基于时序心脏模型样本均衡方法的心律失常分类

doi:10.3969/j.issn.0258-8021.2022.03.006

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (4909 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract As an important clinical application of computer, automatic classification of arrhythmia can effectivelyassist in the diagnosis of cardiovascular diseases. However, the sample imbalance in experiments seriously affects the classification accuracy. At present, the mainstream method to solve the problem of sample imbalance is counter neural network, but it has some problems such as unstable training and mode collapse, and only relies on data for learning, which is lack of certain physiological significance. Therefore, this paper proposed a sample equalization method based on the time-series cardiac model to generate ECG data. The experiment was carried out on the 12 lead dataset provided by China physiological signal challenge (CPSC) in 2018. The deep residual network was used as the classification network to train each lead, and the lead fusion was realized by XGBoost algorithm. After sample equalization, F1 scores of all types were improved, especially in left bundle branch block (LBBB), ST segment depression (STD) and ST segment elevation (STE), which was increased from 0.706, 0.684 and 0.524 to 0.832, 0.809 and 0.618, respectively. In order to verify the universality of this method, PTB dataset was tested independently, and the classification accuracy reached 97.42%. The experimental results showed that the generation of simulation data based on the sequential heart model effectively improved the imbalance of experimental samples.

Key words： arrhythmia time-series cardiac model neural network lead fusion

Received: 21 July 2021

PACS:

R318

Corresponding Authors: ^*E-mail: xyh@ysu.edu.cn

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Xu Yonghong
	Wang Jinping
	Ma Jiayue

Cite this article:

Xu Yonghong,Wang Jinping,Ma Jiayue. Arrhythmia Classification Based on Time-Series Cardiac Model Sample Equalization[J]. Chinese Journal of Biomedical Engineering, 2022, 41(3): 301-309.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2022.03.006 OR http://cjbme.csbme.org/EN/Y2022/V41/I3/301

[1] Virani S, Alonso Á, Aparicio H J, et al. Heart Disease and Stroke Statistics-2021 Update: A Report From the American Heart Association [J]. Circulation, 2021, 143(8): e254-e743.
[2] Baloglu U, Talo M, Yildirim Ö, et al. Classification of myocardial infarction with multi-lead ECG signals and deep CNN [J]. Pattern Recognition Letters, 2019, 122: 23-30.
[3] Chen T, Huang CH, Shih ESC, et al. Detection and classification of cardiac arrhythmias by a challenge-best deep learning neural network model [J]. iScience, 2020, 23(3): 100886.
[4] 杨浩,黄茂林,蔡志鹏,等.融合CNN和BiLSTM的心律失常心拍分类模型[J].中国生物医学工程学报,2020,39(6):719-726.
[5] Haywood L, Murthy VK, Harvey G, et al. On-line real time computer algorithm for monitoring the ECG waveform [J]. Computers and Biomedical Research, 1970, 3(1): 15-25.
[6] 刘电华. 超长时程动态心电图在心房颤动筛查中的应用效果[J].影像研究与医学应用,2021,5(1):95-96.
[7] Emam KE, Rodgers SU, Malin B. Anonymising and sharing individual patient data [J]. BMJ: British Medical Journal, 2015, 350: h1139.
[8] Clifford G, Nemati S, Sameni R. An artificial vector model for generating abnormal electrocardiographic rhythms [J]. Physiological Measurement, 2010, 31(5): 595-609.
[9] Li Z, Ma M. ECG modeling with DFG[C]//The 27th Annual Conference of IEEE Engineering in Medicine and Biology. Shanghai: IEEE, 2006: 2691-2694.
[10] McLachlan S, Dube K, Gallagher T. Using the caremap with health incidents statistics for generating the realistic synthetic electronic healthcare record[C]//IEEE International Conference on Healthcare Informatics (ICHI). Chicago: IEEE, 2016: 439-448.
[11] Quiroz-Juárez MA, Jiménez-Ramírez O, Vázquez-Medina R, et al. Cardiac conduction model for generating 12 lead ECG signals with realistic heart rate dynamics [J]. IEEE Transactions on NanoBioscience, 2018, 17(4): 525-532.
[12] Ryzhii E, Ryzhii M. A heterogeneous coupled oscillator model for simulation of ECG signals [J]. Computer Methods and Programs in Biomedicine, 2014, 117(1): 40-49.
[13] Zhao J, Mao X, Chen L. Speech emotion recognition using deep 1D & 2D CNN LSTM networks [J]. Biomed Signal Process and Control, 2019, 47: 312-323.
[14] Zhao ZQ, Zheng P, Xu ST, et al. Object detection with deep learning: a review [J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30(11): 3212-3232.
[15] Murat F, Yildirim Ö, Talo M, et al. Application of deep learning techniques for heartbeats detection using ECG signals-analysis and review [J]. Computers in Biology and Medicine, 2020, 120: 103726.
[16] Craik A, He Y, Contreras-Vidal J. Deep learning for electroencephalogram (EEG) classification tasks: a review [J]. Journal of Neural Engineering, 2019, 16(3): 031001.
[17] Zhu F, Ye F, Fu Y, et al. Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network [J]. Scientific Reports, 2019, 9(37): 1459-1544.
[18] Hazra D, Byun Y. SynSigGAN: Generative adversarial networks for synthetic biomedical signal generation [J]. Biology, 2020, 9(12): 441.
[19] Ye F, Zhu F, Fu Y, et al. ECG generation with sequence generative adversarial nets optimized by policy gradient [J]. IEEE Access, 2019, 7: 159369-159378.
[20] Golany T, Radinsky K. PGANs: personalized generative adversarial networks for ECG synthesis to improve patient-specific deep ECG classification[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33:557-564.
[21] McSharry P, Clifford G, Tarassenko L, et al. A dynamical model for generating synthetic electrocardiogram signals [J]. IEEE Transactions on Biomedical Engineering, 2003, 50(3): 289-294.
[22] Ayatollahi A, Dabanloo N J, McLernon D, et al. A comprehensive model using modified Zeeman model for generating ECG signals [J]. Iranian Journal of Electrical and Electronic Engineering, 2005, 1(2): 88-93.
[23] Lian J, Krätschme H, Müssig D. Open source modeling of heart rhythm and cardiac pacing [J]. The Open Pacing, Electrophysiology & Therapy Journal, 2013, 3(1): 28-44.
[24] Liu F, Liu C, Zhao L, et al. An open access database for evaluating the algorithms of electrocardiogram rhythm and morphology abnormality detection [J]. Journal of Medical Imaging and Health Informatics, 2018, 8(7): 1368-1373.
[25] Mostayed A, Luo J, Shu X, et al. Classification of 12-lead ECG signals with Bi-directional LSTM network [EB/OL]. https://arxiv.org/abs/1811.02090, 2018-11-05/2021-07-21.
[26] Pan J, Tompkins WJ. A real-time QRS detection algorithm [J]. IEEE Transactions on Biomedical Engineering, 2007, 32(3): 230-236.
[27] Goldberger AL, Amaral L, Glass L, et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals [J]. Circulation, 2000, 101(23): E215.
[28] Acharya UR, Fujita H, Shu LO, et al. Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals [J]. Information Sciences, 2017, 415: 190-198.
[29] Safdarian N, Dabanloo NJ, Attarodi G. A new pattern recognition method for detection and localization of myocardial infarction using T-wave integral and total integral as extracted features from one cycle of ECG signal [J]. Journal of Biomedical Science & Engineering, 2014, 5(7): 818-824.
[30] Kojuri J, Boostani R, Dehghani P, et al. Prediction of acute myocardial infarction with artificial neural networks in patients with nondiagnostic electrocardiogram [J]. Journal of Cardiovascular Disease Research, 2015, 6(2): 51-59.
[31] Sun L, Lu Y, Yang K, et al. ECG analysis using multiple instance learning for myocardial infarction detection [J]. IEEE Trans Biomed Eng, 2012, 59(12): 3348-3356.
[32] Sharma LD, Sunkaria RK. Inferior myocardial infarction detection using stationary wavelet transform and machine learning approach [J]. Signal Image and Video Processing, 2018, 12(2): 199-206.
[33] Remya RS, Indiradevi KP, Babu KKA. Classification of myocardial infarction using multi resolution wavelet analysis of ECG [J]. Procedia Technology, 2016, 24: 949-956.
[34] Savostin AA, Ritter DV, Savostina GV. Using the K-nearest neighbours algorithm for automated detection of myocardial infarction by electrocardiogram data entries [J]. Pattern Recognition and Image Analysis, 2019, 29(4): 730-737.
[35] Wang P, Hou B, Shao S, et al. ECG arrhythmias detection using auxiliary classifier generative adversarial network and residual network [J]. IEEE Access, 2019(99): 1.
[36] Rueda C, Larriba Y, Lamela A. The hidden waves in the ECG uncovered revealing a sound automated interpretation method [J]. Scientific Reports, 2021, 11(1): 3724-3724.