Automatic Detection of Atrial Fibrillation Based on CNN-LSTM and Shortcut Connection
Abstract
:1. Introduction
2. Technical Background
2.1. Convolutional Neural Network (CNN) Structure
2.1.1. Receptive Field
2.1.2. Weight Sharing
2.2. Long Short-Term Memory (LSTM) Structure
2.3. Shortcut Connection
3. Electrocardiogram (ECG) Data
3.1. Data Source
3.2. Data Preprocessing
3.2.1. Normalization
3.2.2. Data Balance
3.2.3. Cropping
4. Model
4.1. Recurrent Neural Networks
4.2. Multi-Convolutional Neural Network (MCNN)
4.3. 8-layer CNN with Shortcut Connection and 1-layer LSTM (8CSL)
5. Classification Performance Evaluation Index
6. Results
6.1. Experiments of 5 Second Segment
6.2. Experiments of 10 Second Segment
6.3. Experiments of 20 Second Segment
6.4. Overall Results
6.5. Efficiency Experiment of Shortcut Connection
7. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Zhou, Z.Q.; Hu, D.Y. An Epidemiological Study on the Prevalence of Atrial Fibrillation in the Chinese Population of Mainland China. J. Epidemiol. 2008, 18, 209–216. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Narayan, S.M.; Rodrigo, M.; Kowalewski, C.A.; Shenasa, F.; Meckler, G.L.; Vishwanathan, M.N.; Baykaner, T.; Zaman, J.A.; Wang, P.J. Ablation of focal impulses and rotational sources: What can be learned from differing procedural outcomes. Curr. Cardiovasc. Risk Rep. 2017, 11, 27. [Google Scholar] [CrossRef]
- Hansen, B.J.; Zhao, J.; Csepe, T.A.; Moore, B.T.; Li, N.; Jayne, L.A.; Kalyanasundaram, A.; Lim, P.; Bratasz, A.; Powell, K.A.; et al. Atrial fibrillation driven by micro-anatomic intramural re-entry revealed by simultaneous sub-epicardial and sub-endocardial optical mapping in explanted human hearts. Eur. Heart J. 2015, 36, 2390–2401. [Google Scholar] [CrossRef] [PubMed]
- Zhao, J.; Hansen, B.J.; Wang, Y.; Csepe, T.A.; Sul, L.V.; Tang, A.; Yuan, Y.; Li, N.; Bratasz, A.; Powell, K.A.; et al. Three-dimensional integrated functional, structural, and computational mapping to define the structural fingerprints of heart-specific atrial fibrillation drivers in human heart ex vivo. J. Am. Heart Assoc. 2017, 6, e005922. [Google Scholar] [CrossRef] [PubMed]
- Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv 2014, arXiv:1409.1556. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778. [Google Scholar]
- Simonyan, K.; Zisserman, A. Two-stream convolutional networks for action recognition in videos. In Proceedings of the Annual Conference on Neural Information Processing Systems, Montreal, QC, Canada, 8–13 December 2014; pp. 568–576. [Google Scholar]
- Ghiasi, S.; Abdollahpur, M.; Madani, N.; Kiani, K.; Ghaffari, A. Atrial fibrillation detection using feature based algorithm and deep convolutional neural network. In Proceedings of the Computing in Cardiology (CinC), Rennes, France, 24–27 September 2017; pp. 1–4. [Google Scholar]
- Pourbabaee, B.; Roshtkhari, M.J.; Khorasani, K. Deep convolutional neural networks and learning ECG features for screening paroxysmal atrial fibrillation patients. IEEE Trans. Syst. Man Cybern. Syst. 2017, 48, 2095–2104. [Google Scholar] [CrossRef]
- Qayyum, A.; Meriaudeau, F.; Chan, G.C.Y. Classification of Atrial Fibrillation with Pre-Trained Convolutional Neural Network Models. In Proceedings of the 2018 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), Sarawak, Malaysia, 3–6 December 2018; pp. 594–599. [Google Scholar]
- Cho, J.; Kim, Y.; Lee, M. Prediction to Atrial Fibrillation Using Deep Convolutional Neural Networks. In International Workshop on PRedictive Intelligence in Medicine; Springer: Cham, Switzerland, 2018; pp. 164–171. [Google Scholar]
- Wang, J. Automated detection of atrial fibrillation and atrial flutter in ECG signals based on convolutional and improved Elman neural network. Knowl. Based Syst. 2019, 193, 105446. [Google Scholar] [CrossRef]
- Xiong, Z.; Stiles, M.K.; Zhao, J. Robust ECG signal classification for detection of atrial fibrillation using a novel neural network. In Proceedings of the 2017 Computing in Cardiology (CinC), Rennes, France, 24–27 September 2017; pp. 1–4. [Google Scholar] [CrossRef]
- Schwab, P.; Scebba, G.C.; Zhang, J.; Delai, M.; Karlen, W. Beat by beat: Classifying cardiac arrhythmias with recurrent neural networks. In Proceedings of the 2017 Computing in Cardiology, Rennes, France, 24–27 September 2017; pp. 1–4. [Google Scholar]
- Sujadevi, V.G.; Soman, K.P.; Vinayakumar, R. Real-Time Detection of Atrial Fibrillation from Short Time Single Lead ECG Traces Using Recurrent Neural Networks. In The International Symposium on Intelligent Systems Technologies and Applications; Springer: Cham, Switzerland, 2017; pp. 212–221. [Google Scholar]
- Faust, O.; Shenfield, A.; Kareem, M.; San, T.R.; Fujita, H.; Acharya, U.R. Automated detection of atrial fibrillation using long short-term memory network with RR interval signals. Comput. Biol. Med. 2018, 102, 327–335. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Graves, A.; Schmidhuber, J. Framewise phoneme classification with bidirectional lstm and other neural network architectures. Neural Netw. 2005, 18, 602–610. [Google Scholar] [CrossRef] [PubMed]
- Wang, J. A deep learning approach for atrial fibrillation signals classification based on convolutional and modified Elman neural network. Future Gener. Comput. Syst. 2020, 102, 670–679. [Google Scholar] [CrossRef]
- Rubin, J.; Parvaneh, S.; Rahman, A.; Conroy, B.; Babaeizadeh, S. Densely connected convolutional networks for detection of atrial fibrillation from short single-lead ECG recordings. J. Electrocardiol. 2018, 51, S18–S21. [Google Scholar] [CrossRef] [PubMed]
- Bishop, M. Neural Networks for Pattern Recognition; Oxford University Press: Oxford, UK, 1995. [Google Scholar]
- Ripley, D.; Hjort, N. Pattern Recognition and Neural Networks; Cambridge University Press: Cambridge, UK, 1996. [Google Scholar]
- Venables, W.N.; Ripley, B.D. Modern Applied Statistics with SPLUS; Springer Science & Business Media: Berlin/Heidelberg, Germany, 2013. [Google Scholar]
- Lee, C.Y.; Xie, S.; Gallagher, P.; Zhang, Z.; Tu, Z. Deeply-supervised nets. In Proceedings of the Artificial intelligence and statistics, San Diego, CA, USA, 9–12 May 2015; pp. 562–570. [Google Scholar]
- Szegedy Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; Rabinovich, A. Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 7–12 June 2015; pp. 1–9. [Google Scholar]
- Raiko, T.; Valpola, H.; LeCun, Y. Deep learning made easier by linear transformations in perceptrons. In Proceedings of the Artificial Intelligence and Statistics, La Palma, Spain, 21–23 April 2012; pp. 924–932. [Google Scholar]
- Schraudolph, N. Accelerated gradient descent by factor-centering decomposition. Tech. Rep. IDSIA 1998, 98. [Google Scholar] [CrossRef]
- Nielsen, M.A. Neural Networks and Deep Learning; Determination Press: San Francisco, CA, USA, 2015; Volume 25. [Google Scholar]
- Andersen, R.S.; Peimankar, A.; Puthusserypady, S. A deep learning approach for real-time detection of atrial fibrillation. Expert Syst. Appl. 2019, 115, 465–473. [Google Scholar] [CrossRef]
- Chung, J.; Gulcehre, C.; Cho, K.; Bengio, Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv 2014, arXiv:1412.3555. [Google Scholar]
- Chang, P.D. Fully convolutional deep residual neural networks for brain tumor segmentation. In International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries; Springer: Cham, Switzerland, 2016; pp. 108–118. [Google Scholar]
- Fan, X.; Yao, Q.; Cai, Y.; Miao, F.; Sun, F.; Li, Y. Multiscaled fusion of deep convolutional neural networks for screening atrial fibrillation from single lead short ECG recordings. IEEE J. Biomed. Health Inform. 2018, 22, 1744–1753. [Google Scholar] [CrossRef] [PubMed]
- Graves, A.; Mohamed, A.R.; Hinton, G. Speech recognition with deep recurrent neural networks. In Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada, 26–31 May 2013; pp. 6645–6649. [Google Scholar]
- Yao, Z.; Zhu, Z.; Chen, Y. Atrial fibrillation detection by multi-scale convolutional neural networks. In Proceedings of the 2017 20th International Conference on Information Fusion (Fusion), Xi’an, China, 10–13 July 2017; pp. 1–6. [Google Scholar]
- Cui, Z.; Chen, W.; Chen, Y. Multi-scale convolutional neural networks for time series classification. arXiv 2016, arXiv:1603.06995. [Google Scholar]
- Ioffe, S.; Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv 2015, arXiv:1502.03167. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Identity mappings in deep residual networks. In Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands, 11–14 October 2016; Springer: Cham, Switzerland; pp. 630–645. [Google Scholar]
- Srivastava, N.; Hinton, G.; Krizhevsky, A.; Sutskever, I.; Salakhutdinov, R. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 2014, 15, 1929–1958. [Google Scholar]
- Wu, H.; Gu, X. Towards dropout training for convolutional neural networks. Neural Netw. 2015, 71, 1–10. [Google Scholar] [CrossRef] [PubMed] [Green Version]
Reference | Model | Result | |||
---|---|---|---|---|---|
Acc | Sen | Spe | F1 | ||
[8] | CNN | 81.5% | / | / | / |
[9] | DCNN | / | / | / | 80% |
[10] | DCNN | / | / | / | / |
[11] | CNN | 97.89% | 97.12% | 96.99% | / |
[12] | DCNN | / | / | / | / |
[13] | CNN | 82% | / | / | / |
[14] | CNN and IENN | 98.8% | 98.6% | / | / |
[15] | RNNs | / | / | / | / |
[16] | RNN, LSTM, and GRU | 95% | / | / | / |
[17] | DRNN and LSTM | 98.51% | / | / | / |
[18] | LSTM | / | / | / | / |
[19] | CNN and MENN | 97.4% | 97.9% | 97.1% | / |
Type | Recording | Time Length (s) | ||||
---|---|---|---|---|---|---|
Mean | SD | Max | Median | Min | ||
Normal | 5154 | 31.9 | 10.0 | 61.0 | 30 | 9.0 |
AF | 771 | 31.6 | 12.5 | 60.0 | 30 | 10.0 |
Other rhythms | 2557 | 34.1 | 11.8 | 60.9 | 30 | 9.1 |
Noisy | 46 | 27.1 | 9.0 | 60 | 30 | 10.2 |
Data | Acc |
---|---|
Normalized Data | 85.06% |
Original Data | 80.23% |
Model | Input Length | Sen | Spe | Pre | Acc | F1 |
---|---|---|---|---|---|---|
RNN | 5 s | 59.21% | 73.31% | 59.39% | 73.78% | 59.30% |
10 s | 69.03% | 73.19% | 59.00% | 75.03% | 63.62% | |
20 s | 65.27% | 73.13% | 58.14% | 73.38% | 61.50% | |
MCNN | 5 s | 81.87% | 87.72% | 75.50% | 80.03% | 78.56% |
10 s | 82.92% | 88.81% | 81.94% | 82.03% | 82.43% | |
20 s | 80.68% | 88.57% | 80.31% | 79.37% | 76.68% | |
8CSL | 5 s | 84.36% | 89.26% | 85.43% | 81.53% | 84.89% |
10 s | 87.42% | 91.37% | 91.78% | 85.06% | 89.55% | |
20 s | 83.08% | 87.21% | 88.37% | 81.86% | 85.64% |
Model | Speed |
---|---|
Shortcut connection | 11 s |
No shortcut connection | 18 s |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ping, Y.; Chen, C.; Wu, L.; Wang, Y.; Shu, M. Automatic Detection of Atrial Fibrillation Based on CNN-LSTM and Shortcut Connection. Healthcare 2020, 8, 139. https://doi.org/10.3390/healthcare8020139
Ping Y, Chen C, Wu L, Wang Y, Shu M. Automatic Detection of Atrial Fibrillation Based on CNN-LSTM and Shortcut Connection. Healthcare. 2020; 8(2):139. https://doi.org/10.3390/healthcare8020139
Chicago/Turabian StylePing, Yongjie, Chao Chen, Lu Wu, Yinglong Wang, and Minglei Shu. 2020. "Automatic Detection of Atrial Fibrillation Based on CNN-LSTM and Shortcut Connection" Healthcare 8, no. 2: 139. https://doi.org/10.3390/healthcare8020139
APA StylePing, Y., Chen, C., Wu, L., Wang, Y., & Shu, M. (2020). Automatic Detection of Atrial Fibrillation Based on CNN-LSTM and Shortcut Connection. Healthcare, 8(2), 139. https://doi.org/10.3390/healthcare8020139