Abstract
The automatic analysis of electrocardiogram (ECG) data using deep learning has become an important method for the diagnosis of cardiovascular disease. In this paper, we proposed a LSTM-CNN hybrid model based on long short-term memory network (LSTM) and convolutional neural network (CNN) to complete short-term ECG positive anomaly classification tasks. The model can independently learn the structural features of ECG signals and have a certain memory and inference function, and deep mining of temporal correlation between the ECG signal points. Evaluated on the MIT-BIH Arrhythmia Database (MIT-BIH-AR), the experimental results show that the proposed algorithm achieves an accuracy of 99.7%, sensitivity of 99.69%, and specificity of 99.7%, respectively. Over 150,000 short-term ECG clinical records in the Chinese Cardiovascular Disease Database (CCDD) were evaluated for model performance with an accuracy of 93.39%, a sensitivity of 91.18%, and a specificity of 95.21%. The experimental results show that the LSTM-CNN model has an efficient and accurate classification performance on large-scale clinical ECG data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
B. Hedén, M. Ohlsson, H. Holst, M. Mjöman, R. Rittner, O. Pahlm, Detection of frequently overlooked electrocardiographic lead reversals using artificial neural networks. Am. J. Cardiol. 78(5), 600–604 (1996)
Y. DanYang, Research on ECG signal classification based on wavelet packet and neural network. Tianjin Polytechnic University (2017)
S. Shahbudin, S. Shamsudin, H. Mohamad, Discriminating ECG signals using support vector machines, In Computer Applications and Industrial Electronics (Malaysia, 2015), pp. 175–180
A. Krizhevsky, I. Sutskever, G. Hinton, ImageNet classification with deep convolutional neural networks, in International Conference on Neural Information Processing Systems, Lecture Notes in Computer Science (Qatar 2012), pp. 1097–1105
O. Russakovsky, J. Deng, H. Su, ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)
A. Graves, A. Mohamed, G. Hinton, speech recognition with deep recurrent neural networks, in Proceedings of the IEEE Conference on Acoustics (Canada 2013), pp. 6645–6649
Y. Li, J. Zhang, D. Pan, D. Hu, A study of speech recognition based on RNN-RBM language model. J. Comput. Res. Dev. 51(9), 1936–1944 (2014)
K. Cho, B.V. Merrienboer, C. Gulcehre, Learning phrase representations using RNN encoder-decoder for statistical machine translation, in Proceedings of Conference on Empirical Methods in Natural Language Processing (Qatar 2014), pp. 1724–1734
Y. Zhao, D.P. Tao, S.Y. Zhang, L. Jin, Similar handwritten chinese character recognition based on deep neural networks with big data. J. Commun. (2014)
A. Karpathy, G. Toderici, S. Shetty, Large-scale video classification with convolutional neural networks, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (USA, 2014), pp. 1725–1732
P. Rajpurkar, A.Y. Hannun, M. Haghpanahi, C. Bourn, A.Y. Ng, Cardiologist-level arrhythmia detection with convolutional neural networks. Comput. Vis. Pattern Recognit. (2017)
W. Liping, Study on approach of ECG classification with do-main knowledge (East China Normal University, Shanghai, 2013)
Z. Honghai, Research on ECG recognition critical methods and development on remote multi bod characteristic signal monito ring system. Beijing University of Chinese Academy of Sciences (2013)
J. Linpeng, D. Jun, Deep learning research on clinical electrocardiogram analysis. Inf. Sci. 21(3), 398–416 (2015)
Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, T. Darrell, Caffe: convolutional architecture for fast feature embedding. ACM MM, 675–678 (2014)
S. Loffe, C. Szegedy, Batch normalization: accelerating deep network training by reducing internal covariate shift, in International Conference on Machine Learning (China 2015), pp. 448–456
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
G. Moody, R. Mark, The impact of the MIT-BIH arrhythmia database. IEEE Eng. Med. Biol. Mag. 20(3), 45–50 (2002)
Z. Jiawei, L. Xia, D. Jun, CCDD: an enhanced standard ECG database with its management and annotation tools. Int. J. Artif. Intell. Tools 21(05), 6721–676 (2012)
Q. Haini, L. Guozheng, X. Weisheng, An asymmetric classifier based on partial least squares. Pattern Recogn. 43, 3448–3457 (2010)
Acknowledgements
The work is supported by the National Natural Science Foundation of China, under Contract 60841004, 60971110, 61172152, 61473265; the Program of Scientific and Technological Research of Henan Province, China, under Contract 172102310393; the Support Program of Science and Technology Innovation of Henan Province, China, under Contract 17IRTSTHN013; Key Support Project Fund of Henan Province, China, under Contract 18A520011; Fund for “Integration of Cloud Computing and Big Data, Innovation of Science and Education”, under Contract 2017A11017; CERNET Innovation Project, under Contract NGII20161202; the Innovation Research Team of Science & Technology of Henan Province, under Contract 17IRTSTHN013.
Conflicts of Interest
The authors declare that they have no conflicts of interest.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Lu, P., Guo, S., Wang, Y., Qi, L., Han, X., Wang, Y. (2019). ECG Classification Based on Long Short-Term Memory Networks. In: Wu, C., Chyu, MC., Lloret, J., Li, X. (eds) Proceedings of the 2nd International Conference on Healthcare Science and Engineering . ICHSE 2018. Lecture Notes in Electrical Engineering, vol 536. Springer, Singapore. https://doi.org/10.1007/978-981-13-6837-0_10
Download citation
DOI: https://doi.org/10.1007/978-981-13-6837-0_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-6836-3
Online ISBN: 978-981-13-6837-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)