Automatic heartbeat classification using S-shaped reconstruction and a squeeze-and-excitation residual network

Xiangyu Li; Feng Zhang; Zhenjuan Sun; Dong Li; Xiaoming Kong; Yatao Zhang

doi:10.1016/j.compbiomed.2021.105108

Automatic heartbeat classification using S-shaped reconstruction and a squeeze-and-excitation residual network

Comput Biol Med. 2022 Jan:140:105108. doi: 10.1016/j.compbiomed.2021.105108. Epub 2021 Dec 2.

Authors

Xiangyu Li¹, Feng Zhang¹, Zhenjuan Sun², Dong Li¹, Xiaoming Kong³, Yatao Zhang⁴

Affiliations

¹ School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China.
² Information Department, The Eighth People's Hospital of Qingdao, China.
³ School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China. Electronic address: xmkong@sdu.edu.cn.
⁴ School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China. Electronic address: zytboy@sdu.edu.cn.

PMID: 34875410
DOI: 10.1016/j.compbiomed.2021.105108

Abstract

To facilitate the identification of arrhythmia, in this study, an S-shaped reconstruction method was proposed, and a two-dimensional (2-D) 19-layer deep squeeze-and-excitation residual network (SE-ResNet) was used to classify heartbeats. The proposed method has three steps. The first step involves data preprocessing, which includes denoising of the original electrocardiogram (ECG) data, removing of baseline drift, heartbeat extraction, and data balancing using a synthetic minority oversampling technique algorithm. Subsequently, the extracted one-dimensional heartbeat series is transformed into a 2-D matrix by employing the novel S-shaped reconstruction method for determining the relationship between distant points in an ECG series. Finally, the 2-D 19-layer SE-ResNet is used to divide the 2-D heartbeat matrix into five heartbeat categories, namely normal, supraventricular ectopic, ventricular ectopic, fusion, and unknown beats, in accordance with the American National Standards Institute/Advancement of Medical Instrumentation standard, and 10-fold cross-validation is employed to train the 2-D 19-layer SE-ResNet. The accuracy, positive prediction rate, sensitivity, and specificity of the proposed method reached 99.61%, 93.87%, 93.78%, and 99.27%, respectively. The results indicated that the S-shaped reconstruction method can be helpful for acquiring additional information from ECG heartbeat data.

Keywords: Arrhythmia heartbeat; S- shaped reconstruction; SE-ResNet.