FOREX Press I. J. of Electrical & Electronics Research
Support Open Access
  • Home/
  • IJEER-140123

Research Article |

New Cardiovascular Signal Processing and Feature Engineering Methods for Disease Detection Based on Machine Learning

Author(s): Haider Abdulkarim1, Hussein Khaleel2, Shaimaa Hameed Abd3, and Qussay S. Tawfeeq4*

Published In : International Journal of Electrical and Electronics Research (IJEER)        Volume 14, Issue 1

Publisher : FOREX Publication

Published : 30 March 2026

e-ISSN : 2347-470X

Page(s) : 216-224

DOI: https://doi.org/10.37391/IJEER.140123

Abstract

Identifying and diagnosing cardiac problems is heavily based on the data analyzed from an ECG. The utilization of artificial intelligence for automated analysis of ECG’s is becoming more common. The way in which the data is processed and which model is selected significantly influences how accurately the signal is classified. This paper presents a methodology for ECG signal processing for creating feature sets in the time domain, in the frequency domain, and of statistical metrics that are used to develop machine learning classification models. All experiments with the proposed methods were conducted using the PTB-XL data set. The results indicate that by designing appropriate feature sets, a wide variety of machine-learning models can be created, which can categorize complex types of cardiac disease more accurately than using random feature sets. Binary and multi-class classification accuracies were achieved at 86.52% and 73.78%, respectively, using the feature sets developed from the proposed methods. Analysis of the features set shows that the feature set adequately represents all identified dynamic characteristics present in the signals collected. As a result, this feature set can also be utilized with any form of method that utilizes an approach other than deep learning. Therefore, there is enough evidence from this research study to conclude that utilizing features-based methods will yield satisfactory results.

Keywords: ECG Classification, Deep Learning, LSTM, CNN, Arrhythmia Detection, Data Augmentation.




Haider Abdulkarim, College of Communications Engineering, University of Technology, Baghdad, Iraq; Email: haider.a.abdulkarim@uotechnology.edu.iq

Hussein Khaleel, College of Communications Engineering, University of Technology, Baghdad, Iraq; Email: hussein.j.khaleel@uotechnology.edu.iq

Shaimaa Hameed Abd, College of Communications Engineering, University of Technology, Baghdad, Iraq; Email: shaymaa.h.abed@uotechnology.edu.iq

Qussay S. Tawfeeq, College of Communications Engineering, University of Technology, Baghdad, Iraq; Email: qussay.s.tawfeeq@uotechnology.edu.iq

    [1] J. Rabcan, V. Levashenko, E. Zaitseva, and M. Kvassay, “Advancing ECG Signal Classification with a Fuzzy Classifier Approach,” IEEE Access, 2025
    [2] S. Palermi, et al., “Artificial intelligence and the electrocardiogram: A modern renaissance”, European Journal of Internal Medicine, Volume 140, 2025, 106329
    [3] B. T. Pham, et al., “Electrocardiogram Heartbeat Classification for Arrhythmias and Myocardial Infarction,” Sensors, vol. 23, no. 6, Mar. 2023
    [4] H. N. Monday et al., "Enhancing ECG Classification in Cardiac Diagnostics: A Novel Approach Using Adaptive Focal Cross-Entropy Loss Function," in IEEE Journal of Biomedical and Health Informatics, vol. 29, no. 10, pp. 7161-7174, Oct. 2025
    [5] Saini, Indu & Kumar, V. & Khosla, Arun. (2013). Feature extraction of ECG signal using a support vector machine. Journal of Electrocardiology. Vol. 46, issue 4, 2013
    [6] Gupta, V., Saxena, N.K., Kanungo, A. et al. “A review of different ECG classification/detection techniques for improved medical applications”. Int J Syst Assur Eng Manag 13, 1037–1051 (2022)
    [7] C. Zhang, G. Wang, J. Zhao, P. Gao, J. Lin and H. Yang, "Patient-specific ECG classification based on recurrent neural networks and clustering technique", 2017 13th IASTED International Conference on Biomedical Engineering (BioMed), Innsbruck, Austria, 2017, pp. 63-67
    [8] Kahlessenane, Y., Bouaziz, F., & Siarry, P. (2025). “A new particle swarm optimization-enhanced deep neural network for automatic ECG arrhythmias classification”. Computer Methods in Biomechanics and Biomedical Engineering, 1–15
    [9] Immaculate Joy Selvam, Moorthi Madhavan, Senthil Kumar Kumarasamy, “Detection and classification of electrocardiography using hybrid deep learning models”, Hellenic Journal of Cardiology, Volume 81, 2025, Pages 75-84
    [10] Oke, O.A., Cavus, N., “Electrocardiogram image classification for six classes of heart diseases”. Iran J Comput Sci 8, 419–439 (2025)
    [11] Patra, N., Banerjee, S. & Bhadra, S. “On-device compression of multilead electrocardiogram using tunable-Q wavelet transform and MLPNN trained using multi-optima optimization based PSO”. SIViP 19, 628 (2025)
    [12] Teng Chen, Yumei Ma, Zhenkuan Pan, Weining Wang, Jinpeng Yu, “Fusion of multi-scale feature extraction and adaptive multi-channel graph neural network for 12-lead ECG classification”, Computer Methods and Programs in Biomedicine, Volume 265, 2025
    [13] Wagner, P., Strodthoff, N., Bousseljot, RD. et al. PTB-XL, a large publicly available electrocardiography dataset. Sci Data 7, 154 (2020)
    [14] Wagner, Patrick, et al. "PTB-XL, a large publicly available electrocardiography dataset" (version 1.0.3). PhysioNet (2022)
    [15] International Organization for Standardization. ISO 41064:2023: Health Informatics — Standard Communication Protocol — Computer-Assisted Electrocardiography. ISO, 2023
    [16] Makowski, D., Pham, T., Lau, Z. J., Brammer, J. C., Lespinasse, F., Pham, H., Schölzel, C., & Chen, S. A. (2021). NeuroKit2: A Python toolbox for neurophysiological signal processing. Behavior Research Methods, 53(4), 1689-1696
    [17] Jolliffe, I. T. (2002). Principal Component Analysis (2nd ed.). New York: Springer-Verlag
    [18] FISHER, R.A. (1936), THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS. Annals of Eugenics, 7: 179-188
    [19] Daubechies, I. (1992) Ten Lectures on Wavelets. SIAM, Philadelphia
    [20] Cortes, C., Vapnik, V. Support-vector networks. Mach Learn 20, 273–297 (1995)
    [21] Scikit-learn: Machine Learning in Python, Pedregosa et al., JMLR 12, pp. 2825-2830, 2011
    [22] Breiman, L. Random Forests. Machine Learning 45, 5–32 (2001)
    [23] Cover, T. and Hart, P. (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 13 (1967), pp.21-27
    [24] LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278–2324
    [25] Fawcett, T. An introduction to roc analysis. Pattern Recogn. Lett. 27(8), 861–874 (2006)
    [26] Ting, K.M. (2011). Confusion Matrix. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning. Springer, Boston, MA
    [27] Safdar, M.F., Nowak, R.M., Pałka, P. et al. An integrated algorithm for single lead electrocardiogram signal analysis using deep learning with 12-lead data. Sci Rep 15, 34955 (2025)
    [28] K. Lee, et al. Mobile single-lead ecg atrial fibrillation prediction enhancement integrated by standard ecg algorithm with deep learning model. Eur. Heart J. 45, 3431 (2024)
    [29] G. Luongo et al. Machine learning using a single-lead ECG to identify patients with atrial fibrillation-induced heart failure. Front. Cardiovasc. Med. 9, 812719 (2022)
    [30] Kim, J. et al. Identification of atrial fibrillation with single-lead mobile ECG during normal sinus rhythm using deep learning. J. Kor. Med. Sci. 39(5), e56 (2024)

Haider Abdulkarim, Hussein Khaleel, Shaimaa Hameed Abd, Qussay S. Tawfeeq (2026), New Cardiovascular Signal Processing and Feature Engineering Methods for Disease Detection Based on Machine Learning. IJEER 14(1), 216-224. DOI: 10.37391/IJEER.140123.