(46-6) 17 * << * >> * Russian * English * Content * All Issues

Arrhythmia detection using resampling and deep learning methods on unbalanced data
E.Y. Shchetinin 1, A.G. Glushkova 2

1 Financial University under the government of the Russian Federation,
125993, Moscow, 49 Leningradsky Prospekt, Russia;
2 Endeavor, London W4 5HR, Chiswick Park, 566 Chiswick High Road, United Kingdom

 PDF, 864 kB

DOI: 10.18287/2412-6179-CO-1112

Pages: 980-987.

Full text of article: English language.

Abstract:
Due to cardiovascular diseases millions of people die around the world. One way to detect abnormality in the heart condition is with the help of electrocardiogram signal (ECG) analysis. This paper's goal is to use machine learning and deep learning methods such as Support Vector Machines (SVM), Random Forests, Light Gradient Boosting Machine (LightGBM), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (BLSTM) to classify arrhythmias, where particular interest represent the rare cases of disease.
     In order to deal with the problem of imbalance in the dataset we used resampling methods such as SMOTE Tomek-Links and SMOTE ENN to improve the representation ration of the minority classes. Although the machine learning models did not improve a lot when trained on the resampled dataset, the deep learning models showed more impressive results. In particular, LSTM model fitted on dataset resampled using SMOTE ENN method provides the most optimal precision-recall trade-off for the minority classes Supraventricular beat and Fusion of ventricular and normal beat, with recall of 83 % and 88 % and precision of 74 % and 66 % for the two classes respectively, whereas the macro-weighted recall is 92 % and precision is 82 % .

Keywords:
machine learning, deep learning, ECG, resampling, arrhythmia.

Citation:
Shchetinin EY, Glushkova AG. Arrhythmia detection using resampling and deep learning methods on unbalanced data. Computer Optics 2022; 46(6): 980-987. DOI: 10.18287/2412-6179-CO-1112.

Acknowledgements:
The authors would like to acknowledge the use of the University of Oxford Advanced Research Computing (ARC) facility in carrying out this work: http://dx.doi.org/10.5281/zenodo.22558. Specifications: https://www.arc.ox.ac.uk/arc-systems.

References:
  1. WHO list of priority medical devices for management of cardiovascular diseases and diabetes. In Book: WHO medical device technical series. Geneva: World Health Organization; 2021. License: CC BY-NC-SA 3.0 IGO. ISBN: 978-92-4-002797-8. Source: <https://www.who.int/publications/i/item/9789240027978>.
  2. Hong S, Zhou Y, Shang J, Xiao C, Sun J. Opportunities and challenges of deep learning methods for electrocardiogram data: A systematic review. Comput Biol Med 2020; 122: 103801. DOI: 10.1016/j.compbiomed.2020.103801.
  3. Haibo H, Yunqian M, eds. Imbalanced learning: Foundations, algorithms, and applications. Hoboken, New Jersey: John Wiley & Sons Inc; 2013. ISBN: 978-1-118-07462-6. DOI: 10.1002/9781118646106.
  4. Murat F, Yildirim O, Talo M, Baloglu UB, Demir Y, Acharya UR. Application of deep learning techniques for heartbeats detection using ECG signals-analysis and review. Comput Biol Med 2020; 120: 103726. DOI: 10.1016/j.compbiomed.2020.103726.
  5. Hannun AY, Rajpurkar P, Haghpanahi M, Tison GH, Bourn C, Turakhia MP, Ng AY. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med 2019; 25(1): 65-69. DOI: 10.1038/s41591-018-0268-3.
  6. Kachuee M, Fazeli S and Sarrafzadeh M. ECG Heartbeat classification: A deep transferable representation. IEEE Int Conf on Healthcare Informatics (ICHI), New York City, NY, USA 2018: 443-444. DOI: 10.1109/ICHI.2018.00092.
  7. Zhong ZX, Michael AJ, Lun ZJ, Yue DH. ECG classification using machine learning techniques and smote oversampling technique. 2nd Int Conf on Image Processing and Machine Vision (IPMV 2020) 2020: 10-13. DOI: 10.1145/3421558.3421560.
  8. Chawla N, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: Synthetic minority over-sampling technique. J Artif Intell Res 2002; 16: 321-357. DOI: 10.1613/jair.953.
  9. He H, Garcia EA. Learning from imbalanced data sets. IEEE Trans Knowl Data Eng 2009; 21(9): 1263-1284. DOI: 10.1109/TKDE.2008.239.
  10. Avanzato R, Beritelli F. Automatic ECG diagnosis using convolutional neural network. Electronics 2020; 9(6): 951. DOI: 10.3390/electronics9060951.
  11. Greff K, Srivastava R, Koutnik J, Steunebrink BR, Schmidhuber J. LSTM: A search space odyssey. IEEE Trans Neural Netw Learn Syst 2017; 28(10): 2222-2232. DOI: 10.1109/TNNLS.2016.2582924.
  12. Liu G, Guo J. Bidirectional LSTM with attention mechanism and convolutional layer for text classification. Neurocomputing 2019; 337(C): 325-338. DOI: 10.1016/j.neucom.2019.01.078.
  13. Rao G, Huang W, Feng Z, Cong Q. LSTM with sentence representations for document-level sentiment classification. Neurocomputing 2018; 308: 49-57. DOI: 10.1016/j.neucom.2018.04.045.
  14. Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adam M, Gertych A, Tan RS. A deep convolutional neural network model to classify heartbeats. Comput Biol Med 2017; 89: 389-396. DOI: 10.1016/j.compbiomed.2017.08.022.
  15. Martis RJ, Acharya UR, Lim CM, Mandana K, Ray AK, Chakraborty C. Application of higher order cumulant features for cardiac health diagnosis using ECG signals. Int J Neural Syst 2013; 23(04): 1350014. DOI: 10.1142/S0129065713500147.
  16. Li T, Zhou M. ECG classification using wavelet packet entropy and random forests. Entropy 2016; 18(8): 285. DOI: 10.3390/e18080285.
  17. Shoughi A, Dowlatshahi MB. A practical system based on CNN-BLSTM network for accurate classification of ECG heartbeats of MITBIH imbalanced dataset. 2021 26th Int Computer Conf Computer Society of Iran (CSICC) 2021: 1-6. DOI: 10.1109/CSICC52343.2021.9420620.
  18. Schetinin E. Automatic arrhythmia detection based on the analysis of electrocardiograms with deep learning. Herald of Computer and Information Technologies 2021; 18(5): 18-27. DOI: 10.14489/vkit.2021.05.pp.018-027.
  19. Gaowei X, Tianhe R, Yu C, Wenliang C. A one-dimensional CNN-LSTM model for epileptic seizure recognition using EEG signal analysis. Front Neurosci 2020; 14: 578126. DOI: 10.3389/fnins.2020.578126.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20