ECG Signal Classification Using Hybrid and Non-Hybrid Learning Technologies
DOI:
https://doi.org/10.31436/ijpcc.v11i1.503Keywords:
Deep Learning, Machine Learning, ECG signals, ClassificationAbstract
Most arrhythmias caused by cardiovascular disorders disrupt the electrical activity of the heart, resulting in changes in the morphology of electrocardiogram (ECG) recordings. By analyzing different ECG patterns and comparing machine learning and deep learning techniques, this research aims to accurately identify twenty-nine different cardiac problems and sinus rhythm. The database contains 48 heart rate recordings at a frequency of 360 Hz for about 25 minutes for five classes, namely “N”, “S”, “V”, “F”, and “Q”. Support Vector Machine (SVM), k-nearest neighbor (k-nearest neighbor) classifier, and random forest (RF) classifier were among the machine learning (ML) techniques used. Experimental results revealed that the random forest classifier achieved the highest classification accuracy, reaching 96.08%, while the support vector machine (SVM) achieved the lowest accuracy, reaching 88.9%. The study included deep learning approaches, namely convolutional neural networks (CNNs), hybrid deep learning models (CNN-LSTM), and recurrent neural networks of the long short-term memory (LSTM) type. Through a comparative analysis of the results of machine learning and deep learning, the best accuracy was achieved by the hybrid deep learning model LSTM-CNN, which achieved 97.25% with a kernel size of 3. Using the Sigmoid and SoftMax activation functions, the model achieved an accuracy of 95.12% and ??97.32%, respectively, with the Adam activation function achieving an accuracy of 98.75%, to achieve the highest accuracy of the proposed model and find a balance between accuracy and speed classification. The main objective of this research is to implement a heart rate classification system from adult electrocardiograms using multiple machine learning and deep learning network architectures.
References
T. Gaziano, K. S. Reddy, F. Paccaud, and S. Horton, “Cardiovascular Disease,” Dis. Control Priorities Dev. Ctries. (2nd Ed., no. Cvd, pp. 645–662, 2006, doi 10.1596/978-0-8213-6179-5/chpt-33.
H. C. Kim, “Epidemiology of cardiovascular disease and its risk factors in Korea,” Glob. Heal. Med., vol. 3, no. 3, pp. 134–141, 2021, doi: 10.35772/ghm.2021.01008.
Mørk, M. S. (2022). Cilostazol a medical treatment for bradycardia of cardiac origin in dogs (Doctoral dissertation).
X. Yang et al., “The highly-cited Electrocardiogram-related articles in science citation index expanded: characteristics and hotspots,” J. Electrocardiol., vol. 47, no. 5, pp. 738–744, 2014, doi: https://doi.org/10.1016/j.jelectrocard.2014.03.005.
E. A. Ashley and J. Niebauer, Conquering the ECG. [Online]. Available: https://www.ncbi.nlm.nih.gov/books/NBK2214/
K. Prashant, P. Choudhary, T. Agrawal, and E. Kaushik, “OWAE-Net: COVID-19 detection from ECG images using deep learning and optimized weighted average ensemble technique,” Intell. Syst. with Appl., vol. 16, no. November, p. 200154, 2022, doi: 10.1016/j.iswa.2022.200154.
T. A. A. Abdullah, M. S. M. Zahid, and W. Ali, “A review of interpretable ml in healthcare: Taxonomy, applications, challenges, and future directions,” Symmetry (Basel)., vol. 13, no. 12, pp. 1–28, 2021, doi: 10.3390/sym13122439.
K. Rasheed, A. Qayyum, M. Ghaly, A. Al-Fuqaha, A. Razi, and J. Qadir, “Explainable, trustworthy, and ethical machine learning for healthcare: A survey,” Comput. Biol. Med., vol. 149, no. September, p. 106043, 2022, doi 10.1016/j.compbiomed.2022.106043.
G. Yang, Q. Ye, and J. Xia, “Unbox the black box for the medical explainable AI via multi-modal and multi-centre data fusion: A mini-review, two showcases and beyond,” Inf. Fusion, vol. 77, no. May 2021, pp. 29–52, 2022, doi: 10.1016/j.inffus.2021.07.016.
G. Stiglic, P. Kocbek, N. Fijacko, M. Zitnik, K. Verbert, and L. Cilar, “Interpretability of machine learning-based prediction models in healthcare,” Wiley Interdiscip. Rev. Data Min. Knowl. Discov., vol. 10, no. 5, pp. 1–13, 2020, doi: 10.1002/widm.1379.
T. A. A. Abdullah, M. S. M. Zahid, and W. Ali, “A Review of Interpretable ML in Healthcare: Taxonomy, Applications, Challenges, and Future Directions,” Symmetry 2021, Vol. 13, Page 2439, vol. 13, no. 12, p. 2439, Dec. 2021, doi: 10.3390/SYM13122439.
K. Rasheed, A. Qayyum, M. Ghaly, A. Al-Fuqaha, A. Razi, and J. Qadir, “Explainable, trustworthy, and ethical machine learning for healthcare: A survey,” Comput Biol Med, vol. 149, p. 106043, Oct. 2022, doi: 10.1016/J.COMPBIOMED.2022.106043.
A. A. Ahmed, W. Ali, T. A. A. Abdullah, and S. J. Malebary, “Classifying Cardiac Arrhythmia from ECG Signal Using 1D CNN Deep Learning Model,” Mathematics, vol. 11, no. 3, pp. 1–16, 2023, doi: 10.3390/math11030562.
Á. T. Escottá, W. Beccaro, and M. A. Ramírez, “Evaluation of 1D and 2D Deep Convolutional Neural Networks for Driving Event Recognition,” Sensors, vol. 22, no. 11, pp. 1–21, 2022, doi: 10.3390/s22114226.
G. Yang, Q. Ye, and J. Xia, “Unbox the black box for the medical explainable AI via multi-modal and multi-centre data fusion: A mini-review, two showcases and beyond,” Information Fusion, vol. 77, pp. 29–52, Jan. 2022, doi: 10.1016/J.INFFUS.2021.07.016.
G. Stiglic, P. Kocbek, N. Fijacko, M. Zitnik, K. Verbert, and L. Cilar, “Interpretability of machine learning-based prediction models in healthcare,” Wiley Interdiscip Rev Data Min Knowl Discov, vol. 10, no. 5, p. e1379, Sep. 2020, doi: 10.1002/WIDM.1379.
A. Y. Hannun et al., “Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network,” Nat. Med., vol. 25, no. 1, pp. 65–69, 2019, doi: 10.1038/s41591-018-0268-3.
E. A. Ashley and J. Niebauer, “explained Euan A Ashley and Josef Niebauer explained”.
C. Antzelevitch and A. Burashnikov, “Overview of Basic Mechanisms of Cardiac Arrhythmia,” Card. Electrophysiol. Clin., vol. 3, no. 1, pp. 23–45, 2011, doi: 10.1016/j.ccep.2010.10.012.
H. Liu et al., “A large-scale multi-label 12-lead electrocardiogram database with standardized diagnostic statements,” Sci. Data, vol. 9, no. 1, pp. 1–10, 2022, doi: 10.1038/s41597-022-01403-5.
P. Wagner et al., “PTB-XL, a large publicly available electrocardiography dataset,” Sci. Data, vol. 7, no. 1, pp. 1–16, 2020, doi: 10.1038/s41597-020-0495-6.
D. Watson, “Conceptual Challenges for Interpretable Machine Learning,” SSRN Electron. J., no. June, 2020, doi: 10.2139/ssrn.3668444.
G. Hinton, “Deep belief networks,” Scholarpedia, vol. 4, no. 5, p. 5947, 2009, doi: 10.4249/scholarpedia.5947.
P. Sharma, M. Kumar, H. K. Sharma, and S. M. Biju, Generative adversarial networks (GANs): Introduction, Taxonomy, Variants, Limitations, and Applications, no. 0123456789. Springer US, 2024. doi: 10.1007/s11042-024-18767-y.
C. Antzelevitch and A. Burashnikov, “Overview of Basic Mechanisms of Cardiac Arrhythmia,” Card Electrophysiol Clin, vol. 3, no. 1, p. 23, Mar. 2011, doi: 10.1016/J.CCEP.2010.10.012.
B. B. Sahoo, R. Jha, A. Singh, and D. Kumar, “Long short-term memory (LSTM) recurrent neural network for low-flow hydrological time series forecasting,” Acta Geophysica, vol. 67, no. 5, pp. 1471–1481, Oct. 2019, doi: 10.1007/S11600-019-00330-1/METRICS.
P. Wagner et al., “PTB-XL, a large publicly available electrocardiography dataset,” Scientific Data 2020 7:1, vol. 7, no. 1, pp. 1–15, May 2020, doi: 10.1038/s41597-020-0495-6.
S. Mukhopadhyay, S. Biswas, A. B. Roy, and N. Dey, “Wavelet-Based QRS Complex Detection of ECG Signal,” vol. 2, no. 3, pp. 2361–2365, 2012, [Online]. Available: http://arxiv.org/abs/1209.1563
H. A. Marzog and H. J. Abd, “Machine Learning ECG Classification Using Wavelet Scattering of Feature Extraction,” Appl. Comput. Intell. Soft Comput., vol. 2022, 2022, doi: 10.1155/2022/9884076.
H. M and S. M.N, “A Review on Evaluation Metrics for Data Classification Evaluations,” Int. J. Data Min. Knowl. Manag. Process, vol. 5, no. 2, pp. 01–11, 2015, doi: 10.5121/ijdkp.2015.5201.
R. Mathur, C. P. Gupta, V. Katewa, D. S. Jat, and N. Yadav, Eds., “Emerging Trends in Data-Driven Computing and Communications,” 2021, doi: 10.1007/978-981-16-3915-9.
