FOREX Press I. J. of Electrical & Electronics Research
Support Open Access
  • Home/
  • IJEER-140313

Research Article |

Morphological and RR-Interval Features for ECG Arrhythmia Classification: A Comparative Study of Intra-Patient and Inter-Patient Evaluation

Author(s): Shams M. Qahtan 1, Hadeel N. Abdullah2*

Published In : International Journal of Electrical and Electronics Research (IJEER)        Volume 14, Issue 3

Publisher : FOREX Publication

Published : 30 September 2026

e-ISSN : 2347-470X

Page(s) :796-806

DOI: https://doi.org/10.37391/IJEER.140313

Abstract

Heartbeat classification on the MIT-BIH Arrhythmia Database is commonly evaluated with beat-level cross-validation, which places beats from the same subject in both training and test sets. In this work, we evaluate a 61-dimensional heartbeat representation under both that protocol and record-level separation, and compare the two. Each beat is described by 60 signal samples spanning 166.7 ms around the R-peak and one RR interval. Under beat-level five-fold cross-validation, a Random Forest reaches 98.42% accuracy and 95.44% macro-F1 across five classes. Under record-level separation, with the configuration selected entirely within DS1 and DS2 withheld from model selection, the same representation reaches 80.80% accuracy and 42.00% macro-F1, with sensitivity of 0.9864 for Normal, 0.9139 for PVC, 0.2004 for RBBB, 0.0002 for LBBB and 0.0023 for APC. We then separate the causes of these failures experimentally. RBBB sensitivity rises to 0.9178 on one held-out subject when the number of training subjects carrying the class is increased, whereas LBBB sensitivity remains below 0.001 under every configuration and feature subset tested. Across the five classifiers evaluated under DS1/DS2, LBBB remains poorly recognized and RBBB sensitivity remains below 0.40, whereas APC performance varies substantially, showing that the poor transfer is not specific to the Random Forest and that the weak classes are affected by different factors. The comparison illustrates the substantial difference between beat-level and record-level evaluation under the standard DS1/DS2 setting, and shows that per-class failures under record-level separation arise from different causes and require different remedies.

Keywords: ECG, Inter-Patient Evaluation , Arrhythmia Classification, Random Forest, RR Interval.




Shams M. Qahtan , Department of Electrical Engineering, University of Technology, Iraq; Email: eng7shams@gmail.com

Hadeel N. Abdullah , Department of Electrical Engineering, University of Technology, Iraq; Email: hadeel.n.abdullah@uotechnology.edu.iq

    [1] M. Costa, G.B. Moody, I. Henry, and A.L. Goldberger, “PhysioNet: an NIH research resource for complex signals,” Journal of electrocardiology, Vol. 36, pp.139-144, 2003. DOI: https://doi.org/10.1016/j.jelectrocard.2003.09.038
    [2] G. B. Moody and R. G. Mark, "The impact of the MIT-BIH arrhythmia database," IEEE engineering in medicine and biology magazine, Vol. 20, Issue. 3, pp. 45–50, 2001. DOI: https://doi.org/10.1109/51.932724
    [3] S. K. Pandey, R. R. Janghel, and V. Vani, "Patient specific machine learning models for ECG signal classification," Procedia Computer Science, Vol. 167, pp. 2181–2190, 2020. DOI: https://doi.org/10.1016/j.procs.2020.03.269
    [4] H. Yang and Z. Wei, "Arrhythmia recognition and classification using combined parametric and visual pattern features," IEEE Access, Vol. 8, pp. 47103–47117, 2020. DOI: 10.1109/ACCESS.2020.2979256
    [5] F. W. Abdullah and H. N. Abdullah, “ECG signal denoising: an integrated filtering approach for improved signal quality”, Kufa Journal of Engineering, Vol. 17, No. 1, pp. 291–307, 2026. DOI: http://doi.org/10.30572/2018/KJE/170116
    [6] Dias, F.M., H.L. Monteiro, T.W. Cabral, R. Naji, M. Kuehni, and E.J.D.S Luz, "Arrhythmia classification from single-lead ECG using the inter-patient paradigm," Computer Methods and Programs in Biomedicine, Vol. 202, p. 105948, 2021. DOI: 10.1016/j.cmpb.2021.105948
    [7] S. Aziz, S. Ahmed, and M.-S. Alouini, "ECG-based machine-learning algorithms for heartbeat classification," Scientific reports, Vol. 11, No. 1, p. 18738, 2021. DOI: 10.1038/s41598-021-97118-5
    [8] Hassaballah, M., Y.M. Wazery, I.E. Ibrahim, and A. Farag, "ECG heartbeat classification using machine learning and metaheuristic optimization," Bioengineering, Vol. 10, No. 4, p. 429, 2023. DOI: 10.3390/bioengineering10040429
    [9] T. Subba and T. Chingtham, "Comparative analysis of ML algorithms with advanced feature extraction for ECG classification," IEEE Access, Vol. 12, pp. 57727–57740, 2024. DOI: 10.1109/ACCESS.2024.3387041
    [10] Darmawahyuni, A., S. Nurmaini, B. Tutuko, M.N. Rachmatullah, F. Firdaus, A.I. Sapitri, A. Islami, J. Marcelino, R. Isdwanta, and M.I. Perwira, "An Improved electrocardiogram arrhythmia classification performance with feature optimization," BMC medical informatics and decision making, Vol. 24, No. 1, p. 412, 2024. DOI: 10.1186/s12911-024-02822-7
    [11] Kung, B.H., P.Y. Hu, C.C. Huang, C.C. Lee, C.Y. Yao, and C.H. Kuan, "An efficient ECG classification system using resource-saving architecture and random forest," IEEE Journal of Biomedical and Health Informatics, Vol. 25, No. 6, pp. 1904–1914, 2021. DOI: https://doi.org/10.1109/JBHI.2020.3035191
    [12] A.F. Ahmed, H.N. Abdullah, B.M. Albaker, “A Robust and Efficient Scheme for ECG Signal Classification Based on Digital Signal Processing, Feature Engineering Selection, and Random Forest Classifier”, Radioelectronics, Nanosystems. Information Technologies, Vol. 16, No. 1, pp. 53-66, 2024. DOI: 10.17725/j.rensit.2024.16.053
    [13] M. Sraitih, Y. Jabrane, and A. H. El Hassani, "An Automated system for ECG arrhythmia detection using machine learning techniques," Journal of Clinical Medicine, Vol. 10, No. 22, p. 5450, 2021. DOI: https://doi.org/10.3390/jcm10225450
    [14] Ullah, A., S.M. Anwar, M. Bilal, and R.M. Mehmood, "Classification of arrhythmia by using deep learning with 2-D ECG spectral image representation," Remote sensing, Vol. 12, No. 10, p. 1685, 2020. DOI: https://doi.org/10.3390/rs12101685
    [15] M. F. Safdar, P. Pałka, R.M. Nowak, and A. Al Faresi, "A novel data augmentation approach for enhancement of ECG signal classification," Biomedical Signal Processing and Control, Vol. 86, p. 105114, 2023. DOI: 10.1016/j.bspc.2023.105114
    [16] Zabihi, F., F. Safara, and B. Ahadzadeh, “An electrocardiogram signal classification using a hybrid machine learning and deep learning approach”. Healthcare Analytics, Vol. 6, p.100366, 2024. DOI: 10.1016/j.health.2024.100366
    [17] U. Gupta N. Paluru, D. Nankani, K. Kulkarni, and N. Awasthi, “A comprehensive review on efficient artificial intelligence models for classification of abnormal cardiac rhythms using electrocardiograms,” Heliyon, Vol. 10, No. 5, e26787, 2024. 10.1016/j.heliyon.2024.e26787
    [18] S. Reznichenko, J. Whitaker, Z. Ni, and S. Zhou, “Comparing ECG lead subsets for heart arrhythmia/ECG pattern classification: Convolutional neural networks and random forest.” CJC open, Vol. 7, No. 2, pp. 176–186, 2025. DOI: https://doi.org/10.1016/j.cjco.2024.10.012
    [19] A. Kirkbas and A. Kizilkaya, "Automated ECG arrhythmia classification using feature images with Common Matrix approach-based classifier," Sensors, Vol. 25, No. 4, p. 1220, 2025. DOI: https://doi.org/10.3390/s25041220
    [20] N. S. Kathayat and A. P. Renold, "Hybrid deep learning for scalogram-based ECG classification of cardiovascular diseases," IEEE Access, Vol. 13, pp. 159628–159638, 2025. DOI: https://doi.org/10.1109/ACCESS.2025.3605279
    [21] P. De Chazal, M. O'Dwyer, and R. B. Reilly, "Automatic classification of heartbeats using ECG morphology and heartbeat interval features," IEEE Transactions on Biomedical Engineering, Vol. 51, No. 7, pp. 1196–1206, 2004. DOI: https://doi.org/10.1109/TBME.2004.827359
    [22] G. A. L. Silva, P. H. L. Silva, G. J. P. Moreira, V. L. de S. Freitas, J. C. Gertrudes, and E. J. da S. Luz, "A systematic review of ECG arrhythmia classification: embedded feasibility, adherence to standards, and fair evaluation," Research on Biomedical Engineering, vol. 42, No. 42, 2026. doi: http://doi.org/10.1007/s42600-026-00485-z
    [23] C. M. Bishop and N. M. Nasrabadi, Pattern Recognition and Machine Learning. Springer, 2006.
    [24] L. Breiman, "Random forests," Machine Learning, Vol. 45, No. 1, pp. 5–32, 2001. doi: https://doi.org/10.1023/A:1010933404324
    [25] H. Shi, H. Wang, F. Zhang, Y. Huang, L. Zhao, and C. Liu, "Inter-patient heartbeat classification based on region feature extraction and ensemble classifier," Biomedical Signal Processing and Control, Vol. 51, pp. 97–105, 2019. doi: https://doi.org/10.1016/j.bspc.2019.02.012
    [26] M. M. Farag, "A tiny matched filter-based CNN for inter-patient ECG classification and arrhythmia detection at the edge," Sensors, vol. 23, no. 3, Art. no. 1365, 2023. doi: https://doi.org/10.3390/s23031365

Shams M. Qahtan, and Hadeel N. Abdullah. (2026), Morphological and RR-Interval Features for ECG Arrhythmia Classification: A Comparative Study of Intra-Patient and Inter-Patient Evaluation. IJEER 14(3), 796-806. DOI: 10.37391/IJEER.140313.