A novel method for automatic detection of arrhythmias using the unsupervised convolutional neural network

• Autorzy: Zhang Junming , Yao Ruxian , Gao Jinfeng , Li Gangqiang , Wu Haitao

Identyfikatory

DOI

10.2478/jaiscr-2023-0014

• Języki publikacji: EN

Abstrakty

EN

In recent years, various models based on convolutional neural networks (CNN) have been proposed to solve the cardiac arrhythmia detection problem and achieved saturated accuracy. However, these models are often viewed as “blackbox” and lack of interpretability, which hinders the understanding of cardiologists, and ultimately hinders the clinical use of intelligent terminals. At the same time, most of these approaches are supervised learning and require label data. It is a time-consuming and expensive process to obtain label data. Furthermore, in human visual cortex, the importance of lateral connection is same as feed-forward connection. Until now, CNN based on lateral connection have not been studied thus far. Consequently, in this paper, we combines CNNs, lateral connection and autoencoder (AE) to propose the building blocks of lateral connection convolutional autoencoder neural networks (LCAN) for cardiac arrhythmia detection, which learn representations in an unsupervised manner. Concretely, the LCAN contains a convolution layer, a lateral connection layer, an AE layer, and a pooling layer. The LCAN detects salient wave features through the lateral connection layer. The AE layer and competitive learning is used to update the filters of the convolution network—an unsupervised process that ensures similar weight distribution for all adjacent filters in each convolution layer and realizes the neurons’ semantic arrangement in the LCAN. To evaluate the performances of the proposed model, we have implemented the experiments on the well-known MIT–BIH Arrhythmia Database. The proposed model yields total accuracies and kappa coefficients of 98% and 0.95, respectively. The experiment results show that the LCAN is not only effective, but also a useful tool for arrhythmia detection.

Słowa kluczowe

EN

convolutional neural network; arrhythmia detection; unsupervised learning; ECG classification

• Wydawca: University of Social Sciences
• Czasopismo: Journal of Artificial Intelligence and Soft Computing Research
• Rocznik: 2023
• Tom: Vol. 13. No. 3
• Strony: 181--196
• Opis fizyczny: Bibliogr. 70 poz., rys.

Twórcy

autor

Zhang Junming

• College of Information Engineering, Huanghuai University, Henan 463000, China
• Henan Key Laboratory of Smart Lighting, Henan 463000, China
• Henan Joint International Research Laboratory of Behavior Optimization Control for Smart Robots, Henan 463000, China
• Zhumadian Artificial Intelligence & Medical Engineering Technical Research Centre, Henan 463000, China

• https://orcid.org/0000-0003-1836-3478

autor

Yao Ruxian

• College of Information Engineering, Huanghuai University, Henan 463000, China
• Henan Key Laboratory of Smart Lighting, Henan 463000, China

• https://orcid.org/0000-0002-1314-528X

autor

Gao Jinfeng

• College of Information Engineering, Huanghuai University, Henan 463000, China
• Henan Key Laboratory of Smart Lighting, Henan 463000, China

• https://orcid.org/0009-0004-1560-1068

autor

Li Gangqiang

• College of Information Engineering, Huanghuai University, Henan 463000, China

• https://orcid.org/0000-0002-7363-1060

autor

Wu Haitao

• College of Information Engineering, Huanghuai University, Henan 463000, China
• Henan Key Laboratory of Smart Lighting, Henan 463000, China

• https://orcid.org/0009-0001-8689-7386

Bibliografia

• [1] E. J, M. J. Blaha, S. E. Chiuve, Benjamin. Heart disease and stroke statistics-2017 update: a report from the american heart association, Circulation, vol. 135, pp. E646-E646, 2017.
• [2] X. Li, C. Wu, J. Lu, et al., Cardiovascular risk factors in China: a nationwide population-based cohort study, The Lancet Public Health, vol. 5, pp. e672-e681, 2020.
• [3] A. Isin, S. Ozdalili, Cardiac arrhythmia detection using deep learning, Procedia Computer Science, vol. 120, pp.268-275, 2017.
• [4] Z. Yldrm, P. Pawiak , S. T. Ru , et al., Arrhythmia detection using deep convolutional neural network with long duration ECG signals, Computers in Biology and Medicine, vol.102, pp.411-420, 2018.
• [5] A. Mb, B. Tt, B. Sd, D. Rstc, et al., Automated arrhythmia detection with homeomorphically irreducible tree technique using more than 10,000 invidual subject ECG records, Information Sciences, vol. 575, pp.323-337, 2021.
• [6] A. Y. Hannun, P. Rajpurkar, M. Haghpanahi, et al., Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network, Nature medicine, vol. 25, pp. 65-69, 2019.
• [7] C. Vimal, B. Sathish, Random forest classifier based ECG arrhythmia classification, International Journal of Healthcare Information Systems & Informatics, vol. 5, pp. 1-10,2009.
• [8] V. N. Pham, H. L. Tran, Electrocardiogram (ECG) circuit design and using the random forest to ECG arrhythmia classification, Lecture Notes in Networks and Systems, DOI:https://doi.org/10.1007/978-3-031-22200-9 54, 2023.
• [9] A. H. Khandoker, M. Palaniswami, C. K. Karmakar, Support vector machines for automated recognition of obstructive sleep apnea syndrome from ECG recordings, IEEE Transactions on Information Technology in Biomedicine, vol. 13, 37-48, 2009.
• [10] E. H. Houssein, I. E. Ibrahim, N. Neggaz, et al., An efficient ecg arrhythmia classification ethod based on manta ray foraging optimization, Expert Systems with Applications, DOI: https://doi.org/10.1016/j.eswa.2021.115131,2021.
• [11] Y. W. Hau, H. W. Lim, C. W. Lim, et al., P204 automated detection of atrial fibrillation based on stationary wavelet transform and artificial neural network targeted for embedded system-onchip technology, European Heart Journal, DOI: 10.1093/ehjci/ehz872.075, 2020.
• [12] M. Alfaro-Ponce, I. Chairez, R. EtienneCummings, Automatic detection of electrocardiographic arrhythmias by parallel continuous neural networks implemented in FPGA, Neural Computing and Applications, vol. 31, 363-375, 2017.
• [13] M. I. Owis, A. H. Abou-Zied, A. B. M. Youssef, et al., Study of features based on nonlinear dynamical modeling in ECG arrhythmia detection and classification, IEEE transactions on biomedical engineering, vol. 49, pp. 733-736, 2002.
• [14] B. Venkataramanaiah , J. Kamala, ECG signal processing and KNN classifier-based abnormality detection by VH-doctor for remote cardiac healthcare monitoring, Soft Computing, vol.24, 17457-17466,2020.
• [15] T. Tuncer, S. Dogan, P. Plawiak, et al., Automated arrhythmia detection using novel hexadecimal local pattern and multilevel wavelet transform with ECG signals, Knowledge-Based Systems, vol. 186, pp. 1-19, 2019 .
• [16] D. A. Coast, R. M. Stern, G. G. Cano, et al., An approach to cardiac arrhythmia analysis using hidden Markov models, IEEE Transactions on Biomedical Engineering, vol. 37, pp. 826-836, 2002.
• [17] A. Sadoughi, M. B. Shamsollahi, E. Fatemizadeh, et al., Detection of Apnea bradycardia from ECG signals of preterm infants using layered hidden markov model, Annals of Biomedical Engineering, vol. 49, pp. 2159-2169, 2021.
• [18] C. Angermueller, T. Parnamaa, L. Parts, et ¨al., Deep learning for computational biology, Molecular Systems Biology, DOI: 10.15252/msb.20156651, 2016.
• [19] Y. Lecun, Y. Bengio, G. Hinton, Deep learning, Nature, vol. 521, pp.436-444 ,2015.
• [20] Y. H. Awni, R. Pranva, H. Masoumeh, et al., Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network, Nature Medicine, vol. 25, pp.65-69,2019.
• [21] C. Uraab, L. Shu, A. Yh, et al., (2017). A deep convolutional neural network model to classify heartbeats. Computers in Biology and Medicine, 89(2017)389-396.
• [22] L. Fiorina, B. Lefebvre, C. Gardella, et al., Smartwatch-based detection of atrial arrhythmia using a deep neural network in a tertiary care hospital, Europace, DOI: https://doi.org/10.1093/europace/euac053.563, 2022.
• [23] F. Uslu, M. Varela, G. Boniface, et al., LA-Net: A Multi-task deep network for the segmentation of the left atrium, IEEE transactions on medical imaging, 41 (2)(2021)456-464.
• [24] X. Fan, Q. Yao, Y. Cai, et al., Multiscaled fusion of deep convolutional neural networks for screening atrial fibrillation from single lead short ECG recordings, IEEE Journal of Biomedical and Health Informatics, 22(6)( 2018)1744-1753.
• [25] H. M. Lynn, S. B. Pan, P. Kim, A deep bidirectional GRU network model for biometric electrocardiogram classification based on recurrent neural networks, IEEE Access, 7(2019)145395-145405.
• [26] R. S. Andersen, A. Peimankar, S. Puthusserypady, A deep learning approach for real-time detection of atrial fibrillation, Expert Systems with Applications, 115(2019)465-473.
• [27] S. Mousavi, F. Afghah, A. Razi, et al., ECGNET: Learning where to attend for detection of atrial fibrillation with deep visual attention, In 2019 IEEEEMBS International Conference on Biomedical & Health Informatics 2019, pp.1-4.
• [28] E. Choi, M. T. Bahadori, J. Sun, et al.. Retain: An interpretable predictive model for healthcare using reverse time attention mechanism, In advances in neural information processing systems, 2016, pp. 3504-3512.
• [29] F. Wu, B. B. Liao, Y. H. Han Interpretability for Deep Learning, Aero Weaponry, 2019(1) 39-46.
• [30] P. W. Koh , P. Liang, Understanding black-box predictions via influence functions, 70(2017) 1885–1894.
• [31] Q. Zhang, Y. N. Wu, S. C. Zhu, Interpretable convolutional neural networks, In: 2018 IEEE/CVF conference on computer vision and pattern recognition, DOI: 10.1109/CVPR.2018.00920, 2018.
• [32] Z. C. Lipton, The mythos of model interpretability, Communications of the ACM, 61(10)(2018)36-43.
• [33] Z. Hu, Z. Yang, X. Liang, et al., Toward controlled generation of Text, arXiv:1703.00955, 2017.
• [34] A. Mahendran, A. Vedaldi, Understanding deep image representations by inverting them, In 2015 IEEE conference on computer vision and pattern recognition, DOI: 10.1109/CVPR.2015.7299155, 2015.
• [35] A. Dosovitskiy, T. Brox, Inverting visual representations with convolutional networks, In 2015 IEEE conference on computer vision and pattern recognition, DOI: 10.1109/CVPR.2016.522, 2016.
• [36] R. C. Fong, A. Vedaldi, Interpretable explanations of black boxes by meaningful perturbation, In 2017 IEEE international conference on computer vision, DOI: 10.1109/ICCV.2017.371, 2017.
• [37] R. R. Selvaraju, M. Cogswell, A. Das, et al., Grad-cam: visual explanations from deep networks via gradient-based localization, In 2017 IEEE international conference on computer vision, DOI: 10.1109/ICCV.2017.37, 1, 2017.
• [38] Q. Zhang, R.Cao, F. Shi, et al., Interpreting CNN knowledge via an explanatory graph, In Thirtysecond AAAI conference on artificial intelligence, pp. 4454-4463, 2018.
• [39] W. Hong, X. Yunchao, L. Dawei, et al., Rapid identification of X-ray diffraction patterns based on very limited data by interpretable convolutional neural networks, Journal of Chemical Information and Modeling, vol. 60, pp.2004-2011, 2020.
• [40] D. Bau, B. Zhou, A. Khosla,et al., Network dissection: Quantifying interpretability of deep visual representations, In 2017 IEEE conference on computer vision and pattern recognition, DOI: 10.1109/CVPR.2017.354, 2017.
• [41] P. Koh, P. Liang, Understanding black-box predictions via influence functions, In proceedings of the 34th international conference on machine learning, pp.1885-1894, 2017.
• [42] H. Asanuma, Recent developments in the study of the columnar arrangement of neurons within the motor cortex, Physiological Reviews, vol. 55,pp. 143-156, pp.1975.
• [43] E. Kandel, J. schwartz, T. Jessell, et al., Principles of neural science, 5th ed. New York, USA: McGraw-Hill, 2012.
• [44] D. H. Hubel, T.N. Wiesel, Ferrier lecture: functional architecture of macaque monkey visual cortex, Proceedings of the Royal Society of London, vol. 198, pp. 1-59, 1977.
• [45] K. Tanaka, Columns for complex visual object features in the inferotemporal cortex:clustering of cells with similar but slightly different stimulus selectivities, Cerebral Cortex, vol. 13, pp. 90-99, 2003.
• [46] A. Angelucci, C. Bressloff P, Contribution of feedforward, lateral and feedback connections to the classical receptive field center and extra-classical receptive field surround of primate V1 neurons, Progress in Brain Research, vol. 154, pp.93-120, 2006.
• [47] V. A. Lamme, H. Super, H. Spekreijse, Feedforward, horizontal, and feedback processing in the visual cortex, Current Opinion in Neurobiology, vol. 8, pp. 529, 1998.
• [48] T. Kohonen, Self-organized formation of topologically correct feature maps, Biological Cybernetics, vol. 43, pp. 59-69,1982.
• [49] G. Bebis, M. Georgiopoulos, N.V. Lobo, et al., Using self-organizing maps to learn geometric hash functions for model-based object recognition, IEEE Transactions on Neural Networks, vol. 9, 560-570, 1998.
• [50] A. Y. Ng, Sparse autoencoder, CS294 A Lecture notes 72, 2011.
• [51] G.B. Moody, R.G. Mark, The impact of the MITBIH arrhythmia database, IEEE Engineering in Medicine and Biology Magazine, vol. 20, pp. 45-50,2001.
• [52] R. Mark, Aami-recommended practice: testing and reporting performance results of ventricular arrhythmia detection algorithms, in: Association for the Advancement of Medical Instrumentation, Arrhythmia Monitoring Subcommittee, AAMI ECAR, 1987.
• [53] D. J. Felleman, D. Essen, Distributed hierarchicalprocessing in the primate cerebral cortex, Cerebral Cortex, vol.1, pp. 1-47,1991.
• [54] Z. P. Lo, M. Fujita, B. Bavarian, Analysis of neighborhood interaction in Kohonen neural networks, In IEEE fifth international proceedings paralel processing symposium, pp. 246-249,199,.
• [55] Z. P. Lo, Y. Yu, B. Bavarian, Analysis of the convergence properties of topology preserveing neural networks. IEEE Transactions on Neural Networks, vol. 4, 207-220,1993.
• [56] J. M. Zhang, Y. Wu, A new method for automatic sleep stage classification, IEEE Transactions on Biomedical Circuits and Systems, vol. 11, pp. 1097-1110, 2017.
• [57] S. F. Liang, C. E. Kuo, Y. H. Hu, et al., Automatic stage scoring of single-channel sleep EEG by using multiscale entropy and autoregressive models, IEEE Transactions on Instrumentation and Measurement, vol. 61, pp. 1649-1657, 2012.
• [58] J. Cohen, A coefficient of agreement for nominal scales, Educational & Psychological Measurement, vol. 20, pp. 37-46, 1960.
• [59] H. Zhang, C. M. Cartwright, M. S. Ding, et al., Image feature extraction with various wavelet functions in a photorefractive joint transform correlator, Optics Communications, vol. 185, pp. 277-284, 2000.
• [60] https://cs231n.github.io/understandingcnn.
• [61] ahilS.,http://medium.com/towards-data-science/experiences-with-a-new-kind-of-convolution-dfe603262e4c, 2017.
• [62] M. Hammad, A. M., Iliyasu, A. Subasi, et al., A multitier deep learning model for arrhythmia detection, IEEE Transactions on Instrumentation and Measurement, DOI: 10.1109/TIM.2020.3033072, 2020.
• [63] H. Rui, C. Jie, Z. Li, A transformer-based deep neural network for arrhythmia detection using continuous ECG signals, Computers in Biology and Medicine, DOI: https://doi.org/10-.1016/j.compbiomed.2022.105325, 2022.
• [64] S. Mousavi, F. Afghah, F. Khadem, U.R. Acharya, Ecg language processing (elp): a new technique to analyze ecg signals, Computer Methods and Programs in Biomedicine, vol. 202, pp.105959, 2021.
• [65] A. Chandrasekar, D. D. Shekar, A. C. Hiremath, et al., Detection of arrhythmia from electrocardiogram signals using a novel gaussian assisted signal smoothing and pattern recognition, Biomedical Signal Processing and Control, DOI:https://doi.org/10.1016/j.bspc.2021.103469, 2022.
• [66] C. Uraab, L. Shu, A. Yh, et al., A deep convolutional neural network model to classify heartbeats, Computers in Biology and Medicine, vol. 89, pp. 389-396, 2017.
• [67] M. Hammad, A. Maher, K. Wang, et al., Detection of abnormal heart conditions based on characteristics of ECG signals, Measurement, vol. 125, pp. 634-644, 2018.
• [68] M. Amrani, M. Hammad, F. Jiang, et al., Very deep feature extraction and fusion for arrhythmias detection, Neural Computing and Applications, vol. 30, pp. 2047-2057, 2018.
• [69] R. Li, X. Zhang, H. Dai, et al., Interpretability analysis of heartbeat classification based on heartbeat activity’s global sequence features and BiLSTMattention neural network, IEEE Access, vol. 7, pp. 109870-109883, 2019.
• [70] J. Lv, Q. Ye, Y. Sun, et al., Heart-darts: classification of heartbeats using differentiable architecture search, In 2021 International Joint Conference on Neural Networks, DOI: 10.1109/IJCNN52387.2021.9534184, 2021.

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).