A Convolutional Neural Network Based Deep Network Model for Atrial Fibrillation Detection

Abstract

Atrial Fibrillation (AFib) is a common heart rhythm disorder that can occur in the elderly and even young people without any heart disease. AFib can result in a stroke, heart failure, or sudden death.. All of these existing and future concerns require significant efforts in the early diagnosis of AFib around the world.. Electrocardiographic (ECG) waveforms are considered the most reliable method for detecting abnormal heart rhythms such as AFib. However, due to the complexity and non-linearity of ECG signals, it is difficult to analyze these signals manually. Furthermore, the interpretation of ECG data is subjective and may differ amongst specialists.. Therefore, the use of computer-assisted diagnostic (CAD) systems is important for automatic and reliable detection of AFib. CAD systems have the potential to make objective and accurate evaluation of ECG signals. In this paper, automatic AFib detection from ECG signals was performed using deep learning system. A deep network model was proposed within the scope of this study for the use of convolutional neural network (CNN) architecture, one of the deep learning algorithms, in the AFib classification problem. The dataset used includes normal sinus rhythms (SR) as well as AFib and Atrial Flutter (AFL) arrhythmias. By combining AFib and AFL classes, automatic classification of SR and AFib is provided at the model output. The suggested model was tested on a data set of 5000 samples of ECG signals from patients with 2222 SR and 2218 AFib, respectively. The CNN model developed within the scope of this study achieved 95.09% sensitivity, 97.27% specificity and 97.26% precision values, respectively, during the test phase. The accuracy percentageof the model on the test data was 96.17%.

Keywords

• Atrial fibrillation
• Convolutional neural networks
• Deep learning

Atriyal Fibrilasyon Tespiti için Evrişimli Sinir Ağı Tabanlı Bir Derin Ağ Modeli

Abstract

Atriyal Fibrilasyon (AFib), yaşlılarda ve hatta herhangi bir kalp hastalığı olmayan gençlerde bile görülebilen yaygın bir kalp ritim bozukluğudur. AFib; inme, kalp yetmezliği ve ani ölümlere neden olabilir. Tüm bu mevcut ve gelecekteki endişeler, dünya çapında AFib'in erken tespitinde önemli önlemlerin alınmasını gerektirir. Elektrokardiyografik (EKG) dalga formları, AFib gibi anormal kalp ritimlerini saptamak için en güvenilir yöntem olarak kabul edilmektedir. Ancak EKG sinyallerinin karmaşıklığı ve doğrusal olmaması nedeniyle bu sinyalleri manuel olarak analiz etmek zordur. Bunun yanı sıra, EKG sinyallerinin yorumlanması kişiye özgü ve uzmanlar arasında farklılık gösterebilmektedir. Bu nedenle otomatik ve güvenilir bir AFib algılama için bilgisayar destekli teşhis (BDT) sistemlerinin kullanımı önemlidir. BDT sistemleri, EKG sinyallerinin değerlendirilmesinin objektif ve doğru olmasını sağlayacak potansiyele sahiptir. Bu çalışmada, derin öğrenme yapısı kullanılarak EKG sinyallerinden otomatik AFib tespiti gerçekleştirilmiştir. Derin öğrenme algoritmalarından evrişimli sinir ağı (ESA) mimarisinin AFib sınıflandırma probleminde kullanımı için çalışma kapsamında derin bir ağ modeli tasarlanmıştır. Kullanılan verisetinde normal sinüs ritimlerinin (SR) yanısıra AFib ve Atriyal Flutter (AFL) aritmileri bulunmaktadır. AFib ve AFL sınıfları birleştirilerek model çıkışında SR ve AFib ayırımının otomatik yapılması sağlanmıştır. Önerilen model, 2222 SR ve 2218 AFib tanısı alan kişilere ait her biri 5000 örneğe sahip EKG sinyali içeren veri seti üzerinde uygulanmıştır. Çalışma kapsamında hazırlanan ESA modeli, test aşamasında sırasıyla %95.09 hassasiyet, %97.27 özgüllük ve %97.26 kesinlik değerlerine ulaşmıştır. Modelin test verileri üzerindeki doğruluk oranı %96.17 olarak elde edilmiştir.

Keywords

• Atriyal fibrilasyon
• Evrişimsel sinir ağları
• Derin öğrenme

References

1. [1] S. N. Yu and K. T. Chou, “Integration of independent component analysis and neural networks for ECG beat classification,” Expert Syst. Appl., vol. 34 no. 4, pp. 2841-2846, 2008.
2. [2] J. Huang, B. Chen, B. Yao and W. He, “ECG arrhythmia classification using STFT-Based spectrogram and convolutional neural network,” IEEE Access, vol. 7, pp. 92871-92880, 2019.
3. [3] C. D. Furberg, B. M. Psaty, T. A. Manolio, J. M. Gardin, V. E. Smith, and P. M. Rautaharju, “Prevalence of atrial fibrillation in elderly subjects (the Cardiovascular Health Study),” Am. J. Cardiol., vol. 74, no. 3, pp. 236–241, 1994.
4. [4] Y. Li, Y. Pang, J. Wang, and X. Li, “Patient-specific ECG classification by deeper CNN from generic to dedicated,” Neurocomputing, vol. 314, pp. 336-346, 2018.
5. [5] Ö. Yildirim, “A novel wavelet sequences based on deep bidirectional LSTM network model for ECG signal classification,” Comput. Biol. Med., vol. 96, pp. 189-202, 2018.
6. [6] A. Y. Hannun, P. Rajpurkar, M. Haghpanahi, G. H. Tison, C. Bourn, M. P. Turakhia and Y. A. Ng, “Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network,” Nature Medicine, vol. 25 no. 1, pp. 65-69, 2019.
7. [7] J. Jiang, H. Zhang, D. Pi, and C. Dai, “A novel multi-module neural network system for imbalanced heartbeats classification,” Expert Syst. with Appl. vol. X, no. 1, p. 100003, 2019.
8. [8] S. L. Oh, E. Y. K. Ng, R. S. Tan, and U. R. Acharya, “Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats,” Comput. Biol. Med., vol. 102, pp. 278-287, 2018.

9. [9] B. M. Maweu, S. Dakshit, R. Shamsuddin, and B. Prabhakaran, “CEFEs: A CNN Explainable Framework for ECG Signals,” Artif. Intell. Med., vol. 115, p. 102059, 2021.
10. [10] F. Rabbi, S. Islam, D. Kumar, S. M. R. Islam, and M. Ali, “SCNN : Scalogram-based convolutional neural network to detect obstructive sleep apnea using single-lead electrocardiogram signals,” Comput. Biol. Med., vol. 134, p. 104532, 2021.
11. [11] X. Yang, X. Zhang, M. Yang, and L. Zhang, “12-Lead ECG arrhythmia classi fi cation using cascaded convolutional neural network and expert feature,” J. Electrocardiol., vol. 67, pp. 56–62, 2021.
12. [12] Y. Zhang, Z. Zhao, Y. Deng, X. Zhang, and Y. Zhang, “Biomedical Signal Processing and Control Human identification driven by deep CNN and transfer learning based on multiview feature representations of ECG,” Biomed. Signal Process. Control, vol. 68, no. April, p. 102689, 2021.
13. [13] M. Sepahvand and F. Abdali-mohammadi, “Biomedical Signal Processing and Control A novel multi-lead ECG personal recognition based on signals functional and structural dependencies using time-frequency representation and evolutionary morphological CNN,” Biomed. Signal Process. Control, vol. 68, no. January, p. 102766, 2021.
14. [14] Z. Yao, Z. Zhu, and Y. Chen, “Atrial fibrillation detection by multi-scale convolutional neural networks,” In 2017 20th International Conference on Information Fusion (Fusion) (pp. 1-6). IEEE, 2017.
15. [15] L. S. Y Huang, J Lin, G Wang, Z Ding, “A Multi-dilation Convolution Neural Network for Atrial Fibrillation Detection,” in ICDSP 2020: Proceedings of the 2020 4th International Conference on Digital Signal Processing, pp. 136–140, 2020.
16. [16] F. Murat, O. Yildirim, M. Talo, U. B. Baloglu, Y. Demir, and U. R. Acharya, “Application of deep learning techniques for heartbeats detection using ECG signals-analysis and review,” Comput. Biol. Med., vol. 120, no. April, p. 103726, 2020.
17. [17] Y. Xia, N. Wulan, K. Wang, and H. Zhang, “Detecting atrial fibrillation by deep convolutional neural networks,” Comput. Biol. Med., vol. 93, no. July 2017, pp. 84–92, 2018.
18. [18] Q. H. Nguyen, B. P. Nguyen, T. B. Nguyen, T. T. T. Do, J. F. Mbinta, and C. R. Simpson, “Stacking segment-based CNN with SVM for recognition of atrial fibrillation from single-lead ECG recordings,” Biomed. Signal Process. Control, vol. 68, no. April, p. 102672, 2021.
19. [19] Z. I. Attia et al., “An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction,” Lancet, vol. 394, no. 10201, pp. 861–867, 2019.
20. [20] J. Zheng, J. Zhang, S. Danioko, H. Yao, H. Guo, and C. Rakovski, “A 12-lead electrocardiogram database for arrhythmia research covering more than 10,000 patients,” Sci. Data, vol. 7, no. 1, pp. 1-8, 2020.
21. [21] U. R. Acharya, H. Fujita, O. S. Lih, Y. Hagiwara, J. H. Tan, and M. Adam, “Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network,” Inf. Sci. (Ny)., vol. 405, pp. 81–90, 2017.
22. [22] D. Lai, Y. Bu, Y. Su, X. Zhang, and C. S. Ma, “Non-standardized patch-based ECG lead together with deep learning based algorithm for automatic screening of atrial fibrillation,” IEEE J. Biomed. Heal. Informatics, vol. 24, no. 6, pp. 1569–1578, 2020.
23. [23] S. Nurmaini, A. E. Tondas, A. Darmawahyuni, M.N. Rachmatullah, R. U. Partan, F. Firdaus, B. Tutuko, F. Pratiwi, A. H. Juliano and R. Khoirani, “Robust detection of atrial fibrillation from short-term electrocardiogram using convolutional neural networks,” Futur. Gener. Comput. Syst., vol. 113, pp. 304–317, 2020.