Title: Detection of cardiac abnormalities in ECG signal using time-based signal processing algorithm
Authors: Kiran Kumar Patro; Allam Jaya Prakash; Geetamma Tummalapalli; P. Lalitha Kumari; M. Jaya Manmadha Rao
Addresses: Department of ECE, Aditya Institute of Technology and Management, Tekkali, AP-532201, India ' Department of EC, National Institute of Technology, Rourkela, Odisha 769008, India ' Department of Electronics and Commutation Engineering, GMR Institute of Technology, Rajam, AP, India ' SCOPE, VITAP University, Vijayawada, India ' Department of ECE, Aditya Institute of Technology and Management, Tekkali, AP-532201, India
Abstract: Electrocardiograms are bioelectrical signals that provide information regarding the normal and abnormal physiology of the heart. Early detection of cardiac irregularities in cardiac patients prevents strokes and sudden deaths. The effective functioning of the heart in each individual is dependent on the amplitude and interval values of the P-QRS-T segment. In this work, a modified Pan-Tompkins algorithm is used for identifying the characteristic points. Various signal characteristics, including R-R interval, T-amplitude, and QRS duration, were meticulously quantified and compared with NSR to determine ECG cardiac problems. Further, different cardiac abnormalities such as atrial fibrillation (AF), right bundle branch block (RBBB), cardiac ischemia (CI), left bundle branch block (LBBB), bradycardia, and tachycardia are detected using the time and amplitude features of the ECG. The suggested method was evaluated on three major online Physionet ECG databases (the AFDB, NSR, and MIT-BIH Arrhythmia databases) to assess its generalisability.
Keywords: electrocardiogram; ECG; cardiac abnormalities; signal processing; bradycardia; tachycardia; atrial fibrillation; AF; left bundle branch block; LBBB; right bundle branch block; RBBB.
DOI: 10.1504/IJCVR.2025.143052
International Journal of Computational Vision and Robotics, 2025 Vol.15 No.1, pp.59 - 74
Received: 01 Nov 2022
Accepted: 15 Mar 2023
Published online: 02 Dec 2024 *