Detection and diagnosis of arrhythmias using computational models
Keywords:
ECG Classification, Arrhythmia Detection, Machine Learning, Deep Learning, SVM, ANN, CNNAbstract
Accurate classification of Electrocardiogram (ECG) signals is crucial for early detection of arrhythmias and timely medical intervention. This study introduces a machine learning framework that combines three classifiers—Support Vector Machine (SVM), Artificial Neural Network (ANN), and Convolutional Neural Network (CNN)—to analyze ECG signals from the MIT-BIH Arrhythmia Database. A total of 100,689 ECG signal segments were processed to extract 31 morphological features, such as QRS intervals and peak amplitudes. Experimental results showed that SVM achieved an accuracy of 88.31%, ANN (with 24 hidden neurons) reached 97.01%, and CNN attained a validation accuracy of 96.02%, demonstrating CNN’s advantage in automated feature extraction. These results highlight CNN’s potential for clinical applications by minimizing dependence on manual preprocessing. Future work will focus on refining deep learning architectures for real-time implementation.
References
[1] Anika Alim, Md Kafiul , “Application of Machine Learning in ECG signal Classification Using Morphological Features”, conference paper 2020 IEEE Region 10 Symposium(TENSYMP),DOI: 1109/TENSYMP50017.2020.9230780
[2] Abdul Karin, Samir Brahim Belhaouari, Mobeen Shahroz, Khabib Mustofa and S. Ramana Kumar Joga, “Phishing Detection System Through Hybrid Machine Learning Based on URL”, Research Article ;Date of publication: 3 March 2023, DOI:10.1109/ACCESS.202303252366
[3] Iyengar N, Peng C-K, Morin R, Goldberger AL, Lipsitz LA. Age related alterations in the fractal scaling of cardiac interbeat interval dynamics. Am J Physiol 1996;271:10781084.
[4] Moody GB, Mark RG. The impact of the MIT-BIH Arrhythmia Database. IEEE Eng in Med and Biol 20(3):45-50 (May-June 2001). (PMID: 11446209).
[5] S Pithika,“Electrocardiogram (ECG): Definition and CharacteristicsVeterinary Pharmacology, onlineAvailable:http://www.biologydiscussion.com/veterinarypharmacology/electrocardiogram-ecg-definition-and-characteristics veterinary pharmacology/74308 (accessed on Dececember 17, 2019)
[6] S. Ray, “Understanding Support Vector Machine algorithm from examples (along with code)” 6 October, 2015. [Online document], https://www.analyticsvidhya.com/blog/2017/09/understaing-support vector-machine-example-code/ (accessed on 20 December, 2019)
[7] B. Marr, “What Are Artificial Neural Networks - A Simple Explanation For Absolutely Anyone,” 24 September, 2018, Available: https://www.forbes.com/ (accessed on December 19, 2019)
[8] Q. Zhao and L. Zhang, “ECG feature extraction and classification using wavelet transform and support vector machines,” IEEE International Conference on Neural Networks and Brain (ICNN&B), vol. 2, pp. 1089–1092 (2015).
[9] D. Thanapatay, C. Suwansaroj and C. Thanawattano, “ECG beat classification method for ECG printout with Principle Components Analysis and Support Vector Machines”, International Conference on Electronics and Information Engineering, vol. 1, pp. 72-75 (2010).
[10] C. Venkatesan, P. Karthigaikumar, A. Paul, S. Satheeskumaran, and R. Kumar, ‘‘ECG signal preprocessing and SVM classifier-based abnormality detection in remote healthcare applications,’’ IEEE Access, vol. 6, pp. 9767–9773, (2018).
[11] Y. Bazi, N. Alajlan, H. AlHichri and S. Malek, “Domain adaptation methods for ECG classification”, in: IEEE International Conference on Computer Medical Application (ICCMA), January 2013, pp. 1–4.
[12] N. Jannah and S. Hadjiloucas, “Comparison Between ECG Beat Classifiers Using Multiclass SVM and SIMCA with Time Domain PCA Feature Reduction”, UKSim-AMSS 19th International Conference on Modeling & Simulation, pp. 126-131, (2017).
[13] M.G. Tsipouras, D.I. Fotiadis and D. Sideris, “Arrhythmia classification system based on the RR-interval signal” Artificial Intelligence in Medicine, vol.33, 237—250, (2005).
[14] Z. Zidelmala, A. Amirou, D. O. Abdeslam and J. Merckle, “ECG beat classification using a cost sensitive classifier”, vol. 111 (3), pp.570 577, (2013).
[15] M.K. Gautam, “Morphological Analysis of ECG Arrhythmias using SVM Methodology”, International Journal of Computer Science and Information Security (IJCSIS), Vol. 15, No. 5, pp.421-427, (May 2017)
[16] Iyengar N, Peng C-K, Morin R, Goldberger AL, Lipsitz LA. Age related alterations in the fractal scaling of cardiac interbeat interval dynamics. Am J Physiol 1996;271:1078-1084.
[17] Moody GB, Mark RG. The impact of the MIT-BIH Arrhythmia Database. IEEE Eng in Med and Biol 20(3):45-50 (May-June 2001). (PMID: 11446209)
[18] Greenwald SD. Development and analysis of a ventricular fibrillation detector. M.S. thesis, MIT Dept. of Electrical Engineering and Computer Science, 1986.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Articles in this journal are licensed under the Creative Commons Attribution-NonCommercial 4.0 International License. This license permits others to copy, distribute, and adapt the work, provided it is for non-commercial purposes, and the original author and source are properly credited.
