K-B2S+: A one-dimensional CNN model for AF detection with short single-lead ECG waves from wearable devices

Abstract

Wearable signal analysis is an important technology for monitoring physiological signals without interfering with an individual's daily behavior. As detecting cardiovascular diseases can dramatically reduce mortality, arrhythmia recognition using ECG signals has attracted much attention. In this paper, we propose a single-channel convolutional neural network to detect Atrial Fibrillation (AF) based on ECG signals collected by wearable devices. It contains 3 primary modules. All recordings are firstly uniformly sized, normalized, and Butterworth low-pass filtered for noise removal. Then the preprocessed ECG signals are fed into convolutional layers for feature extraction. In the classification module, the preprocessed signals are fed into convolutional layers containing large kernels for feature extraction, and the fully connected layer provides probabilities. During the training process, the output of the previous pooling layer is concatenated with the vectors of the convolutional layer as a new feature map to reduce feature loss. Numerous comparison and ablation experiments are performed on the 2017 PhysioNet/CinC Challenge dataset, demonstrating the superiority of the proposed method.

Keywords

Single-lead ECG / Wearable devices / Feature concatenating / Atrial fibrillation

CRediT authorship contribution statement

Bo Fang: Writing - original draft, Software. Zhaocheng Yu: Software, Conceptualization. Li-bo Zhang: Validation, Supervision. Yue Teng: Validation, Supervision, Investigation. Junxin Chen: Writing - review & editing, Supervision.

Declaration of Competing Interest

The authors declare that they have no conflict of interest.

Acknowledgements

This work is funded by the National Natural Science Foundation of China (No. 62171114), the Fundamental Research Funds for the Central Universities (No. DUT22RC(3)099), and Xiaomi Young Talents Program.

References

[1] F. Melgani, Y. Bazi, Classification of electrocardiogram signals with support vector machines and particle swarm optimization, IEEE Trans. Inf. Technol. Biomed. 12 (5) (2008) 667-677.

[2] J. Chen, Z. Guo, X. Xu, L.-b. Zhang, Y. Teng, Y. Chen, M. Woźniak, W. Wang, A ro-bust deep learning framework based on spectrograms for heart sound classification, IEEE/ACM Trans. Comput. Biol. Bioinform. (2023) 1-12.

[3] J. Chen, S. Sun, L.-b. Zhang, B. Yang, W. Wang, Compressed sensing framework for heart sound acquisition in Internet of medical things, IEEE Trans. Ind. Inform. 18 (3) (2021) 2000-2009.

[4] L. Fauchier, O. Villejoubert, N. Clementy, A. Bernard, B. Pierre, D. Angoulvant, F. Ivanes, D. Babuty, G.Y. Lip, Causes of death and influencing factors in patients with atrial fibrillation, Am. J. Med. 129 (12) (2016) 1278-1287.

[5] W. Wang, X. Yu, B. Fang, Y. Zhao, Y. Chen, W. Wei, J. Chen, Cross-modality LGE-CMR segmentation using image-to-image translation based data augmentation, IEEE/ACM Trans. Comput. Biol. Bioinform. 20 (4) (2023) 2367-2375.

[6] Y. Liu, J. Chen, B. Fang, Y. Chen, Z. Lv, Ensemble learning-based atrial fibrillation detection from single lead ECG wave for wireless body sensor network, IEEE Trans. Netw. Sci. Eng. 10 (5) (2023) 2627-2636.

[7] J. Chen, W. Wang, B. Fang, Y. Liu, K. Yu, V.C.M. Leung, X. Hu, Digital twin empow-ered wireless healthcare monitoring for smart home, IEEE J. Sel. Areas Commun. 41 (11) (2023) 3662-3676.

[8] T.A. Lankveld, S. Zeemering, H.J. Crijns, U. Schotten, The ECG as a tool to determine atrial fibrillation complexity, Heart 100 (14) (2014) 1077-1084.

[9] K. Rajakariar, A.N. Koshy, J.K. Sajeev, S. Nair, L. Roberts, A.W. Teh, Accuracy of a smartwatch based single-lead electrocardiogram device in detection of atrial fibril-lation, Heart 106 (9) (2020) 665-670.

[10] S. Patidar, A. Sharma, N. Garg,Automated detection of atrial fibrillation using Fourier-Bessel expansion and teager energy operator from electrocardiogram sig-nals, in: 2017 Computing in Cardiology (CinC), IEEE, 2017, pp. 1-4.

[11] R. Mahajan, R. Kamaleswaran, J.A. Howe, O. Akbilgic,Cardiac rhythm classification from a short single lead ECG recording via random forest, in: 2017 Computing in Cardiology (CinC), IEEE, 2017, pp. 1-4.

[12] L. Billeci, F. Chiarugi, M. Costi, D. Lombardi, M. Varanini,Detection of af and other rhythms using rr variability and ECG spectral measures, in: 2017 Computing in Cardiology (CinC), IEEE, 2017, pp. 1-4.

[13] M.S. Islam, M.M.B. Ismail, O. Bchir, M. Zakariah, Y.A. Alotaibi, Robust detection of atrial fibrillation using classification of a linearly-transformed window of rr intervals tachogram, IEEE Access 7 (2019) 110012-110022.

[14] B. Fang, J. Chen, Y. Liu, W. Wang, K. Wang, A.K. Singh, Z. Lv, Dual-channel neu-ral network for atrial fibrillation detection from a single lead ECG wave, IEEE J. Biomed. Health Inform. 27 (5) (2023) 2296-2305.

[15] Q. Li, X. Yu, J. Chen, B.-G. He, W. Wang, D.B. Rawat, Z. Lyu, Pga-net: polynomial global attention network with mean curvature loss for lane detection, IEEE Trans. Intell. Transp. Syst. 25 (1) (2024) 417-429.

[16] B.-G. He, L. Wang, X.-T. Feng, R.-L. Zhen, Failure modes of jointed granite subjected to weak dynamic disturbance under true-triaxial compression, Rock Mech. Rock Eng. 56 (11) (2023) 7939-7957.

[17] B.-G. He, Q. Tong, X.-T. Feng, Q. Jiang, H. Li, Y. Li, Z. Li, Brittle failure modes of underground powerhouses: an insight based on true triaxial compression tests, Bull. Eng. Geol. Environ. 82 (4) (2023) 153.

[18] B.-G. He, B. Lin, H.-P. Li, S.-Q. Zhu, Suggested method of utilizing soil arching for optimizing the design of strutted excavations, Tunn. Undergr. Space Technol. 143 (2024) 105450.

[19] Y. Zhang, S.C. Satapathy, L.-Y. Zhu, J.M. Gorriz, S. Wang, A seven-layer convolu-tional neural network for chest ct-based covid-19 diagnosis using stochastic pooling, IEEE Sens. J. 22 (18) (2022) 17573-17582.

[20] Y.-D. Zhang, S.C. Satapathy, D. Wu, D.S. Guttery, J.M. Górriz, S.-H. Wang, Improv-ing ductal carcinoma in situ classification by convolutional neural network with exponential linear unit and rank-based weighted pooling, Complex Intell. Syst. 7 (2021) 1295-1310.

[21] S.-H. Wang, V.V. Govindaraj, J.M. Górriz, X. Zhang, Y.-D. Zhang,Covid-19 classi-fication by fgcnet with deep feature fusion from graph convolutional network and convolutional neural network, Inf. Fusion 67 ( 2021) 208-229.

[22] B. Fang, J. Chen, W. Wang, Y. Zhou,Combining multiple style transfer networks and transfer learning for lge-cmr segmentation, in: ICASSP 2022-2022 IEEE In-ternational Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, pp. 1201-1205.

[23] Q. Li, X. Huang, Z. Wan, L. Hu, S. Wu, J. Zhang, S. Shan, Z. Wang,Data-efficient masked video modeling for self-supervised action recognition, in:Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 2723-2733.

[24] B.S. Chandra, C.S. Sastry, S. Jana, S. Patidar,Atrial fibrillation detection using con-volutional neural networks, in: 2017 Computing in Cardiology (CinC), IEEE, 2017, pp. 1-4.

[25] J. Rubin, S. Parvaneh, A. Rahman, B. Conroy, S. Babaeizadeh, Densely connected convolutional networks for detection of atrial fibrillation from short single-lead ECG recordings, J. Electrocardiol. 51 (6) (2018) S18-S21.

[26] M. Limam, F. Precioso,Atrial fibrillation detection and ECG classification based on convolutional recurrent neural network, in: 2017 Computing in Cardiology (CinC), IEEE, 2017, pp. 1-4.

[27] X. Ding, X. Zhang, J. Han, G. Ding,Scaling up your kernels to 31x31: revisiting large kernel design in cnns,in:Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11963-11975.

[28] P. Warrick, M.N. Homsi,Cardiac arrhythmia detection from ECG combining convo-lutional and long short-term memory networks, in: 2017 Computing in Cardiology (CinC), IEEE, 2017, pp. 1-4.

[29] S. Butterworth, et al., On the theory of filter amplifiers, Wirel. Eng. 7 (6) (1930) 536-541.

[30] H. Jiawei, K. Micheline, P. Jian, Data Mining Concepts and Techniques, third edi-tion, The Morgan Kaufmann Series in Data Management Systems, vol. 5 (4), 2011, pp. 83-124.

[31] Z. Zhou, M.M.R. Siddiquee, N. Tajbakhsh, J. Liang,Unet++: redesigning skip con-nections to exploit multiscale features in image segmentation, IEEE Trans. Med. Imaging 39 (6) (2019) 1856-1867.

[32] G. Bouchard,Efficient bounds for the softmax function and applications to approxi-mate inference in hybrid models, in:NIPS 2007 Workshop for Approximate Bayesian Inference in Continuous/Hybrid Systems, Vol. 6, 2007.

[33] A. Krizhevsky, I. Sutskever, G.E. Hinton, Imagenet classification with deep convolu-tional neural networks, Commun. ACM 60 (6) (2017) 84-90.

[34] M.I. Jordan, T.M. Mitchell, Machine learning: trends, perspectives, and prospects, Science 349 (6245) (2015) 255-260.

[35] J. Chung, C. Gulcehre, K. Cho, Y. Bengio,Gated feedback recurrent neural networks, in:International Conference on Machine Learning, PMLR, 2015, pp. 2067-2075.

[36] D.P. Kingma, J. Ba, Adam: a method for stochastic optimization, arXiv preprint, arXiv :1412.6980.

[37] S. Ruder,An overview of gradient descent optimization algorithms, arXiv preprint, arXiv :1609.04747.

[38] G.D. Clifford, C. Liu, B. Moody, L.-w.H. Lehman, I. Silva, Q. Li, A.E. Johnson, R.G. Mark, Af classification from a short single lead ECG recording: the physionet/com-puting in cardiology challenge 2017, in: 2017 Computing in Cardiology (CinC), 2017, pp. 1-4.

[39] Z. Yu, J. Chen, Y. Liu, Y. Chen, T. Wang, R. Nowak, Z. Lv, Ddcnn: a deep learning model for af detection from a single-lead short ecg signal, IEEE J. Biomed. Health Inform. 26 (10) (2022) 4987-4995.

[40] S. Hong, M. Wu, Y. Zhou, Q. Wang, J. Shang, H. Li, J. Xie,Encase: an ensemble classifier for ECG classification using expert features and deep neural networks, in: 2017 Computing in Cardiology (cinc), IEEE, 2017, pp. 1-4.

[41] M. Vollmer, P. Sodmann, L. Caanitz, N. Nath, L. Kaderali,Can supervised learning be used to classify cardiac rhythms?, in: 2017 Computing in Cardiology (CinC), IEEE, 2017, pp. 1-4.

[42] Z. Xiong, M.K. Stiles, J. Zhao,Robust ECG signal classification for detection of atrial fibrillation using a novel neural network, in: 2017 Computing in Cardiology (CinC), IEEE, 2017, pp. 1-4.

[43] P. Cao, X. Li, K. Mao, F. Lu, G. Ning, L. Fang, Q. Pan, A novel data augmentation method to enhance deep neural networks for detection of atrial fibrillation, Biomed. Signal Process. Control 56 (2020) 101675.