Detection model of atrial fibrillation based on multi-branch and multi-scale convolutional networks_Journal of Biomedical Engineering

Authors：

ZHAO Siyu ¹ , LIU Ming ¹ , LIU Mingqi ¹ , YANG Xiaoru ² , XIONG Peng ¹ ,  ZHANG Jieshuo ¹

1. College of Electronic and Information Engineering, Hebei University, Baoding, Hebei 071002, P. R. China;
2. Baoding Municipal Productivity Promotion Center, Baoding, Hebei 071023, P. R. China;

Corresponding author：

ZHANG Jieshuo, Email: zhangjieshuo@126.com

Keywords：

Atrial fibrillation detection; Multi-branch neural network; Multi-scale convolution; Mixed loss function

DOI：

10.7507/1001-5515.202303014

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Atrial fibrillation (AF) is a life-threatening heart condition, and its early detection and treatment have garnered significant attention from physicians in recent years. Traditional methods of detecting AF heavily rely on doctor’s diagnosis based on electrocardiograms (ECGs), but prolonged analysis of ECG signals is very time-consuming. This paper designs an AF detection model based on the Inception module, constructing multi-branch detection channels to process raw ECG signals, gradient signals, and frequency signals during AF. The model efficiently extracted QRS complex and RR interval features using gradient signals, extracted P-wave and f-wave features using frequency signals, and used raw signals to supplement missing information. The multi-scale convolutional kernels in the Inception module provided various receptive fields and performed comprehensive analysis of the multi-branch results, enabling early AF detection. Compared to current machine learning algorithms that use only RR interval and heart rate variability features, the proposed algorithm additionally employed frequency features, making fuller use of the information within the signals. For deep learning methods using raw and frequency signals, this paper introduced an enhanced method for the QRS complex, allowing the network to extract features more effectively. By using a multi-branch input mode, the model comprehensively considered irregular RR intervals and P-wave and f-wave features in AF. Testing on the MIT-BIH AF database showed that the inter-patient detection accuracy was 96.89%, sensitivity was 97.72%, and specificity was 95.88%. The proposed model demonstrates excellent performance and can achieve automatic AF detection.

Citation： ZHAO Siyu, LIU Ming, LIU Mingqi, YANG Xiaoru, XIONG Peng, ZHANG Jieshuo. Detection model of atrial fibrillation based on multi-branch and multi-scale convolutional networks. Journal of Biomedical Engineering, 2024, 41(4): 700-707. doi: 10.7507/1001-5515.202303014 Copy

1.	Pereira T, Tran N, Gadhoumi K, et al. Photoplethysmography based atrial fibrillation detection: a review. NPJ Digit Med, 2020, 3(1): 1-12.
2.	Hagiwara Y, Fujita H, Oh S L, et al. Computer-aided diagnosis of atrial fibrillation based on ECG Signals: A review. Inf Sci, 2018, 467: 99-114.
3.	Engdahl J, Rosenqvist M. Large‐scale screening studies for atrial fibrillation–is it worth the effort?. J Intern Med, 2021, 289(4): 474-492.
4.	Healey J S, Connolly S J, Gold M R, et al. Subclinical atrial fibrillation and the risk of stroke. N Engl J Med, 2012, 366(2): 120-129.
5.	Schläpfer J, Wellens H J. Computer-interpreted electrocardiograms: benefits and limitations. J Am Coll Cardiol, 2017, 70(9): 1183-1192.
6.	Kirchhof P, Camm A J, Goette A, et al. Early rhythm-control therapy in patients with atrial fibrillation. N Engl J Med, 2020, 383(14): 1305-1316.
7.	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.
8.	Ramesh J, Solatidehkordi Z, Aburukba R, et al. Atrial fibrillation classification with smart wearables using short-term heart rate variability and deep convolutional neural networks. Sensors, 2021, 21(21): 7233.
9.	Liu S, Wang A, Deng X, et al. MGNN: A multiscale grouped convolutional neural network for efficient atrial fibrillation detection. Comput Biol Med, 2022, 148: 105863.
10.	Rahul J, Sharma L D. Artificial intelligence-based approach for atrial fibrillation detection using normalised and short-duration time-frequency ECG. Biomed Signal Process Control, 2022, 71: 103270.
11.	Shen M, Zhang L, Luo X, et al. Atrial fibrillation detection algorithm based on manual extraction features and automatic extraction features// IOP Conference Series: Earth and Environmental Science. Bangkok: IOP Publishing, 2020: 12050.
12.	季恒宇. 基于多分支卷积神经网络的心律失常分类算法研究. 长春: 吉林大学, 2024.
13.	Hirsch G, Jensen S H, Poulsen E S, et al. Atrial fibrillation detection using heart rate variability and atrial activity: A hybrid approach. Expert Syst Appl, 2021, 169: 114452.
14.	Pereira R, Andreão R V. Inter-patient detection of atrial fibrillation in short ECG segments based on LSTM network with multiple input layers. Res Biomed Eng, 2022, 38(2): 465-476.
15.	Bucklew E A, Reis S E, Kancharla K. Wide QRS tachycardia in a man with a medical history of atrial fibrillation. JAMA Intern Med, 2019, 179(4): 567-569.
16.	Evangelista A B R, Monteiro F R, Nearing B D, et al. Flecainide-induced QRS complex widening correlates with negative inotropy. Heart Rhythm, 2021, 18(8): 1416-1422.
17.	Abedin Z. Differential diagnosis of wide QRS tachycardia: A review. J Arrhythm, 2021, 37(5): 1162-1172.
18.	Hangiel U, Kuśnierz J, Bardyszewski A, et al. Atrial electrogram amplitude variability during atrial fibrillation ablation. J Cardiovasc Electrophysiol, 2023, 34(1): 35-43.
19.	Squara F, Scarlatti D, Bun S S, et al. Fibrillatory wave amplitude evolution during persistent atrial fibrillation ablation: Implications for atrial substrate and fibrillation complexity assessment. J Clin Med, 2022, 11(15): 4519.
20.	Alraies M C, Eisa N, Alraiyes A H, et al. The long and short of it: Ashman’s phenomenon. Am J Med, 2013, 126(11): 962-963.
21.	Goldberger Z D, Rho R W, Page R L. Approach to the diagnosis and initial management of the stable adult patient with a wide complex tachycardia. Am J Cardiol, 2008, 101(10): 1456-1466.
22.	Harrigan R A, Garg M. An interesting cause of wide complex tachycardia: Ashman’s phenomenon in atrial fibrillation. J Emerg Med, 2013, 45(6): 835-841.
23.	Mousavi S, Afghah F, Acharya U R. HAN-ECG: An interpretable atrial fibrillation detection model using hierarchical attention networks. Comput Biol Med, 2020, 127: 104057.
24.	Petmezas G, Haris K, Stefanopoulos L, et al. Automated atrial fibrillation detection using a hybrid CNN-LSTM network on imbalanced ECG datasets. Biomed Signal Process Control, 2021, 63: 102194.
25.	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.
26.	濮玉, 朱俊江, 张德涛, 等. 基于改进卷积神经网络的房颤筛查算法. 生物医学工程学杂志, 2021, 38(4): 686-694.
27.	Goldberger A L, Amaral L A, Glass L, et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation, 2000, 101(23): e215-e220.
28.	Reddy G U, Muralidhar M, Varadarajan S. ECG De-Noising using improved thresholding based on Wavelet transforms. Int J Comput Sci Netw Secur, 2009, 9(9): 221-225.
29.	Wang Z, Zhu J, Yan T, et al. A new modified wavelet-based ECG denoising. Comput Assist Surg, 2019, 24: 174-183.
30.	Marinho L B, de MM Nascimento N, Souza J W M, et al. A novel electrocardiogram feature extraction approach for cardiac arrhythmia classification. Future Gener Comput Syst, 2019, 97: 564-577.
31.	Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 2818-2826.
32.	Zhang H, Wu C, Zhang Z, et al. Resnest: Split-attention networks// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 2736-2746.

1. Pereira T, Tran N, Gadhoumi K, et al. Photoplethysmography based atrial fibrillation detection: a review. NPJ Digit Med, 2020, 3(1): 1-12.
2. Hagiwara Y, Fujita H, Oh S L, et al. Computer-aided diagnosis of atrial fibrillation based on ECG Signals: A review. Inf Sci, 2018, 467: 99-114.
3. Engdahl J, Rosenqvist M. Large‐scale screening studies for atrial fibrillation–is it worth the effort?. J Intern Med, 2021, 289(4): 474-492.
4. Healey J S, Connolly S J, Gold M R, et al. Subclinical atrial fibrillation and the risk of stroke. N Engl J Med, 2012, 366(2): 120-129.
5. Schläpfer J, Wellens H J. Computer-interpreted electrocardiograms: benefits and limitations. J Am Coll Cardiol, 2017, 70(9): 1183-1192.
6. Kirchhof P, Camm A J, Goette A, et al. Early rhythm-control therapy in patients with atrial fibrillation. N Engl J Med, 2020, 383(14): 1305-1316.
7. 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.
8. Ramesh J, Solatidehkordi Z, Aburukba R, et al. Atrial fibrillation classification with smart wearables using short-term heart rate variability and deep convolutional neural networks. Sensors, 2021, 21(21): 7233.
9. Liu S, Wang A, Deng X, et al. MGNN: A multiscale grouped convolutional neural network for efficient atrial fibrillation detection. Comput Biol Med, 2022, 148: 105863.
10. Rahul J, Sharma L D. Artificial intelligence-based approach for atrial fibrillation detection using normalised and short-duration time-frequency ECG. Biomed Signal Process Control, 2022, 71: 103270.
11. Shen M, Zhang L, Luo X, et al. Atrial fibrillation detection algorithm based on manual extraction features and automatic extraction features// IOP Conference Series: Earth and Environmental Science. Bangkok: IOP Publishing, 2020: 12050.
12. 季恒宇. 基于多分支卷积神经网络的心律失常分类算法研究. 长春: 吉林大学, 2024.
13. Hirsch G, Jensen S H, Poulsen E S, et al. Atrial fibrillation detection using heart rate variability and atrial activity: A hybrid approach. Expert Syst Appl, 2021, 169: 114452.
14. Pereira R, Andreão R V. Inter-patient detection of atrial fibrillation in short ECG segments based on LSTM network with multiple input layers. Res Biomed Eng, 2022, 38(2): 465-476.
15. Bucklew E A, Reis S E, Kancharla K. Wide QRS tachycardia in a man with a medical history of atrial fibrillation. JAMA Intern Med, 2019, 179(4): 567-569.
16. Evangelista A B R, Monteiro F R, Nearing B D, et al. Flecainide-induced QRS complex widening correlates with negative inotropy. Heart Rhythm, 2021, 18(8): 1416-1422.
17. Abedin Z. Differential diagnosis of wide QRS tachycardia: A review. J Arrhythm, 2021, 37(5): 1162-1172.
18. Hangiel U, Kuśnierz J, Bardyszewski A, et al. Atrial electrogram amplitude variability during atrial fibrillation ablation. J Cardiovasc Electrophysiol, 2023, 34(1): 35-43.
19. Squara F, Scarlatti D, Bun S S, et al. Fibrillatory wave amplitude evolution during persistent atrial fibrillation ablation: Implications for atrial substrate and fibrillation complexity assessment. J Clin Med, 2022, 11(15): 4519.
20. Alraies M C, Eisa N, Alraiyes A H, et al. The long and short of it: Ashman’s phenomenon. Am J Med, 2013, 126(11): 962-963.
21. Goldberger Z D, Rho R W, Page R L. Approach to the diagnosis and initial management of the stable adult patient with a wide complex tachycardia. Am J Cardiol, 2008, 101(10): 1456-1466.
22. Harrigan R A, Garg M. An interesting cause of wide complex tachycardia: Ashman’s phenomenon in atrial fibrillation. J Emerg Med, 2013, 45(6): 835-841.
23. Mousavi S, Afghah F, Acharya U R. HAN-ECG: An interpretable atrial fibrillation detection model using hierarchical attention networks. Comput Biol Med, 2020, 127: 104057.
24. Petmezas G, Haris K, Stefanopoulos L, et al. Automated atrial fibrillation detection using a hybrid CNN-LSTM network on imbalanced ECG datasets. Biomed Signal Process Control, 2021, 63: 102194.
25. 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.
26. 濮玉, 朱俊江, 张德涛, 等. 基于改进卷积神经网络的房颤筛查算法. 生物医学工程学杂志, 2021, 38(4): 686-694.
27. Goldberger A L, Amaral L A, Glass L, et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation, 2000, 101(23): e215-e220.
28. Reddy G U, Muralidhar M, Varadarajan S. ECG De-Noising using improved thresholding based on Wavelet transforms. Int J Comput Sci Netw Secur, 2009, 9(9): 221-225.
29. Wang Z, Zhu J, Yan T, et al. A new modified wavelet-based ECG denoising. Comput Assist Surg, 2019, 24: 174-183.
30. Marinho L B, de MM Nascimento N, Souza J W M, et al. A novel electrocardiogram feature extraction approach for cardiac arrhythmia classification. Future Gener Comput Syst, 2019, 97: 564-577.
31. Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 2818-2826.
32. Zhang H, Wu C, Zhang Z, et al. Resnest: Split-attention networks// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 2736-2746.

Journal of Biomedical Engineering

Detection model of atrial fibrillation based on multi-branch and multi-scale convolutional networks

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content