Mahsa, Ghahjaverestan, Nasim Montazeri, Shamsollahi, Mohammad B., Jutten, Christian
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.04.2018; Elsevier
• Subjects: Arrhythmias, Cardiac - physiopathology; Computer Simulation; Database Management Systems; Electrocardiogram (ECG); Electrocardiography - methods; Engineering Sciences; Extended Kalman filter (EKF); Fiducial Markers; Fiducial point (FP) extraction; Humans; Probability; Segmentation; Signal and Image processing; Signal Processing, Computer-Assisted; Switching Kalman filter (SKF); Extended Kalman filter (EKF); Fiducial point (FP) extraction; Segmentation; Electrocardiogram (ECG); Switching Kalman filter (SKF); Switching Kalman Filter (SKF); Extended Kalman Filter (EKF); Fiducial Point (FP) Extraction
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2018.01.018

•A method based on switching Kalman filter is proposed for extracting fiducial points of ECG signals.•ECG waveforms are modeled with Gaussian functions and ECG baselines are modeled with first order auto regressive models.•A discrete state variable called switch is considered that affects only the observation equations.•A mode is denoted as a specific observation equation and switch changes between 7 modes.•The probability of each mode is calculated and compared among two consecutive modes and a path is estimated. Fiducial points are found from the estimated path. In this paper, we propose a novel method for extracting fiducial points (FPs) of the beats in electrocardiogram (ECG) signals using switching Kalman filter (SKF). In this method, according to McSharry’s model, ECG waveforms (P-wave, QRS complex and T-wave) are modeled with Gaussian functions and ECG baselines are modeled with first order auto regressive models. In the proposed method, a discrete state variable called “switch” is considered that affects only the observation equations. We denote a mode as a specific observation equation and switch changes between 7 modes and corresponds to different segments of an ECG beat. At each time instant, the probability of each mode is calculated and compared among two consecutive modes and a path is estimated, which shows the relation of each part of the ECG signal to the mode with the maximum probability. ECG FPs are found from the estimated path. For performance evaluation, the Physionet QT database is used and the proposed method is compared with methods based on wavelet transform, partially collapsed Gibbs sampler (PCGS) and extended Kalman filter. For our proposed method, the mean error and the root mean square error across all FPs are 2 ms (i.e. less than one sample) and 14 ms, respectively. These errors are significantly smaller than those obtained using other methods. The proposed method achieves lesser RMSE and smaller variability with respect to others.