A Deep Learning Approach for Detecting Atrial Fibrillation using RR Intervals of ECG
Abstract
Purpose: Atrial Fibrillation (AF) is one of the most common types of heart arrhythmias observed in clinical practice. AF can be detected using an Electrocardiogram (ECG). ECG signals are time-varying and nonlinear in nature. Hence, it is very difficult for a physician to manually perform accurate and rapid classification of different heart rhythms.
Materials and Methods: In this paper, we propose a method using Discrete Wavelet Transform (DWT) with db6 as the basis function for denoising ECG signal.
Results: The denoised ECG is smoothened using the Savitzky- Golay filter. Deep learning methods, such as a combination of Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) (CNN-LSTM) and ResNet18 are used for the accurate classification of ECG signals using Physionet Challenge 2017 database.
Conclusion: With a 10-fold cross-validation method the model provided overall accuracy of 98.25% with the CNN-LSTM classifier.
[2] Tsao, Connie W., Aaron W. Aday, Zaid I. Almarzooq, Alvaro Alonso, Andrea Z. Beaton, Marcio S. Bittencourt, Amelia K. Boehme et al. "Heart Disease and Stroke Statistics—2022 Update: A Report From the American Heart Association." Circulation 145, no. 8 (2022): e153-e639.https://doi.org/10.1161/CIR.0000000000001052.
[3] Z. Ebrahimi, M. Loni, M. Daneshtalab, and A. Gharehbaghi, “A review on deep learning methods for ECG arrhythmia classification,” Expert Syst. with Appl. X, vol. 7, p. 100033, 2020; https://doi: 10.1016/j.eswax.2020.100033.
[4] G. Lippi, F. Sanchis-Gomar, and G. Cervellin, “Global epidemiology of atrial fibrillation: An increasing epidemic and public health challenge,” Int. J. Stroke, vol. 16, no. 2, pp. 217–221, 2021; https://doi: 10.1177/1747493019897870.
[5] M. Rizwan, B. M. Whitaker, and D. V. Anderson, “AF detection from ECG recordings using feature selection, sparse coding, and ensemble learning,” Physiol. Meas., vol. 39, no. 12, 2018; https://doi: 10.1088/1361-6579/aaf35b.
[6] B. M. Whitaker, M. Rizwan, V. B. Aydemir, J. M. Rehg, and D. V. Anderson, “AF classification from ECG recording using feature ensemble and sparse coding,” Comput. Cardiol. (2010)., vol. 44, pp. 1–4, 2017; https://doi: 10.22489/CinC.2017.174-192.
[7] M. Zabihi, A. B. Rad, A. K. Katsaggelos, S. Kiranyaz, S. Narkilahti, and M. Gabbouj, “Detection of atrial fibrillation in ECG hand-held devices using a random forest classifier,” Comput. Cardiol. (2010)., vol. 44, pp. 1–4, 2017; https://doi: 10.22489/CinC.2017.069-336.
[8] Datta, Shreyasi, Chetanya Puri, Ayan Mukherjee, Rohan Banerjee, Anirban Dutta Choudhury, Rituraj Singh, Arijit Ukil, Soma Bandyopadhyay, Arpan Pal, and Sundeep Khandelwal. "Identifying normal, AF and other abnormal ECG rhythms using a cascaded binary classifier." In 2017 Computing in cardiology (cinc), pp. 1-4. IEEE, 2017; https://doi: 10.22489/CinC.2017.173-154.
[9] Kropf, Martin, D. Hayn, D. Morris, Aravind-Kumar Radhakrishnan, E. Belyavskiy, A. Frydas, E. Pieske-Kraigher,
B. Pieske, and G. Schreier. "Cardiac anomaly detection based on time and frequency domain features using tree-based
classifiers." Physiological measurement 39, no. 11 (2018):
114001; https://doi.org/10.1088/1361-6579/aae13e.
[10] R. J. Martis, U. R. Acharya, H. Prasad, C. K. Chua, C. M. Lim, and J. S. Suri, “Application of higher order statistics for atrial arrhythmia classification,” Biomed. Signal Process. Control, vol. 8, no. 6, pp. 888–900, 2013; https://doi: 10.1016/j.bspc.2013.08.008.
[11] N. Ahmed and Y. Zhu, “Early detection of atrial fibrillation based on ecg signals,” Bioengineering, vol. 7, no. 1, pp. 1–17, 2020; https://doi: 10.3390/bioengineering7010016.
[12] M. Kumar, R. B. Pachori, and U. Rajendra Acharya, “Automated diagnosis of atrial fibrillation ECG signals using entropy features extracted from flexible analytic wavelet transform,” Biocybern. Biomed. Eng., vol. 38, no. 3, pp. 564–573, 2018; https://doi: 10.1016/j.bbe.2018.04.004.
[13] Liu, Na, Muyi Sun, Ludi Wang, Wei Zhou, Hao Dang, and Xiaoguang Zhou. "A supportvector machine approach for
AF classification from a short single-lead ECG recording." Physiological Measurement 39, no. 6 (2018): 064004;
https://doi.org/10.1088/1361-6579/aac7aa
[14] L. Zhao, C. Liu, S. Wei, Q. Shen, F. Zhou, and J. Li, “A new entropy-based atrial fibrillation detection method for Scanning Wearable ECG recordings,” Entropy, vol. 20, no. 12, pp. 1–17, 2018; https://doi: 10.3390/e20120904.
[15] Shao, Minggang, Guangyu Bin, Shuicai Wu, Guanghong Bin, Jiao Huang, and Zhuhuang Zhou.
Detection of atrial fibrillation from ECG recordings using decisiontree ensemble with multi-level
features." Physiological measurement 39, no. 9 (2018): 094008; https://doi.org/10.1088/1361-6579/aadf48
[16] T. Radhakrishnan, J. Karhade, S. K. Ghosh, P. R. Muduli, R. K. Tripathy, and U. R. Acharya, “AFCNNet: Automated detection of AF using chirplet transform and deep convolutional bidirectional long short term memory network with ECG signals,” Comput. Biol. Med., vol. 137, no. May, p. 104783, 2021; https://doi: 10.1016/j.compbiomed.2021.104783.
[17] X. Chen et al., “Atrial fibrillation detection based on multi-feature extraction and convolutional neural network for processing ECG signals,” Comput. Methods Programs Biomed., vol. 202, 2021; https://doi: 10.1016/j.cmpb.2021.106009.
[18] X. Wu, Z. Sui, C. H. Chu, and G. Huang, “Automatic atrial fibrillation detection from short ECG signals: A hybrid deep learning approach,” IISE Trans. Healthc. Syst. Eng., vol. 0, no. 0, pp. 1–19, 2021; https://doi: 10.1080/24725579.2021.1919249.
[19] G. Bortolan, I. Christov, and I. Simova, “Potential of rule-based methods and deep learning architectures for ecg diagnostics,” Diagnostics, vol. 11, no. 9, pp. 1–13, 2021; https://doi: 10.3390/diagnostics11091678.
[20] H. C. Seo, S. Oh, H. Kim, and S. Joo, “ECG data dependency for atrial fibrillation detection based on residual networks,” Sci. Rep., vol. 11, no. 1, pp. 1–8, 2021; https://doi: 10.1038/s41598-021-97308-1.
[21] P. Zhang et al., “Global hybrid multi-scale convolutional network for accurate and robust detection of atrial fibrillation using single-lead ECG recordings,” Comput. Biol. Med., vol. 139, no. July, p. 104880, 2021; https://doi: 10.1016/j.compbiomed.2021.104880.
[22] L. Dagher, C. H. Lim, A. Dhore, M. Crawford, T. Ayoub, and N. Marrouche, “Deep Neural Network for Accurate Af Detection on a Smartphone-Derived Single-Lead Ecg,” J. Am. Coll. Cardiol., vol. 77, no. 18, p. 3249, 2021; https://doi: 10.1016/s0735-1097(21)04603-9.
[23] Q. Xie, X. Wang, H. Sun, Y. Zhang, and X. Lu, “ECG Signal Detection and Classification of Heart Rhythm Diseases Based on ResNet and LSTM,” Adv. Math. Phys., vol. 2021, 2021; https://doi: 10.1155/2021/5862017.
[24] Feng, Kunye, and Zile Fan. "A novel bidirectional LSTM network based on scale factor for atrial
fibrillation signals classification." Biomedical Signal Processing and Control 76 (2022): 103663;
https://doi.org/10.1016/j.bspc.2022.103663
[25] Manisha, S. K. Dhull, and K. K. Singh, “ECG Beat Classifiers: A Journey from ANN to DNN,” Procedia Comput. Sci., vol. 167, no. Iccids 2019, pp. 747–759, 2020; https://doi: 10.1016/j.procs.2020.03.340.
[26] F. Murat, O. Yildirim, M. Talo, U. B. Baloglu, Y. Demir, and U. R. Acharya, “Application of deep learning techniques for heartbeats detection using ECG signals-analysis and review,” Comput. Biol. Med., vol. 120, no. February, p. 103726, 2020; https://doi: 10.1016/j.compbiomed.2020.103726.
[27] Clifford, Gari D., Chengyu Liu, Benjamin Moody, H. Lehman Li-wei, Ikaro Silva, Qiao Li, A. E. Johnson, and Roger G. Mark. "AF classification from a short single lead ECG recording: The PhysioNet/computing in cardiology challenge 2017." In 2017 Computing in Cardiology (CinC), pp. 1-4. IEEE, 2017; https:// doi: 10.22489/CinC.2017.065-469.
[28] R. J. Martis, U. R. Acharya, and L. C. Min, “ECG beat classification using PCA, LDA, ICA and Discrete Wavelet Transform,” Biomed. Signal Process. Control, vol. 8, no. 5, pp. 437–448, 2013; https://doi: 10.1016/j.bspc.2013.01.005.
[29] S. K. Shrikanth Rao and R. J. Martis, “Machine Learning Based Decision Support System for Atrial Fibrillation Detection using Electrocardiogram,” 2020 IEEE Int. Conf. Distrib. Comput. VLSI, Electr. Circuits Robot. Discov. 2020 - Proc., pp. 263–266, 2020; https://doi: 10.1109/DISCOVER50404.2020.9278124.
[30] R. J. Martis, U. R. Acharya, and H. Adeli, “Current methods in electrocardiogram characterization,” Comput. Biol. Med., vol. 48, no. 1, pp. 133–149, 2014; https://doi: 10.1016/j.compbiomed.2014.02.012.
[31] V. Sangeetha and K. J. R. Prasad, “Syntheses of novel derivatives of 2-acetylfuro[2,3-a]carbazoles, benzo[1,2-b]-1,4-thiazepino[2,3-a]carbazoles and 1-acetyloxycarbazole-2- carbaldehydes,” Indian J. Chem. - Sect. B Org. Med. Chem., vol. 45, no. 8, pp. 1951–1954, 2006; https://doi: 10.1002/chin.200650130.
[32] S. K. Shrikanth Rao, M. H. Kolekar, and R. J. Martis, “A Deep Learning Based Assisted Tool for Atrial Fibrillation Detection Using Electrocardiogram,” 2021 2nd Glob. Conf. Adv. Technol. GCAT 2021, vol. 560098, pp. 2–5, 2021; https:// doi: 10.1109/GCAT52182.2021.9587503.
[33] G. Petmezas et al., “Automated Atrial Fibrillation Detection using a Hybrid CNN-LSTM Network on Imbalanced ECG Datasets,” Biomed. Signal Process. Control, vol. 63, no. March 2020, p. 102194, 2021; https://doi: 10.1016/j.bspc.2020.102194.
[34] J. Rubin, S. Parvaneh, A. Rahman, B. Conroy, and S. Babaeizadeh, “Densely connected convolutional networks for detection of atrial fibrillation from short single-lead ECG recordings,” J. Electrocardiol., vol. 51, no. 6, pp. S18–S21, 2018; https://doi: 10.1016/j.jelectrocard.2018.08.008.
[35] F. A. Rivera Sánchez and J. A. González Cervera, “ECG Classification Using Artificial Neural Networks,” J. Phys. Conf. Ser., vol. 1221, no. 1, 2019; https://doi: 10.1088/1742-6596/1221/1/012062.
[36] C. H. Hsieh, Y. S. Li, B. J. Hwang, and C. H. Hsiao, “Detection of atrial fibrillation using 1D convolutional neural network,” Sensors (Switzerland), vol. 20, no. 7, 2020; https://doi: 10.3390/s20072136.
[37] S. R. S. K, K. K, Anushree, M. Akhila, Archana, and R. J. Martis, “Deep Learning Based Atrial Fibrillation Detection Using Effective Denoising Methods and Dimensionality Reduction Techniques,” pp. 01–07, 2021; https:// doi: 10.1109/r10-htc53172.2021.9641550.
[38] S. . Shrikanth Rao, M. H. Kolekar, and R. J. Martis, “Frequency Domain Features Based Atrial Fibrillation Detection Using Machine Learning And Deep Learning Approach,” pp. 1–6, 2021; https://doi: 10.1109/conecct52877.2021.9622533.
[39] J. Shi, C. Chen, H. Liu, Y. Wang, M. Shu, and Q. Zhu, “Automated Atrial Fibrillation Detection Based on Feature Fusion Using Discriminant Canonical Correlation Analysis,” Comput. Math. Methods Med., vol. 2021, 2021; https://doi: 10.1155/2021/6691177.
[40] Q. H. Nguyen, B. P. Nguyen, T. B. Nguyen, T. T. T. Do, J. F. Mbinta, and C. R. Simpson, “Stacking segment-based CNN with SVM for recognition of atrial fibrillation from single-lead ECG recordings,” Biomed. Signal Process. Control, vol. 68, no. January, p. 102672, 2021; https://doi: 10.1016/j.bspc.2021.102672.
[41] Fayyazifar, Najmeh. "An accurate CNN Architecture for Atrial Fibrillation Detection Using Neural Architecture
Search." In 2020 28th European Signal Processing Conference (EUSIPCO), pp. 1135- 1139. IEEE, 2021;
https://doi.10.23919/Eusipco47968.2020.9287496.
[42] Wesselius, Fons J., Mathijs S. van Schie, Natasja MS De Groot, and Richard C. Hendriks. "An accurate and efficient
method to train classifiers for atrial fibrillation detection in ECGs: Learning by asking better questions." Computers in
Biology and Medicine 143 (2022): 105331; https://doi.org/10.1016/j.compbiomed.2022.105331.
Files | ||
Issue | Vol 11 No 2 (2024) | |
Section | Original Article(s) | |
DOI | https://doi.org/10.18502/fbt.v11i2.15343 | |
Keywords | ||
Atrial Fibrillation Electrocardiogram Discrete Wavelet Transform Savitzky-Golay Filter Convolutional Neural Network Long Short Term Memory ResNet18 |
Rights and permissions | |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |