G2-ResNeXt: A Novel Model for ECG Signal Classification

• Published in: IEEE access Vol. 11; pp. 34808 - 34820
• Main Authors: Hao, Shengnan, Xu, Hang, Ji, Hongyu, Wang, Zhiwu, Zhao, Li, Ji, Zhanlin, Ganchev, Ivan
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Arrhythmia; Cardiovascular disease (CVD); Cardiovascular diseases; convolutional block attention module (CBAM); Diagnosis; ECG signal classification; Electrocardiography; Feature extraction; Heart beat; Heart rate variability; MIT-BIH; Pattern classification; ResNeXt; Signal classification
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2023.3265305

Electrocardiograms (ECG) are the primary basis for the diagnosis of cardiovascular diseases. However, due to the large volume of patients' ECG data, manual diagnosis is time-consuming and laborious. Therefore, intelligent automatic ECG signal classification is an important technique for overcoming the shortage of medical resources. This paper proposes a novel model for inter-patient heartbeat classification, named G2-ResNeXt, which adds a two-fold grouping convolution (G2) to the original ResNeXt structure, as to achieve better automatic feature extraction and classification of ECG signals. Experiments, conducted on the MIT-BIH arrhythmia database, confirm that the proposed model outperforms all state-of-the-art models considered (except the GRNN model for one of the heartbeat classes), by achieving overall accuracy of 96.16%, and sensitivity and precision of 97.09% and 95.90%, respectively, for the ventricular ectopic heartbeats (VEB), and of 80.59% and 82.26%, respectively, for the supraventricular ectopic heartbeats (SVEB).