Research on a CNN Based Clinical Electrocardiogram Classification Model

Abstract:

Electrocardiogram (ECG) is the most commonly used diagnostic method for heart diseases such as arrhythmia. However, its inherent complexity, to some extent, reduces the accuracy of diagnosis. To quickly and automatically identify the type of arrhythmia, this paper constructs a clinical ECG classification model based on Convolutional Neural Network (CNN) to assist clinicians in analyzing ECG signals. The MIT-BIH ECG database is used as the research data source, and the heart beats are classified into 5 categories based on AAMI EC57 standard. 95% of the ECG data is randomly divided into training and testing sets, and the remaining 5% is used as the internal testing set. Based on the experimental outcomes, the model's accuracy exceeds 96%, indicating a commendable overall performance.

• Periodical: Advances in Science and Technology (Volume 166)
• Pages: 123-131
• DOI: https://doi.org/10.4028/p-fj7A4X
• Online since: June 2025
• Authors: Jia Lun Lin, Jin Yang Xia, Xiao Ling Li*
• Keywords: AAMI EC57, Arrhythmias, Convolutional Neural Network (CNN), Electrocardiogram (ECG)

References

[1] Goldberger A L, Goldberger Z D, Shvilkin A. ECG Leads [M]//Goldberger A L, Goldberger Z D, Shvilkin A. Goldberger's Clinical Electrocardiography. Elsevier. 2018: 21-31.

DOI: 10.1016/b978-0-323-40169-2.00004-4

[2] W Z, CHEN X, WANG Y, et al. Arrhythmia Recognition and Classific-ation Using ECG Morphology and Segment Feature Analysis [J]. IEEE/ACMTransactions on Computational Biology and Bioinformatics,2019,16(1): 131-8.

DOI: 10.1109/tcbb.2018.2846611

[3] GOLDBERGERA. Atrioventricular (AV) Heart Block[J]. Goldberger AL Clinical Electrocardiography: A Simplified Approach 7th ed St Louis: Mosby/Elsevier, 2006:203-14.

DOI: 10.1016/b0-323-04038-1/50018-4

[4] Yuan Jiali, Wang Qunshan. Prospects and challenges of artificial intelligence in the diagnosis of arrhythmia [J]. Advances in Cardiology, 2020, 41 (10): 999-1001+6

[5] Galloway CD, Valys AV, Shreibati JB, Treiman DL, Petterson FL, Gundotra VP, et al. Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram. JAMA cardiology. 2019;4(5):428-36.

DOI: 10.1001/jamacardio.2019.0640

[6] Shin HC, Roth HR, Gao M, Lu L, Xu Z, Nogues I, et al. Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning. IEEE transactions on medical imaging.2016;35(5):1285-98.

DOI: 10.1109/tmi.2016.2528162

[7] Yıldırım Ö, Pławiak P, Tan R S, et al. Arrhythmia detection using deep convolutional neural network with long duration ECG signals[J]. Computers in biology and medicine, 2018, 102: 411-420.

DOI: 10.1016/j.compbiomed.2018.09.009

[8] Hannun A Y, Rajpurkar P, Haghpanahi M, et al. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network[J]. Nature medicine, 2019, 25(1): 65-69.

DOI: 10.1038/s41591-018-0268-3

[9] Bazi Y, Al Rahhal M M, Al Hichri H, et al. Real-time mobile-based electrocardiogram system for remote monitoring of patients with cardiac arrhythmias[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2020, 34(10）: 2058013.

DOI: 10.1142/s0218001420580136

[10] Ribeiro AH, Ribeiro MH, Paixao GMM, Oliveira DM, Gomes PR, Canazart JA, et al. Automatic diagnosis of the 12-lead ECG using a deep neural network. Nature communications. 2020; 11(1): 1760.

DOI: 10.1038/s41467-020-15432-4

[11] De Chazal P, O'Dwyer M, Reilly R B. Automatic classification of heartbeats using ECG morphology and heartbeat interval features.[J]. IEEE transactions on bio-medical engineering, 2004, 51(7):1196-1206.

DOI: 10.1109/tbme.2004.827359

[12] MOODY G B, MARK R G. The impact of the MIT-BIH Arrhythmia Database [J].IEEE Engineering in Medicine and Biology Magazine,2001,20(3): 45-50.

DOI: 10.1109/51.932724

[13] MOODY G BMARK R G. The MIT-BIH arrhythmia database on CD-ROM and software for use with it; proceedings of the [1990] Proceedings Computers inCardiology, F, 1990[C]. IEEE, 1990.

DOI: 10.1109/cic.1990.144205

[14] YıLDıRıM Ö, PŁAWIAK P, TAN R-S, et al. Arrhythmia detection using deep convolutional neural network with long duration ECG signals [J]. Computers in Biology and Medicine, 2018, 102: 411-20.

DOI: 10.1016/j.compbiomed.2018.09.009

[15] J. Pan, W. J. Tompkins. A real­time qrs detection algorithm[J]. IEEE Transactions on Biomedical Engineering, 2007, 32(3): 230­236