A two-step method for paroxysmal atrial fibrillation event detection based on machine learning

Ya'nan Wang; Sen Liu; Haijun Jia; Xintao Deng; Chunpu Li; Aiguo Wang; Cuiwei Yang; Ya'nan Wang; Sen Liu; Haijun Jia; Xintao Deng; Chunpu Li; Aiguo Wang; Cuiwei Yang

doi:10.3934/mbe.2022460

Mathematical Biosciences and Engineering

2022, Volume 19, Issue 10: 9877-9894. doi: 10.3934/mbe.2022460

Previous Article Next Article

Research article Special Issues

A two-step method for paroxysmal atrial fibrillation event detection based on machine learning

1.
Center for Biomedical Engineering, School of Information Science and Technology, Fudan University, Shanghai 200433, China
2.
Department of Cardiology, Xinghua City People's Hospital, Jiangsu 225700, China
3.
Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai, Shanghai 200093, China

Received: 29 March 2022 Revised: 17 June 2022 Accepted: 30 June 2022 Published: 11 July 2022

Detection of atrial fibrillation (AF) events is significant for early clinical diagnosis and appropriate intervention. However, in existing detection algorithms for paroxysmal AF (AFp), the location of AF starting and ending points in AFp is not concerned. To achieve an accurate identification of AFp events in the long-term dynamic electrocardiograms (ECGs), this paper proposes a two-step method based on machine learning. In the first step, based on features extracted from the calculated R-to-R intervals (RR intervals, the cycle of heart beat), the rhythm type of the ECG signal is first classified into three classes (AFp rhythm, persistent AF (AFf) rhythm, and non-atrial fibrillation (non-AF, N) rhythm) using support vector machine (SVM). In the second step, the starting and ending points for AF episodes of AFp rhythms predicted in the first step are further located based on heartbeat classification. By training a deep convolutional neural network with phased training, the segmented beats of AFp rhythms are divided into AF beats and non-AF beats to determine the beginning and end of any AF episode. The proposed two-step method is trained and tested on the 4th China Physiological Signal Challenge 2021 databases. A final score U of 1.9310 is obtained on the unpublished test set maintained by the challenge organizers, which demonstrates the advantage of the two-step method in AFp event detection. The work is useful for assessing AF burden index for AFp patients.
- atrial fibrillation event detection,
- machine learning,
- phased training,
- two-step method,
- RR intervals
Citation: Ya'nan Wang, Sen Liu, Haijun Jia, Xintao Deng, Chunpu Li, Aiguo Wang, Cuiwei Yang. A two-step method for paroxysmal atrial fibrillation event detection based on machine learning[J]. Mathematical Biosciences and Engineering, 2022, 19(10): 9877-9894. doi: 10.3934/mbe.2022460

Related Papers:

Abstract

Detection of atrial fibrillation (AF) events is significant for early clinical diagnosis and appropriate intervention. However, in existing detection algorithms for paroxysmal AF (AFp), the location of AF starting and ending points in AFp is not concerned. To achieve an accurate identification of AFp events in the long-term dynamic electrocardiograms (ECGs), this paper proposes a two-step method based on machine learning. In the first step, based on features extracted from the calculated R-to-R intervals (RR intervals, the cycle of heart beat), the rhythm type of the ECG signal is first classified into three classes (AFp rhythm, persistent AF (AFf) rhythm, and non-atrial fibrillation (non-AF, N) rhythm) using support vector machine (SVM). In the second step, the starting and ending points for AF episodes of AFp rhythms predicted in the first step are further located based on heartbeat classification. By training a deep convolutional neural network with phased training, the segmented beats of AFp rhythms are divided into AF beats and non-AF beats to determine the beginning and end of any AF episode. The proposed two-step method is trained and tested on the 4th China Physiological Signal Challenge 2021 databases. A final score U of 1.9310 is obtained on the unpublished test set maintained by the challenge organizers, which demonstrates the advantage of the two-step method in AFp event detection. The work is useful for assessing AF burden index for AFp patients.

References

[1]	M. Young, Atrial fibrillation, Crit. Care. Nurs. Clin., 31 (2019), 77–90. https://doi.org/10.1016/j.cnc.2018.11.005 doi: 10.1016/j.cnc.2018.11.005
[2]	A. Margulescu, L. Mont, Persistent atrial fibrillation vs paroxysmal atrial fibrillation: Differences in management, Expert. Rev. Cardiovas., 15 (2017), 601–618. https://doi.org/10.1080/14779072.2017.1355237 doi: 10.1080/14779072.2017.1355237
[3]	J. Imberti, W. Y. Ding, A. Kotalczyk, J. Zhang, G. Boriani, G. Lip, et al., Catheter ablation as first-line treatment for paroxysmal atrial fibrillation: A systematic review and meta-analysis, Heart, 107 (2021), 1630–1636. https://doi.org/10.1136/heartjnl-2021-319496 doi: 10.1136/heartjnl-2021-319496
[4]	S. Hong, Y. Zhou, J. Shang, C. Xiao, J. Sun, Opportunities and challenges of deep learning methods for electrocardiogram data: A systematic review, Comput. Biol. Med., 122 (2019), 103801. https://doi.org/10.1016/j.compbiomed.2020.103801 doi: 10.1016/j.compbiomed.2020.103801
[5]	E. K. Wang, L. Xi, R. P. Sun, F. Wang, L. Y. Pan, C. X. Cheng, et al., A new deep learning model for assisted diagnosis on electrocardiogram, Math. Biosci. Eng., 16 (2019), 2481–2491. https://doi.org/10.3934/mbe.2019124 doi: 10.3934/mbe.2019124
[6]	G. Hindricks et al., 2020 ESC guidelines for the diagnosis and management of atrial fibrillation developed in collaboration with the European Association for Cardio-Thoracic Surgery (EACTS): The task force for the diagnosis and management of atrial fibrillation of the European Society of Cardiology (ESC) developed with the special contribution of the European Heart Rhythm Association (EHRA) of the ESC, Eur. Heart J., 42 (2021), 373–498. https://doi.org/10.1093/eurheartj/ehaa612 doi: 10.1093/eurheartj/ehaa612
[7]	Q. Li, B. Su, J. Liu, Diagnostic values of different ECG durations in paroxysmal AF diagnosis, Ann. Noninvas. Electro., 27 (2022), e12921. https://doi.org/10.1111/anec.12921 doi: 10.1111/anec.12921
[8]	M. Liu, X. Meng, P. Xiong, X. Liu, Detection of paroxysmal atrial fibrillation based on kernel sparse coding, J. Elec. Info. Technol., 42 (2020), 1743–1749. https://doi.org/10.11999/JEIT190582 doi: 10.11999/JEIT190582
[9]	A. Petrėnas, L. Sörnmo, A. Lukoševičius, V. Marozas, Detection of occult paroxysmal atrial fibrillation, Med. Biol. Eng. Comput., 67 (2020), 978–986. https://doi.org/10.1007/s11517-014-1234-y doi: 10.1007/s11517-014-1234-y
[10]	N. Ganapathy, D. Baumgartel, T. M. Deserno, Automatic detection of atrial fibrillation in ECG using co-occurrence patterns of dynamic symbol assignment and machine learning, Sensors (Basel), 21 (2021), 3542. https://doi.org/10.3390/s21103542 doi: 10.3390/s21103542
[11]	Y. Xin, Y. Z. Zhao, Y. H. Mu, Q. Li, C. C. Shi, Paroxysmal atrial fibrillation recognition based on multi-scale Rényi entropy of ECG, Technol Health Care., 25 (2017), 189–196. https://doi.org/10.3233/THC-171321 doi: 10.3233/THC-171321
[12]	E. Sabeti, M. B. Shamsollahi, F. Afdideh, Prediction of paroxysmal atrial fibrillation using empirical mode decomposition and RR intervals, in 2012 IEEE-EMBS Conference on Biomedical Engineering and Sciences, (2012) 750–754. https://doi.org/10.1109/IECBES.2012.6498147
[13]	L. Y. Chen, M. K. Chung, L. A. Allen, M. Ezekowitz, K. L. Furie, P. McCabe, et al., Atrial fibrillation burden: moving beyond atrial fibrillation as a binary entity: A scientific statement from the American Heart Association, Circulation, 137 (2018), E623–E644. https://doi.org/10.1161/CIR.0000000000000568 doi: 10.1161/CIR.0000000000000568
[14]	X. Wang, C. Ma, X. Zhang, H. Gao, G. Clifford, C. Liu, Paroxysmal atrial fibrillation events detection from dynamic ECG recordings: The 4th China physiological signal challenge 2021, 2021, PhysioNet, 2021 (2021), 1–83. https://doi.org/10.13026/ksya-qw89 doi: 10.13026/ksya-qw89
[15]	N. Larburu, T. Lopetegi, I. Romero, Comparative study of algorithms for atrial fibrillation detection, Comput. Cardiol., 38 (2011), 265–268.
[16]	B. Chen, W. Chen, J. Liu, L. H. Zhu, The research of electrophysiological data normalization, in 2010 5th International Conference on Computer Science & Education, (2010), 149–151. https://doi.org/10.1109/ICCSE.2010.5593672
[17]	B. E. Boser, I. M. Guyon, V. N. Vapnik, A training algorithm for optimal margin classifiers, in Proceedings of the Fifth Annual Workshop on Computational Learning Theory, (1992), 144–152. https://doi.org/10.1145/130385.130401
[18]	P. de Chazal, M. O'Dwyer, R. B. Reilly, Automatic classification of heartbeats using ECG morphology and heartbeat interval features, IEEE Trans Biomed Eng., 51 (2004), 1196–1206. https://doi.org/10.1109/TBME.2004.827359 doi: 10.1109/TBME.2004.827359
[19]	A. A. Almazroi, Survival prediction among heart patients using machine learning techniques, Math. Biosci. Eng., 19 (2022), 134–145. https://doi.org/10.1109/TBME.2004.827359 doi: 10.1109/TBME.2004.827359
[20]	J. Jiang, H. F. Zhang, D. C. Pi, C. L. Dai, A novel multi-module neural network system for imbalanced heartbeats classification, Exp. Syst. Appl. X, 1 (2019), 100003. https://doi.org/10.1016/j.eswax.2019.100003 doi: 10.1016/j.eswax.2019.100003
[21]	Association for the Advancement of Medical Instrumentation, Testing and Reporting Performance Results of Cardiac Rhythm and ST Segment Measurement Algorithms, 1998.
[22]	A. Saif, A. Garba, J. Awwalu, H. Arshad, L. Zakaria, Performance comparison of min-max normalisation on frontal face detection using haar classifiers, Pertanika J. Sci. Technol., 25 (2017), 163–171.
[23]	C. He, H. kang, T. Yao, X. Li, An effective classifier based on convolutional neural network and regularized extreme learning machine, Math. Biosci. Eng., 16 (2019), 8309–8321. https://doi.org/10.3934/mbe.2019420 doi: 10.3934/mbe.2019420
[24]	K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, preprint, arXiv: 1409.1556
[25]	K. Kosaka, T. Itoh, A visualization method for training data comparison, in 2021 25th International Conference Information Visualisation (IV), (2021), 205–210. https://doi.org/10.1109/IV53921.2021.00040
[26]	K. Weimann, T. Conrad, Transfer learning for ECG classification, Sci. Rep., 11 (2021), 1–12. https://doi.org/10.1038/s41598-021-84374-8 doi: 10.1038/s41598-021-84374-8
[27]	C. Yu, X. Qi, H. Ma, X. He, C. Wang, Y. Zhao, LLR: Learning rates by LSTM for training neural networks, Neurocomputing, 394 (2020), 41–50. https://doi.org/10.1016/j.neucom.2020.01.106 doi: 10.1016/j.neucom.2020.01.106

Reader Comments

Your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)