Inter-patient ECG heartbeat classification for arrhythmia classification: a new approach of multi-layer perceptron with weight capsule and sequence-to-sequence combination

Chenchen Zhou; Xiangkui Li; Fan Feng; Jian Zhang; He Lyu; Weixuan Wu; Xuezhi Tang; Bin Luo; Dong Li; Wei Xiang; Dengju Yao

doi:10.3389/fphys.2023.1247587

Inter-patient ECG heartbeat classification for arrhythmia classification: a new approach of multi-layer perceptron with weight capsule and sequence-to-sequence combination

Front Physiol. 2023 Sep 28:14:1247587. doi: 10.3389/fphys.2023.1247587. eCollection 2023.

Authors

Chenchen Zhou^#^{1

2}, Xiangkui Li^#^{1

3}, Fan Feng², Jian Zhang⁴, He Lyu¹, Weixuan Wu¹, Xuezhi Tang¹, Bin Luo⁵, Dong Li^{4

6}, Wei Xiang¹, Dengju Yao³

Affiliations

¹ Key Laboratory of Electronic and Information Engineering, State Ethnic Affairs Commission, Southwest Minzu University, Chengdu, China.
² Guangxi Key Laboratory of Digital Infrastructure, Guangxi Information Center, Nanning, China.
³ School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China.
⁴ West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu, China.
⁵ Sichuan Huhui Software Co., Ltd., Mianyang, China.
⁶ Med-X Center for Informatics, Sichuan University, Chengdu, China.

^# Contributed equally.

Abstract

Objective: The objective of this research is to construct a method to alleviate the problem of sample imbalance in classification, especially for arrhythmia classification. This approach can improve the performance of the model without using data enhancement. Methods: In this study, we have developed a new Multi-layer Perceptron (MLP) block and have used a Weight Capsule (WCapsule) network with MLP combined with sequence-to-sequence (Seq2Seq) network to classify arrhythmias. Our work is based on the MIT-BIH arrhythmia database, the original electrocardiogram (ECG) data is classified according to the criteria recommended by the American Association for Medical Instrumentation (AAMI). Also, our method's performance is further evaluated. Results: The proposed model is evaluated using the inter-patient paradigm. Our proposed method shows an accuracy (ACC) of 99.88% under sample imbalance. For Class N, sensitivity (SEN) is 99.79%, positive predictive value (PPV) is 99.90%, and specificity (SPEC) is 99.19%. For Class S, SEN is 97.66%, PPV is 96.14%, and SPEC is 99.85%. For Class V, SEN is 99.97%, PPV is 99.07%, and SPEC is 99.94%. For Class F, SEN is 97.94%, PPV is 98.70%, and SPEC is 99.99%. When using only half of the training sample, our method shows that the SEN of Class N and V is 0.97% and 5.27% higher than the traditional machine learning algorithm. Conclusion: The proposed method combines MLP, weight capsule network with Seq2seq network, effectively addresses the problem of sample imbalance in arrhythmia classification, and produces good performance. Our method also shows promising potential in less samples.

Keywords: MIT-BIH; arrhythmia classification; deep learning; multilayer perceptron; weight capsule.

Grants and funding

This work was supported by National Nature Science Foundation (72174172, 71774134) and Open Project Program of Guangxi Key Laboratory of Digital Infrastructure (Grant Number: GXDIOP2023013). And this research was supported by the Fundamental Research Funds for Central University, Southwest Minzu University (2022NYXXS102).