Inter-patient ECG heartbeat classification for arrhythmia classification: a new approach of multi-layer perceptron with weight capsule and sequence-to-sequence combination
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...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-09-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2023.1247587/full |
| _version_ | 1797671361928232960 |
|---|---|
| author | Chenchen Zhou Chenchen Zhou Xiangkui Li Xiangkui Li Fan Feng Jian Zhang He Lyu Weixuan Wu Xuezhi Tang Bin Luo Dong Li Dong Li Wei Xiang Dengju Yao |
| author_facet | Chenchen Zhou Chenchen Zhou Xiangkui Li Xiangkui Li Fan Feng Jian Zhang He Lyu Weixuan Wu Xuezhi Tang Bin Luo Dong Li Dong Li Wei Xiang Dengju Yao |
| author_sort | Chenchen Zhou |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-11T21:14:16Z |
| format | Article |
| id | doaj.art-dc9b75e90e5a4d4f9fcced117ea97f9f |
| institution | Directory Open Access Journal |
| issn | 1664-042X |
| language | English |
| last_indexed | 2024-03-11T21:14:16Z |
| publishDate | 2023-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physiology |
| spelling | doaj.art-dc9b75e90e5a4d4f9fcced117ea97f9f2023-09-29T05:39:41ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2023-09-011410.3389/fphys.2023.12475871247587Inter-patient ECG heartbeat classification for arrhythmia classification: a new approach of multi-layer perceptron with weight capsule and sequence-to-sequence combinationChenchen Zhou0Chenchen Zhou1Xiangkui Li2Xiangkui Li3Fan Feng4Jian Zhang5He Lyu6Weixuan Wu7Xuezhi Tang8Bin Luo9Dong Li10Dong Li11Wei Xiang12Dengju Yao13Key Laboratory of Electronic and Information Engineering, State Ethnic Affairs Commission, Southwest Minzu University, Chengdu, ChinaGuangxi Key Laboratory of Digital Infrastructure, Guangxi Information Center, Nanning, ChinaKey Laboratory of Electronic and Information Engineering, State Ethnic Affairs Commission, Southwest Minzu University, Chengdu, ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin, ChinaGuangxi Key Laboratory of Digital Infrastructure, Guangxi Information Center, Nanning, ChinaWest China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu, ChinaKey Laboratory of Electronic and Information Engineering, State Ethnic Affairs Commission, Southwest Minzu University, Chengdu, ChinaKey Laboratory of Electronic and Information Engineering, State Ethnic Affairs Commission, Southwest Minzu University, Chengdu, ChinaKey Laboratory of Electronic and Information Engineering, State Ethnic Affairs Commission, Southwest Minzu University, Chengdu, ChinaSichuan Huhui Software Co., Ltd., Mianyang, ChinaWest China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu, ChinaMed-X Center for Informatics, Sichuan University, Chengdu, ChinaKey Laboratory of Electronic and Information Engineering, State Ethnic Affairs Commission, Southwest Minzu University, Chengdu, ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin, ChinaObjective: 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.https://www.frontiersin.org/articles/10.3389/fphys.2023.1247587/fullarrhythmia classificationmultilayer perceptronweight capsuleMIT-BIHdeep learning |
| spellingShingle | Chenchen Zhou Chenchen Zhou Xiangkui Li Xiangkui Li Fan Feng Jian Zhang He Lyu Weixuan Wu Xuezhi Tang Bin Luo Dong Li Dong Li Wei Xiang Dengju Yao Inter-patient ECG heartbeat classification for arrhythmia classification: a new approach of multi-layer perceptron with weight capsule and sequence-to-sequence combination Frontiers in Physiology arrhythmia classification multilayer perceptron weight capsule MIT-BIH deep learning |
| title | Inter-patient ECG heartbeat classification for arrhythmia classification: a new approach of multi-layer perceptron with weight capsule and sequence-to-sequence combination |
| title_full | Inter-patient ECG heartbeat classification for arrhythmia classification: a new approach of multi-layer perceptron with weight capsule and sequence-to-sequence combination |
| title_fullStr | Inter-patient ECG heartbeat classification for arrhythmia classification: a new approach of multi-layer perceptron with weight capsule and sequence-to-sequence combination |
| title_full_unstemmed | Inter-patient ECG heartbeat classification for arrhythmia classification: a new approach of multi-layer perceptron with weight capsule and sequence-to-sequence combination |
| title_short | Inter-patient ECG heartbeat classification for arrhythmia classification: a new approach of multi-layer perceptron with weight capsule and sequence-to-sequence combination |
| title_sort | inter patient ecg heartbeat classification for arrhythmia classification a new approach of multi layer perceptron with weight capsule and sequence to sequence combination |
| topic | arrhythmia classification multilayer perceptron weight capsule MIT-BIH deep learning |
| url | https://www.frontiersin.org/articles/10.3389/fphys.2023.1247587/full |
| work_keys_str_mv | AT chenchenzhou interpatientecgheartbeatclassificationforarrhythmiaclassificationanewapproachofmultilayerperceptronwithweightcapsuleandsequencetosequencecombination AT chenchenzhou interpatientecgheartbeatclassificationforarrhythmiaclassificationanewapproachofmultilayerperceptronwithweightcapsuleandsequencetosequencecombination AT xiangkuili interpatientecgheartbeatclassificationforarrhythmiaclassificationanewapproachofmultilayerperceptronwithweightcapsuleandsequencetosequencecombination AT xiangkuili interpatientecgheartbeatclassificationforarrhythmiaclassificationanewapproachofmultilayerperceptronwithweightcapsuleandsequencetosequencecombination AT fanfeng interpatientecgheartbeatclassificationforarrhythmiaclassificationanewapproachofmultilayerperceptronwithweightcapsuleandsequencetosequencecombination AT jianzhang interpatientecgheartbeatclassificationforarrhythmiaclassificationanewapproachofmultilayerperceptronwithweightcapsuleandsequencetosequencecombination AT helyu interpatientecgheartbeatclassificationforarrhythmiaclassificationanewapproachofmultilayerperceptronwithweightcapsuleandsequencetosequencecombination AT weixuanwu interpatientecgheartbeatclassificationforarrhythmiaclassificationanewapproachofmultilayerperceptronwithweightcapsuleandsequencetosequencecombination AT xuezhitang interpatientecgheartbeatclassificationforarrhythmiaclassificationanewapproachofmultilayerperceptronwithweightcapsuleandsequencetosequencecombination AT binluo interpatientecgheartbeatclassificationforarrhythmiaclassificationanewapproachofmultilayerperceptronwithweightcapsuleandsequencetosequencecombination AT dongli interpatientecgheartbeatclassificationforarrhythmiaclassificationanewapproachofmultilayerperceptronwithweightcapsuleandsequencetosequencecombination AT dongli interpatientecgheartbeatclassificationforarrhythmiaclassificationanewapproachofmultilayerperceptronwithweightcapsuleandsequencetosequencecombination AT weixiang interpatientecgheartbeatclassificationforarrhythmiaclassificationanewapproachofmultilayerperceptronwithweightcapsuleandsequencetosequencecombination AT dengjuyao interpatientecgheartbeatclassificationforarrhythmiaclassificationanewapproachofmultilayerperceptronwithweightcapsuleandsequencetosequencecombination |