Self-organized operational neural networks for the detection of atrial fibrillation

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

Identyfikatory

DOI

10.2478/jaiscr-2024-0004

• Języki publikacji: EN

Abstrakty

EN

Atrial fibrillation is a common cardiac arrhythmia, and its incidence increases with age. Currently, numerous deep learning methods have been proposed for AF detection. However, these methods either have complex structures or poor robustness. Given the evidence from recent studies, it is not surprising to observe the limitations in the learning performance of these approaches. This can be attributed to their strictly homogenous conguration, which solely relies on the linear neuron model. The limitations mentioned above have been addressed by operational neural networks (ONNs). These networks employ a heterogeneous network configuration, incorporating neurons equipped with diverse nonlinear operators. Therefore, in this study, to enhance the detection performance while maintaining computational efficiency, a novel model named multi-scale Self-ONNs (MSSelf-ONNs) was proposed to identify AF. The proposed model possesses a significant advantage and superiority over conventional ONNs due to their self-organization capability. Unlike conventional ONNs, MSSelf -ONNs eliminate the need for prior operator search within the operator set library to find the optimal set of operators. This unique characteristic sets MSSelf -ONNs apart and enhances their overall performance. To validate and evaluate the system, we have implemented the experiments on the wellknown MIT-BIH atrial fibrillation database. The proposed model yields total accuracies and kappa coefficients of 98% and 0.95, respectively. The experiment results demonstrate that the proposed model outperform the state-of-the-art deep CNN in terms of both performance and computational complexity.

Słowa kluczowe

EN

convolutional neural network; operational Neural Networks; atrial fibrillation detection; ECG classification

• Wydawca: University of Social Sciences
• Czasopismo: Journal of Artificial Intelligence and Soft Computing Research
• Rocznik: 2024
• Tom: Vol. 14, No. 1
• Strony: 63--75
• Opis fizyczny: Bibliogr. 49 poz., rys.

Twórcy

autor

Zhang Junming

• College of Computer and Artificial Intelligence, 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

Dong Hao

• College of Computer and Artificial Intelligence, Huanghuai University, Henan 463000, China
• Henan Key Laboratory of Smart Lighting, Henan 463000, China
• School of Computer Science, Zhongyuan University of Technology, Henan 450007, China

• https://orcid.org/0009-0004-3613-7372

autor

Gao Jinfeng

• College of Computer and Artificial Intelligence, Huanghuai University, Henan 463000, China
• Henan Key Laboratory of Smart Lighting, Henan 463000, China

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

autor

Yao Ruxian

• College of Computer and Artificial Intelligence, Huanghuai University, Henan 463000, China
• Henan Key Laboratory of Smart Lighting, Henan 463000, China

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

autor

Li Gangqiang

• College of Computer and Artificial Intelligence, Huanghuai University, Henan 463000, China
• Henan Key Laboratory of Smart Lighting, Henan 463000, China

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

autor

Wu Haitao

• College of Computer and Artificial Intelligence, Huanghuai University, Henan 463000, China

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

Bibliografia

• [1] .P. Verma, M. Wong, Atrial fibrillation., Aust. J. Gen. Pract., 48 10, 2019, 694–9.
• [2] . Dharmaprani, L. Dykes, A. McGavigan, et al., Information Theory and Atrial Fibrillation (AF): A Review, Front. Physiol., 9, 2018.
• [3] .-J. Lin, P.A. Wolf, M. Kelly-Hayes, et al., Stroke severity in atrial fibrillation. The Framingham Study, Stroke, 27 10, 1996, 1760–4.
• [4] .J. Wang, M.G. Larson, D. Levy, et al., Temporal relations of atrial fibrillation and congestive heart failure and their joint influence on mortality and the framingham heart study, Circulation, 107, 2003, 2920–6.
• [5] . Hagiwara, H. Fujita, S.L. Oh, et al., Computer-aided diagnosis of atrial fibrillation based on ECG Signals: A review, Inf. Sci., 467, 2018, 99–114.
• [6] .S. Kaufman, A.L. Waldo, The impact of asymptomatic atrial fibrillation., J. Am. Coll. Cardiol., 43 1, 2004, 53–4.
• [7] . Freedman, J.A. Camm, H. Calkins, et al., Screening for Atrial Fibrillation: a report of the AF-SCREEN international collaboration, Circulation, 135, 2017, 1851–67.
• [8] .S. Andersen, A. Peimankar, S.K. Puthusserypady, A deep learning approach for real-time detection of atrial fibrillation, Expert Syst Appl, 115, 2019, 465–73.
• [9] . Bettoni, M. Zimmermann, Autonomic Tone Variations Before the Onset of Paroxysmal Atrial Fibrillation, Circ. J. Am. Heart Assoc., 105, 2002, 2753–9.
• [10] . Scherr, D. Dalal, C.A. Henrikson, et al., Prospective comparison of the diagnostic utility of a standard event monitor versus a “leadless” portable ECG monitor in the evaluation of patients with palpitations, J. Interv. Card. Electrophysiol., 22, 2008, 39–44.
• [11] . Chandrakar, O. Yadav, V.K. Chandra, A survey of noise removal techniques for ecg signals, Int. J. Adv. Res. Comput. Commun. Eng., 2, 2013, 1354–7.
• [12] . Serhal, N. Abdallah, J.-M. Marion, et al., Overview on prediction, detection, and classification of atrial fibrillation using wavelets and AI on ECG, Comput. Biol. Med., 142, 2022, 105168.
• [13] . Kumar, S.K. Puthusserypady, H. Domínguez, et al., An investigation of the contextual distribution of false positives in a deep learning-based atrial fibrillation detection algorithm, Expert Syst. Appl., 2022.
• [14] . Rahul, M. Sora, L.D. Sharma, et al., An improved cardiac arrhythmia classification using an RR interval-based approach, Biocybern. Biomed. Eng., 41, 2021, 656–66.
• [15] . Chen, Z. Hong, Y. Guo, et al., A cascaded classifier for multi-lead ECG based on feature fusion, Comput. Methods Programs Biomed., 178, 2019, 135–43.
• [16] . Hirsch, S.H. Jensen, E.S. Poulsen, et al., Atrial fibrillation detection using heart rate variability and atrial activity: A hybrid approach, Expert Syst Appl, 169, 2021, 114452.
• [17] .A. Millán, N.A. Girón, D.M. López, Analysis of Relevant Features from Photoplethysmographic Signals for Atrial Fibrillation Classification, Int. J. Environ. Res. Public. Health, 17, 2020.
• [18] . Wan, J. Liu, Z. Jin, et al., Ventricular repolarization instability quantified by instantaneous frequency of ECG ST intervals, Technol. Health Care, 29, 2020, 73–83.
• [19] .S. Udawat, P. Singh, An automated detection of atrial fibrillation from single-lead ECG using HRV features and machine learning, J. Electrocardiol., 2022.
• [20] . Gregoire, C. Gilon, N. Vaneberg, et al., QT-dynamicity for atrial fibrillation detection and short-term forecast using machine learning, Arch. Cardiovasc. Dis. Suppl., 2023.
• [21] . Kumar, S.K. Puthusserypady, H. Domínguez, et al., An investigation of the contextual distribution of false positives in a deep learning-based atrial fibrillation detection algorithm, Expert Syst. Appl., 2022.
• [22] . Petmezas, K. Haris, L. Stefanopoulos, et al., Automated atrial fibrillation detection using a hybrid CNN-LSTM network on imbalanced ECG datasets, Biomed Signal Process Control, 63, 2021, 102194.
• [23] . Tran, Y. Li, L. Nocera, et al., MultiFusion-Net: Atrial Fibrillation detection with deep neural networks., AMIA Jt. Summits Transl. Sci. Proc. AMIA Jt. Summits Transl. Sci., 2020, 2020, 654–63.
• [24] . Shi, H. Wang, C. Qin, et al., An incremental learning system for atrial fibrillation detection based on transfer learning and active learning, Comput. Methods Programs Biomed., 187, 2019, 105219.
• [25] . Jin, C. Qin, J. Liu, et al., A novel domain adaptive residual network for automatic Atrial Fibrillation detection, Knowl Based Syst, 203, 2020, 106122.
• [26] . Subramanyan, U. Ganesan, A novel deep neural network for detection of Atrial Fibrillation using ECG signals, Knowl Based Syst, 258, 2022, 109926.
• [27] .F. Gündüz, M.F. Talu, Atrial fibrillation classification and detection from ECG recordings, Biomed. Signal Process. Control, 2023.
• [28] . Rahul, L.D. Sharma, Artificial intelligence-based approach for atrial fibrillation detection using normalised and short-duration time-frequency ECG, Biomed Signal Process Control, 71, 2022, 103270.
• [29] . Ding, R. Xiao, D.H. Do, et al., Log-Spectral matching GAN: PPG-Based atrial fibrillation detection can be enhanced by GAN-Based data augmentation with integration of spectral loss, IEEE J. Biomed. Health Inform., 27, 2021, 1331–41.
• [30] . Malik, O.C. Devecioglu, S. Kiranyaz, et al., Real-time patient-Specific ECG classification by 1D self-operational neural networks, IEEE Trans. Biomed. Eng., 69, 2021, 1788–801.
• [31] . Gabbouj, S. Kiranyaz, J. Malik, et al., Robust peak detection for holter ECGs by self-organized operational neural networks, IEEE Trans. Neural Netw. Learn. Syst., PP, 2022, 1–12.
• [32] . Malik, O.C. Devecioglu, S. Kiranyaz, et al., Real-Time patient-specific ECG classification by 1D self-operational neural networks, IEEE Trans. Biomed. Eng., 69, 2021, 1788–801.
• [33] . Malik, S. Kiranyaz, M. Gabbouj, Operational vs convolutional neural networks for image denoising, ArXiv, abs/2009.00612, 2020.
• [34] . Malik, S. Kiranyaz, M. Gabbouj, Self-organized operational neural networks for severe image restoration problems, Neural Netw. Off. J. Int. Neural Netw. Soc., 135, 2020, 201–11.
• [35] . Kiranyaz, T. Ince, A. Iosifidis, et al., Operational neural networks, Neural Comput. Appl., 32, 2019, 6645–68.
• [36] . Kiranyaz, J. Malik, H.B. Abdallah, et al., Exploiting heterogeneity in operational neural networks by synaptic plasticity, Neural Comput. Appl., 33, 2021, 7997–8015.
• [37] . Kiranyaz, J. Malik, H.B. Abdallah, et al., Self-Organized operational neural networks with generative neurons, Neural Netw. Off. J. Int. Neural Netw. Soc., 140, 2020, 294–308.
• [38] .H. Mohammed, J. Malik, S. Al-Madeed, et al., 2D self-organized ONN model for handwritten text recognition, Appl Soft Comput, 127, 2022, 109311.
• [39] .U. Zahid, S. Kiranyaz, M. Gabbouj, Global ECG classification by self-operational neural networks with feature injection, IEEE Trans. Biomed. Eng., 70, 2022, 205–15.
• [40] . Ross-Howe, H.R. Tizhoosh, Atrial fibrillation detection using deep features and convolutional networks, 2019 IEEE EMBS Int. Conf. Biomed. Health Inform. BHI, 2019, 1–4.
• [41] . Malik, S. Kiranyaz, M. Yamaç, et al., Convolutional versus self-organized operational neural networks for real-world blind image denoising, ArXiv, abs/2103.03070, 2021.
• [42] . Malik, S. Kiranyaz, M. Gabbouj, FastONN-Python based open-source GPU implementation for Operational Neural Networks, ArXiv, abs/2006.02267, 2020.
• [43] . Wang, J. Fan, Y. Li, Deep multi-scale fusion neural network for multi-class arrhythmia detection, IEEE J. Biomed. Health Inform., 24, 2020, 2461–72.
• [44] .-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 Trans. Instrum. Meas., 61, 2012, 1649–57.
• [45] . Cohen, A coefficient of agreement for nominal scales, Educ. Psychol. Meas., 20, 1960, 37–46.
• [46] .S. Jahan, M. Mansourvar, S.K. Puthusserypady, et al., Short-term atrial fibrillation detection using electrocardiograms: A comparison of machine learning approaches, Int. J. Med. Inf., 163, 2022, 104790.
• [47] . Feng, Z. Fan, A novel bidirectional LSTM network based on scale factor for atrial fibrillation signals classification, Biomed Signal Process Control, 76, 2022, 103663.
• [48] . Ma, S. Wei, T. Chen, et al., Integration of results from convolutional neural network in a support vector machine for the detection of Atrial Fibrillation, IEEE Trans. Instrum. Meas., 70, 2021, 1–10.
• [49] . Wang, Automated detection of atrial fibrillation and atrial flutter in ECG signals based on convolutional and improved Elman neural network, Knowl Based Syst, 193, 2020, 105446.