ECG-Based Heartbeat Classification Using Convolutional Neural Networks

Authors: Jacqueline R. T. Alipo-on, Francesca I. F. Escobar, Myles J. T. Tan, Hezerul Abdul Karim, Nouar AlDahoul

Abstract:

Electrocardiogram (ECG) signal analysis and processing are crucial in the diagnosis of cardiovascular diseases which are considered as one of the leading causes of mortality worldwide. However, the traditional rule-based analysis of large volumes of ECG data is time-consuming, labor-intensive, and prone to human errors. With the advancement of the programming paradigm, algorithms such as machine learning have been increasingly used to perform an analysis on the ECG signals. In this paper, various deep learning algorithms were adapted to classify five classes of heart beat types. The dataset used in this work is the synthetic MIT-Beth Israel Hospital (MIT-BIH) Arrhythmia dataset produced from generative adversarial networks (GANs). Various deep learning models such as ResNet-50 convolutional neural network (CNN), 1-D CNN, and long short-term memory (LSTM) were evaluated and compared. ResNet-50 was found to outperform other models in terms of recall and F1 score using a five-fold average score of 98.88% and 98.87%, respectively. 1-D CNN, on the other hand, was found to have the highest average precision of 98.93%.

Keywords: Heartbeat classification, convolutional neural network, electrocardiogram signals, ECG signals, generative adversarial networks, long short-term memory, LSTM, ResNet-50.

References:

[1] B. London, Arrhythmias, Genomic and Personalized Medicine (2013) 587–601doi:10.1016/b978-0-12-382227- 7.00051-3.
[2] A. L. Goldberger, Z. D. Goldberger, A. Shvilkin, Sinus and escape rhythms, Goldberger’s Clinical Electrocardiography (2013) 114–120doi:10.1016/b978-0-323-08786-5.00013-0.
[3] G. Lippi, F. Sanchis-Gomar, G. Cervellin, Global epidemiology of atrial fibrillation: An increasing epidemic and public health challenge, International Journal of Stroke 16 (2) (2020) 217–221. doi:10.1177/1747493019897870.
[4] E. J. Luz, W. R. Schwartz, G. Ca´mara-Cha´vez, D. Menotti, ECG-based heartbeat classification for arrhythmia detection: A survey, Computer Methods and Programs in Biomedicine 127 (2016) 144–164. doi:10.1016/j.cmpb.2015.12.008.
[5] W. Ullah, I. Siddique, R. M. Zulqarnain, M. M. Alam, I. Ahmad, U. A. Raza, Classification of arrhythmia in heartbeat detection using deep learning, Computational Intelligence and Neuroscience 2021 (2021) 1–13. doi:10.1155/2021/2195922.
[6] M. Faezipour, A. Saeed, S. C. Bulusu, M. Nourani, H. Minn, L. Tamil, A patient-adaptive profiling scheme for ECG beat classification, IEEE transactions on information technology in biomedicine 14 (5) (2010) 1153–1165.
[7] S. Sahoo, M. Dash, S. Behera, S. Sabut, Machine learning approach to detect cardiac arrhythmias in ECG signals: a survey, Irbm 41 (4) (2020) 185–194.
[8] B. Müller, J. Reinhardt, Neural networks introduced, Neural Networks (1990) 12–22doi:10.1007/978-3-642-97239- 32.
[9] S. Kiranyaz, T. Ince, R. Hamila, M. Gabbouj, Convolutional neural networks for patient-specific ECG classification, in: 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2015, pp. 2608–2611. doi:10.1109/EMBC.2015.7318926.
[10] S. Kiranyaz, T. Ince, M. Gabbouj, Real-time patient-specific ECG classification by 1-d convolutional neural networks, IEEE Transactions on Biomedical Engineering 63 (3) (2016) 664–675. doi:10.1109/TBME.2015.2468589.
[11] S. Kiranyaz, T. Ince, M. Gabbouj, Personalized monitoring and advance warning system for cardiac arrhythmias, Scientific Reports 7 (1) (2017). doi:10.1038/s41598-017-09544-z.
[12] F. Li, J. Wu, M. Jia, Z. Chen, Y. Pu, Automated heartbeat classification exploiting convolutional neural network with channel-wise attention, IEEE Access 7 (2019) 122955–122963. doi:10.1109/ACCESS.2019.2938617.
[13] U. R. Acharya, S. L. Oh, Y. Hagiwara, J. H. Tan, M. Adam, A. Gertych, R. S. Tan, A deep convolutional neural network model to classify heartbeats, Computers in Biology and Medicine 89 (2017) 389–396. doi:10.1016/j.compbiomed.2017.08.022.
[14] T. Navamani, Efficient deep learning approaches for health informatics, Deep Learning and Parallel Computing Environment for Bioengineering Systems (2019) 123–137doi:10.1016/b978-0-12-816718-2.00014-2.
[15] M. Chourasia, A. Thakur, S. Gupta, A. Singh, ECG heartbeat classification using CNN, in: 2020 IEEE 7th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON), 2020, pp. 1–6. doi:10.1109/UPCON50219.2020.9376451.
[16] D. Li, J. Zhang, Q. Zhang, X. Wei, Classification of ECG signals based on 1d convolution neural network, in: 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom), 2017, pp. 1–6. doi:10.1109/HealthCom.2017.8210784.
[17] C. Zhang, G. Wang, J. Zhao, P. Gao, J. Lin, H. Yang, Patient-specific ECG classification based on recurrent neural networks and clustering technique, Biomedical Engineering (2017). doi:10.2316/p.2017.852-029.
[18] P. Le, W. Zuidema, Quantifying the vanishing gradient and long distance dependency problem in recursive neu- ral networks and recursive lstms, Proceedings of the 1st Workshop on Representation Learning for NLP (2016). doi:10.18653/v1/w16-1610.
[19] S. Saadatnejad, M. Oveisi, M. Hashemi, Lstm-based ECG classification for continuous monitoring on personal wearable devices, IEEE Journal of Biomedical and Health Informatics 24 (2) (2020) 515–523. doi:10.1109/JBHI.2019.2911367.
[20] S. Singh, S. K. Pandey, U. Pawar, R. R. Janghel, Classification of ECG arrhythmia using recurrent neural networks, Procedia Computer Science 132 (2018) 1290–1297. doi:10.1016/j.procs.2018.05.045.
[21] X. Liu, Y. Si, D. Wang, Lstm neural network for beat classification in ECG identity recognition, Intelligent Automation and Soft Computing (2019). doi:10.31209/2019.100000104.
[22] J. Gao, H. Zhang, P. Lu, Z. Wang, An effective LSTM recurrent network to detect arrhythmia on imbalanced ECG dataset, Journal of Healthcare Engineering 2019 (2019) 1–10. doi:10.1155/2019/6320651.
[23] R. Li, X. Zhang, H. Dai, B. Zhou, Z. Wang, Interpretability analysis of heartbeat classification based on heart-beat activity’s global sequence features and BILSTM-attention neural network, IEEE Access 7 (2019) 109870–109883. doi:10.1109/ACCESS.2019.2933473.
[24] O. Yildirim, U. B. Baloglu, R.-S. Tan, E. J. Ciaccio, U. R. Acharya, A new approach for arrhythmia classification using deep coded features and lstm networks, Computer Methods and Programs in Biomedicine 176 (2019) 121–133. doi:10.1016/j.cmpb.2019.05.004.
[25] S. Chauhan, L. Vig, Anomaly detection in ECG time signals via deep long short-term memory networks, in: 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA), 2015, pp. 1–7. doi:10.1109/DSAA.2015.7344872.
[26] V. G. Sujadevi, K. P. Soman, R. Vinayakumar, Real-time detection of atrial fibrillation from short time single lead ECG traces using recurrent neural networks, Advances in Intelligent Systems and Computing (2017) 212–221doi:10.1007/978- 3-319-68385-018.
[27] Y. Liang, S. Yin, Q. Tang, Z. Zheng, M. Elgendi, Z. Chen, Deep learning algorithm classifies heartbeat events based on electrocardiogram signals, Frontiers in Physiology 11 (2020). doi:10.3389/fphys.2020.569050.
[28] Y. Zhou, H. Zhang, Y. Li, G. Ning, Ecg heartbeat classification based on resnet and BI-LSTM, IOP Conference Series: Earth and Environmental Science 428 (1) (2020) 012014. doi:10.1088/1755-1315/428/1/012014.
[29] C. Han, L. Shi, Ml–resnet: A novel network to detect and locate myocardial infarction using 12 leads ECG, Computer Methods and Programs in Biomedicine 185 (2020) 105138. doi:10.1016/j.cmpb.2019.105138.
[30] E. Jing, H. Zhang, Z. Li, Y. Liu, Z. Ji, I. Ganchev, Ecg heartbeat classification based on an improved resnet-18 model, Computational and Mathematical Methods in Medicine 2021 (2021) 1–13. doi:10.1155/2021/6649970.
[31] C. Brito, A. Machado, A. Sousa, Electrocardiogram beat-classification based on a resnet network, Studies in Health Technology and Informatics 264 (2019) 55–59. doi:10.3233/SHTI190182.
[32] Q. Yao, R. Wang, X. Fan, J. Liu, Y. Li, Multi-class arrhythmia detection from 12-lead varied-length ECG using attention-based time-incremental convolutional neural network, Information Fusion 53 (2020) 174–182. doi:10.1016/j.inffus.2019.06.024.
[33] Y. Gan, J.-c. Shi, W.-m. He, F.-j. Sun, Parallel classification model of arrhythmia based on densenet-bilstm, Biocybernetics and Biomedical Engineering 41 (4) (2021) 1548–1560. doi:10.1016/j.bbe.2021.09.001.
[34] E. Jing, H. Zhang, Z. Li, Y. Liu, Z. Ji, I. Ganchev, Ecg heartbeat classification based on an improved resnet-18 model, Computational and Mathematical Methods in Medicine 2021 (2021) 1–13. doi:10.1155/2021/6649970.
[35] J. Venton, P. M. Harris, A. Sundar, N. A. Smith, P. J. Aston, Robustness of convolutional neural networks tonbsp;physiological electrocardiogram noise, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 379 (2212) (2021). doi:10.1098/rsta.2020.0262.
[36] E. Essa, X. Xie, An ensemble of deep learning-based multi-model for ECG heartbeats arrhythmia classification, IEEE Access 9 (2021) 103452–103464. doi:10.1109/ACCESS.2021.3098986.
[37] M. A. Ahamed, K. A. Hasan, K. F. Monowar, N. Mashnoor, M. A. Hossain, ECG heartbeat classification using ensemble of efficient machine learning approaches on imbalanced datasets, in: 2020 2nd International Conference on Advanced Information and Communication Technology (ICAICT), 2020, pp. 140–145. doi:10.1109/ICAICT51780.2020.9333534.
[38] P. Nejedly, A. Ivora, R. Smisek, I. Viscor, Z. Koscova, P. Jurak, F. Plesinger, Classification of ECG using ensemble of residual CNNs with attention mechanism, in: 2021 Computing in Cardiology (CinC), Vol. 48, 2021, pp. 1–4. doi:10.23919/CinC53138.2021.9662723.
[39] B. K. Iwana, S. Uchida, An empirical survey of data augmentation for time series classification with neural networks, PLOS ONE 16 (7) (2021). doi:10.1371/journal.pone.0254841.
[40] Q. Wen, L. Sun, F. Yang, X. Song, J. Gao, X. Wang, H. Xu, Time series data augmentation for deep learning: A survey, Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (2021). doi:10.24963/ijcai.2021/631.
[41] I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio, Generative adversarial networks (2014). doi:10.48550/ARXIV.1406.2661 URL https://arxiv.org/abs/1406.2661
[42] A. Rath, D. Mishra, G. Panda, S. C. Satapathy, Heart disease detection using deep learning methods from imbalanced ECG samples, Biomedical Signal Processing and Control 68 (2021) 102820. doi:10.1016/j.bspc.2021.102820.
[43] A. M. Shaker, M. Tantawi, H. A. Shedeed, M. F. Tolba, Generalization of convolutional neural networks for ECG classification using generative adversarial networks, IEEE Access 8 (2020) 35592–35605. doi:10.1109/ACCESS.2020.2974712.
[44] S. Fazeli, Ecg heartbeat categorization dataset (2018). URL https://www.kaggle.com/datasets/shayanfazeli/heartbeat
[45] M. Polo, mitbihwithsynthetic (2021). URL https://www.kaggle.com/datasets/polomarco/mitbih-with-synthetic
[46] G. B. Moody, R. G. Mark, Mit-bih arrhythmia database (1997). URL http://ECG.mit.edu/dbinfo.html
[47] A. AAMI, A. EC57, (r) 2008-testing and reporting performance results of cardiac rhythm and st segment measurement algorithms, American National Standards Institute, Arlington, VA, USA (2008).
[48] S. Kiranyaz, O. Avci, O. Abdeljaber, T. Ince, M. Gabbouj, D. J. Inman, 1d convolutional neural networks and applications: A survey 151 107398. doi:10.1016/j.ymssp.2020.107398. URL https://linkinghub.elsevier.com/retrieve/pii/S0888327020307846
[49] P. Le, W. Zuidema, Quantifying the vanishing gradient and long distance dependency problem in recursive neural networks and recursive LSTMs, in: Proceedings of the 1st Workshop on Representation Learning for NLP, Association for Computational Linguistics, Berlin, Germany, 2016, pp. 87–93. doi:10.18653/v1/W16-1610. URL https://aclanthology.org/W16-1610
[50] S. Dey, R. Pal, S. Biswas, Deep learning algorithms for efficient analysis of ECG signals to detect heart disorders IntechOpen. URL https://www.intechopen.com/online-first/81360
[51] T. Lodaya, keras-signs-resnet, https://github.com/tejaslodaya/keras-signs-resnet.git (2017).
[52] L. Niu, C. Chen, H. Liu, S. Zhou, M. Shu, A deep-learning approach to ECG classification based on adversarial domain adaptation 8 (4) 437. doi:10.3390/healthcare8040437. URL https://www.mdpi.com/2227-9032/8/4/437