Lightweight beat score map method for electrocardiogram-based arrhythmia classification

• Autorzy: Lee Kyeonghwan , Lee Jaewon , Shin Miyoung

Identyfikatory

DOI

10.1016/j.bbe.2024.11.002

• Języki publikacji: EN

Abstrakty

EN

We recently investigated beat score map (BSM)-based methods for electrocardiogram (ECG)-based arrhythmia classification. Although BSM-based methods show impressive performance, they are somewhat resource-intensive owing to the arrangement of beat score vectors generated from 1D ECG sequences with zero-padding across time points. To address this issue, we propose a lightweight BSM (Lw-BSM) method that significantly reduces the size of the original BSM while capturing the characteristics of beat arrangement patterns as does the original BSM. Specifically, two types of Lw-BSMs are generated without zero-padding and evaluated for multiclass arrhythmia prediction. Experimental results on two public datasets, MIT-BIH and SPH, demonstrate that arrhythmia classification using Lw-BSM images is quite comparable to that using the original BSM images as an input to CNN-based classification models. At the same time, the image size can be reduced significantly. Moreover, it is observed that this approach is almost insensitive to the selection of the R-peak detection algorithm, showing stable performance across different R-peak algorithms.

Słowa kluczowe

EN

arrhythmia classification; electrocardiogram; beat score map; lightweight method

PL

klasyfikacja arytmii serca; elektrokardiogram; mapa wyników

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2024
• Tom: Vol. 44, no. 4
• Strony: 844--857
• Opis fizyczny: Bibliogr. 67 poz., rys., tab., wykr.

Twórcy

autor

Lee Kyeonghwan

• Bio-Intelligence & Data Mining Laboratory, School of Electronic and Electrical Engineering, Kyungpook National University, Daegu 41566, Republic of Korea

autor

Lee Jaewon

• Bio-Intelligence & Data Mining Laboratory, School of Electronic and Electrical Engineering, Kyungpook National University, Daegu 41566, Republic of Korea

autor

Shin Miyoung

• Bio-Intelligence & Data Mining Laboratory, School of Electronic and Electrical Engineering, Kyungpook National University, Daegu 41566, Republic of Korea

Bibliografia

• [1] Roth GA, Mensah GA, Johnson CO, Addolorato G, Ammirati E, Baddour LM, et al. Global burden of cardiovascular diseases and risk factors, 1990-2019: update from the GBD 2019 study. J Am Coll Cardiol 2020;76(25):2982-3021.
• [2] Ma Q, Zhu J, Zheng P, Zhang J, Xia X, Zhao Y, et al. Global burden of atrial fibrillation/flutter: Trends from 1990 to 2019 and projections until 2044. Heliyon 2024;10(2).
• [3] Dai H, Zhang Q, Much AA, Maor E, Segev A, Beinart R, et al. Global, regional, and national prevalence, incidence, mortality, and risk factors for atrial fibrillation, 1990-2017: results from the Global Burden of Disease Study 2017. Eur Heart JQuality Care Clin Outcomes 2021;7(6):574-82.
• [4] Gunawardene MA, Willems S. Atrial fibrillation progression and the importance of early treatment for improving clinical outcomes. EP Europace 2022;24 (Supplement_2):ii22-ii28.
• [5] Pham TH, Sree V, Mapes J, Dua S, Lih OS, Koh JE, et al. A novel machine learning framework for automated detection of arrhythmias in ECG segments. J Ambient Intell Hum Comput 2021:1-18.
• [6] Subramanian K, Prakash NK. Machine Learning based Cardiac Arrhythmia detection from ECG signal. In 2020 Third International Conference on smart systems and inventive technology (ICSSIT) 2020;(pp. 1137-1141). IEEE.
• [7] Kumari CU, Murthy ASD, Prasanna BL, Reddy MPP, Panigrahy AK. An automated detection of heart arrhythmias using machine learning technique: SVM. Mater Today Proc 2021;45:1393-8.
• [8] Ruipérez-CS RM, Ramírez E, Cebrián A, Millet J, Castells F. Clustering and machine learning framework for medical time series classification. Biocybernetics Biomed Eng 2024;44(3):521-33.
• [9] Yakut Ö, Bolat ED. A high-performance arrhythmic heartbeat classification using ensemble learning method and PSD based feature extraction approach. Biocybernet Biomed Eng 2022;42(2):667-80.
• [10] Nahak S, Pathak A, Saha G. Evaluation of handcrafted features and learned representations for the classification of arrhythmia and congestive heart failure in ECG. Biomed Signal Process Control 2023;79:104230.
• [11] Montenegro L, Abreu M, Fred A, Machado JM. Human-Assisted vs. deep learning feature extraction: an evaluation of ECG Features extraction methods for arrhythmia classification using machine learning. Appl Sci 2022;12(15):7404.
• [12] Venkatesh NP, Kumar RP, Neelapu BC, Pal K, Sivaraman J. Automated atrial arrhythmia classification using 1D-CNN-BiLSTM: A deep network ensemble model. Biomed Signal Process Control 2024;97:106703.
• [13] Ferretti J, Randazzo V, Cirrincione G, Pasero E. 1-D convolutional neural network for ECG arrhythmia classification. Progr Artif Intelligence Neural Syst 2021: 269-79.
• [14] Ahmed AA, Ali W, Abdullah TA, Malebary SJ. Classifying cardiac arrhythmia from ECG signal using 1D CNN deep learning model. Mathematics 2023;11(3):562.
• [15] Allam JP, Samantray S, Sahoo SP, Ari S. A deformable CNN architecture for predicting clinical acceptability of ECG signal. Biocybernetics Biomed Eng 2023;43 (1):335-51.
• [16] Ben-Moshe N, Tsutsui K, Biton S, Zvuloni E, Sörnmo L, RawECGNet BJA. Deep learning generalization for atrial fibrillation detection from the raw ECG. IEEE J Biomed Health Inform 2024.
• [17] Lu X, Wang X, Zhang W, Wen A, Ren Y. An end-to-end model for ECG signals classification based on residual attention network. Biomed Signal Process Control 2023;80:104369.
• [18] Habineza T, Ribeiro AH, Gedon D, Behar JA, Ribeiro ALP, Schön TB. End-to-end risk prediction of atrial fibrillation from the 12-Lead ECG by deep neural networks. J Electrocardiol 2023;81:193-200.
• [19] Kim DH, Lee G, Kim SH. An ECG stitching scheme for driver arrhythmia classification based on deep learning. Sensors 2023;23(6):3257.
• [20] Wang T, Lu C, Sun Y, Yang M, Liu C, Ou C. Automatic ECG classification using continuous wavelet transform and convolutional neural network. Entropy 2021;23 (1):119.
• [21] Mewada H. 2D-wavelet encoded deep CNN for image-based ECG classification. Multimed Tools Appl 2023;82(13):20553-69.
• [22] Madan P, Singh V, Singh DP, Diwakar M, Pant B, Kishor A. A hybrid deep learning approach for ECG-based arrhythmia classification. Bioengineering 2022;9(4):152.
• [23] Mathunjwa BM, Lin YT, Lin CH, Abbod MF, Shieh JS. ECG arrhythmia classification by using a recurrence plot and convolutional neural network. Biomed Signal Process Control 2021;64:102262.
• [24] Yang J, Xi C. Detection of congestive heart failure based on Gramian angular field and two-dimensional symbolic phase permutation entropy. Biocybern Biomed Eng 2024;44(3):674-88.
• [25] Atal DK, Singh M. Arrhythmia classification with ECG signals based on the optimization-enabled deep convolutional neural network. Comput Methods Programs Biomed 2020;196:105607.
• [26] Degirmenci M, Ozdemir MA, Izci E, Akan A. Arrhythmic heartbeat classification using 2d convolutional neural networks. Irbm 2022;43(5):422-33.
• [27] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv 2014;1409.1556.
• [28] Jiao Y, Qi H, Wu J. Capsule network assisted electrocardiogram classification model for smart healthcare. Biocybern Biomed Eng 2022;42(2):543-55.
• [29] Rahul J, Sharma LD. Automatic cardiac arrhythmia classification based on hybrid 1-D CNN and Bi-LSTM model. Biocybernetics Biomed Eng 2022;42(1):312-24.
• [30] Gan Y, Shi JC, He WM, Sun FJ. Parallel classification model of arrhythmia based on DenseNet-BiLSTM. Biocybernetics Biomed Eng 2021;41(4):1548-60.
• [31] Yang X, Yang H, Dou M. ADLNet: an adaptive network for arrhythmia classification based on deformable convolution and LSTM. SIViP 2024:1-12.
• [32] Khaliran MUK, Zabbah I, Faraji M, Ebrahimpour R. Improving deep learning in arrhythmia Detection: The application of modular quality and quantity controllers in data augmentation. Biomed Signal Process Control 2024;91:105940.
• [33] Weimann K, Conrad TO. Transfer learning for ECG classification. Sci Rep 2021;11 (1):5251.
• [34] Xia Y, Xu Y, Chen P, Zhang J, Zhang Y. Generative adversarial network with transformer generator for boosting ECG classification. Biomed Signal Process Control 2023;80:104276.
• [35] Jeong DU, Lim KM. Convolutional neural network for classification of eight types of arrhythmias using 2D time-frequency feature map from standard 12-lead electrocardiogram. Sci Rep 2021;11(1):20396.
• [36] Chen CY, Lin YT, Lee SJ, Tsai WC, Huang TC, Liu YH, et al. Automated ECG classification based on 1D deep learning network. Methods 2022;202:127-35.
• [37] Cheng Y, Li D, Wang D, Chen Y, Wang L. Multi-label arrhythmia classification using 12-lead ECG based on lead feature guide network. Eng Appl Artif Intel 2024;129: 107599.
• [38] Qaisar SM, Khan SI, Dallet D, Tadeusiewicz R, Pławiak P. Signal-piloted processing metaheuristic optimization and wavelet decomposition based elucidation of arrhythmia for mobile healthcare. Biocybernetics Biomed Eng 2022;42(2):681-94.
• [39] Liu Y, Liu J, Tian Y, Jin Y, Li Z, Zhao L, et al. Pruned lightweight neural networks for arrhythmia classification with clinical 12-Lead ECGs. Appl Soft Comput 2024; 154:111340.
• [40] Li Y, Chen M, Liu L, Han B, Zhang L, Wei S. An atrial fibrillation detection algorithm based on lightweight design architecture and feature fusion strategy. Biomed Signal Process Control 2024;91:106016.
• [41] Kung BH, Hu PY, Huang CC, Lee CC, Yao CY, Kuan CH. An efficient ECG classification system using resource-saving architecture and random forest. IEEE J Biomed Health Inform 2020;25(6):1904-14.
• [42] Bechinia H, Benmerzoug D, Khlifa N. Approach based lightweight custom convolutional neural network and fine-tuned MobileNet-V2 for ECG arrhythmia signals classification. IEEE Access 2024;12:40827-41.
• [43] Xiao J, Liu J, Yang H, Liu Q, Wang N, Zhu Z. ULECGNet: An ultra-lightweight endto-end ECG classification neural network. IEEE J Biomed Health Inform 2021;26 (1):206-17.
• [44] Meng L, Tan W, Ma J, Wang R, Yin X, Zhang Y. Enhancing dynamic ECG heartbeat classification with lightweight transformer model. Artif Intell Med 2022;124: 102236.
• [45] Neri L, Oberdier MT, van Abeelen KC, Menghini L, Tumarkin E, Tripathi H, et al. Electrocardiogram monitoring wearable devices and artificial-intelligence-enabled diagnostic capabilities: a review. Sensors 2023;23(10):4805.
• [46] Lee J, Shin M. Method for solving difficulties in rhythm classification caused by few samples and similar characteristics in electrocardiograms. Bioengineering 2023;10 (2):196.
• [47] Moody GB, Mark RG. The impact of the MIT-BIH arrhythmia database. IEEE Eng Med Biol Mag 2001;20(3):45-50.
• [48] Zheng J, Zhang J, Danioko S, Yao H, Guo H, Rakovski C. A 12-lead electrocardiogram database for arrhythmia research covering more than 10,000 patients. Sci Data 2020;7(1):48.
• [49] Cosío FG. Atrial flutter, typical and atypical: a review. Arrhythmia Electrophysiol Rev 2017;6(2):55.
• [50] AAMI. ANSI/AAMI EC57:2012 - Testing and Reporting Performance Results of Cardiac Rhythm and ST Segment Measurement Algorithms. 2012.
• [51] Ullah A, Anwar SM, Bilal M, Mehmood RM. Classification of arrhythmia by using deep learning with 2-D ECG spectral image representation. Remote Sens (Basel) 2020;12(10):1685.
• [52] Zhang H, Liu C, Zhang Z, Xing Y, Liu X, Dong R, et al. Recurrence plot-based approach for cardiac arrhythmia classification using inception-ResNet-v2. Front Physiol 2021;12:648950.
• [53] Lee J, Shin M. Using beat score maps with successive segmentation for ECG classification without R-peak detection. Biomed Signal Process Control 2024;91: 105982.
• [54] Abd-jabbar EY, Al-Hatab MMM, Qasim MA, Fadhil MA. Clinical fusion for real-time complex QRS pattern detection in wearable ecg using the pan-tompkins algorithm. Fusion: Practice and Application (FPA) 2023;12(2):172-84.
• [55] Ivora A, Viscor I, Nejedly P, Smisek R, Koscova Z, Bulkova V, et al. QRS detection and classification in Holter ECG data in one inference step. Sci Rep 2022;12(1): 12641.
• [56] Kapsecker M, Charushnikov N, Nissen L, Jonas SM. PeakSwift: mobile detection of r-peaks in single lead electrocardiograms. SoftwareX 2024;25:101608.
• [57] Howard AG. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv 2017;1704.04861. Preprint.
• [58] Chen C, Hua Z, Zhang R, Liu G, Wen W. Automated arrhythmia classification based on a combination network of CNN and LSTM. Biomed Signal Process Control 2020; 57:101819.
• [59] Pokaprakarn T, Kitzmiller RR, Moorman R, Lake DE, Krishnamurthy AK, Kosorok MR. Sequence to sequence ECG cardiac rhythm classification using convolutional recurrent neural networks. IEEE J Biomed Health Inform 2021;26 (2):572-80.
• [60] Tran DT, Tran QN, Dang TTK, Tran DH. A novel approach for long ECG synthesis utilize diffusion probabilistic model. In: Proceedings of the 2023 8th International Conference on Intelligent Information Technology; 2023;(pp.. p. 251-8.
• [61] Alamatsaz N, Tabatabaei L, Yazdchi M, Payan H, Alamatsaz N, Nasimi F. A lightweight hybrid CNN-LSTM explainable model for ECG-based arrhythmia detection. Biomed Signal Process Control 2024;90:105884.
• [62] Aziz S, Ahmed S, Alouini MS. ECG-based machine-learning algorithms for heartbeat classification. Sci Rep 2021;11(1):18738.
• [63] Purkayastha BB, Hazarika A, Thomas A, Poddar S. Cardiac anomaly detection using embedded attractors reconstructed from multichannel ECG. In: Proceedings of the 2022 9th International Conference on Biomedical and Bioinformatics Engineering; 2022. p. 120-6.
• [64] Tahmid MT, Kader ME, Mahmud T, Fattah SA. MD-CardioNet: a multi-dimensional deep neural network for cardiovascular disease diagnosis from electrocardiogram. IEEE J Biomed Health Inform 2023.
• [65] Yoon T, Kang D. Bimodal CNN for cardiovascular disease classification by cotraining ECG grayscale images and scalograms. Sci Rep 2023;13(1):2937.
• [66] Jeong Y, Lee J, Shin M. Enhancing inter-patient performance for arrhythmia classification with adversarial learning using beat-score maps. Appl Sci 2024;14 (16):7227.
• [67] Wazed S, Chowdhury MS, Sian M, Rahman A, Mahmud T, Shawon MMH, et al. Deep learning-based arrhythmia detection using convolutional neural network. In 2024 IEEE 9th International Conference for Convergence in Technology 2024; (I2CT)(pp. 1-6). IEEE.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).