Detection of the electrocardiogram fiducial points in the phase space using the euclidian distance measure

• Published in: Medical engineering & physics Vol. 34; no. 4; pp. 524 - 529
• Main Authors: Plesnik, E., Malgina, O., Tasič, J.F., Zajc, M.
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.05.2012; Elsevier
• Subjects: Algorithms; Biological and medical sciences; Digital signal processing; ECG signal; EKG; Electrocardiography - standards; Electrocardiography. Vectocardiography; Electrodiagnosis. Electric activity recording; Euclidian distance; Fiducial Markers; Fiducial points; Heart; Heart - physiology; Investigative techniques, diagnostic techniques (general aspects); Medical sciences; Phase portrait; Phase space; Radiology; Signal Processing, Computer-Assisted; Time Factors; Fiducial points; ECG signal; Phase portrait; Euclidian distance; Phase space; Digital signal processing; Electrodiagnosis; Fiducial marker; Electrocardiography; Signal processing; Diagnosis; Biomedical engineering
• ISSN: 1350-4533; 1873-4030; 1873-4030
• DOI: 10.1016/j.medengphy.2012.01.005

The paper proposes a phase-space based algorithm applying the Euclidian distance measure enabling detection of heartbeats and characteristic (fiducial) points from a single-lead electrocardiogram (ECG) signal. It extends the QRS detection in the phase space by detecting the P and T fiducial points. The algorithm is derived by reconstructing the ECG signals in a two-dimensional (2D) phase space according to the delay method and utilizes geometrical properties of the reconstructed phase portrait of the signal in the phase space for the heartbeat and fiducial-point detection. It uses adaptive thresholding and the Euclidian distance measure between the signal points in the phase portrait as an alternative to the phase-portrait area calculation (Lee et al., 2002 [1]). It was verified with the QT Database (2011; [2]) and its performance was assessed using sensitivity (Se) and the positive predictive value (PPV). Results for the proposed algorithm are 99.06%, 99.75% and 99.66% for Se and 94.87%, 99.75% and 99.66% for PPV for the P points, heartbeats and T points, respectively.