Three-class ECG beat classification by ordinal entropies. (May 2021)

• Record Type: Journal Article
• Authors: Bidias à Mougoufan, Jean Bertin; Eyebe Fouda, J. S. Armand; Tchuente, Maurice; Koepf, Wolfram
• Is Part Of: Biomedical signal processing and control. Volume 67(2021)
• Publication Date: 2021-05
• Subjects: Adaptive ECG classification -- Ordinal entropy -- Real-time analysis; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102506
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: No prior learning required for classification. Application of ordinal entropies to ECG data. Real-time capability of ECG beat classification. Adaptive evaluation of thresholds for three class ECG beat classification. Abstract: The automatic and rapid analysis of long-term electrocardiogram (ECG) records still remains a challenging task. Most of the existing algorithms are time consuming and require a training step. In this paper, we present a training free two-level hierarchical model based on ordinal patterns for classifying ECG beats into three types. The classification rules include morphological and temporal properties of the ECG signal that are compared to R-R and QRS dependent thresholds derived from the beat CEOP or PE series. The experimental classification rates obtained from the MIT-BIH Arrhythmia database (93.66%) and the St. Petersburg Institute of Cardiological Technics (INCART) database (95.43%), considering the Advancement of Medical Instrumentation (AAMI) recommendations, confirm the ability of the proposed approach for a multi-class classification.