Evaluation of Stacked Generalization: Integration of CatBoost with SVM and Random Forest for Arrhythmia Classification in Adolescents

##plugins.themes.academic_pro.article.sidebar##

Published Oct 30, 2026
https://doi.org/10.34012/jutikomp.v9i2.8135
Download
PDF
Statistic
Vol. 9 No. 2 (2026): Jurnal Teknologi dan Ilmu Komputer Prima (JUTIKOMP)

##plugins.themes.academic_pro.article.main##

Mei Ditta Kristie Br Bangun
Universitas Prima Indonesia
Swando Sagala
Universitas Prima Indonesia
Eddrick Wilbert Solo
Universitas Prima Indonesia
Delima Sitanggang
Universitas Prima Indonesia

Abstract

Arrhythmia is a disorder of heart rhythm that can occur in anyone, including adolescents, and may pose serious risks if not detected early. This study aims to evaluate the effectiveness of the CatBoost algorithm, both as a standalone model and in combination with Support Vector Machine (SVM) and Random Forest (RF) using ensemble approaches, namely voting and stacked generalization, for arrhythmia classification based on electrocardiogram (ECG) signals. Data were obtained from 72 students aged 15–19 years using a Smart Holter ECG 5-lead device based on Raspberry Pi 4. The models were developed and tested using the Python programming language. The results show that the standalone CatBoost model achieved strong performance, with an accuracy of 95.45% and a ROC AUC of 99.81%. The CatBoost–RF voting method yielded a higher accuracy (96.97%), while the CatBoost–RF stacking approach demonstrated the best overall performance, achieving an accuracy of 98.48% and a ROC AUC of 99.85%. In contrast, the CatBoost–SVM stacking approach produced the lowest performance, with an accuracy of 89.39%. Based on evaluation using accuracy, F1-score, and ROC AUC metrics, it can be concluded that the ensemble stacking method with Random Forest as the base learner and CatBoost as the meta-learner is the most effective approach for arrhythmia classification in adolescent ECG data. This study is expected to contribute to the development of more accurate machine learning-based automatic arrhythmia detection systems tailored for younger populations.

##plugins.themes.academic_pro.article.details##

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

How to Cite
Br Bangun, M. D. K., Sagala, S., Solo, E. W., & Sitanggang, D. (2026). Evaluation of Stacked Generalization: Integration of CatBoost with SVM and Random Forest for Arrhythmia Classification in Adolescents. JURNAL TEKNOLOGI DAN ILMU KOMPUTER PRIMA (JUTIKOMP), 9(2), 133–150. https://doi.org/10.34012/jutikomp.v9i2.8135

References

  1. Nagpal, A. K., Pundkar, A., Singh, A., & Gadkari, C. (2024). Cardiac arrhythmias and their management: An in-depth review of current practices and emerging therapies. Cureus, 16(8), e66549. https://doi.org/10.7759/cureus.66549
  2. Gajowniczek, K., Grzegorczyk, I., Ząbkowski, T., & Bajaj, C. (2020). Weighted random forests to improve arrhythmia classification. Electronics, 9(1). https://doi.org/10.3390/electronics9010099
  3. Kumari, C. U., Murthy, A. S. D., Prasanna, B. L., Reddy, M. P., & Panigrahy, A. K. (2021). An automated detection of heart arrhythmias using machine learning technique: SVM. Materials Today: Proceedings, 45(Part 2), 1393–1398. https://doi.org/10.1016/j.matpr.2020.07.088
  4. Behera, S. K., et al. (2025). Non-linear dynamics in ECG: a novel approach for robust classification of cardiovascular disorders. npj Cardiovascular Health. https://doi.org/10.1038/s44325-024-00038-2
  5. Ma, S., Cui, J., Chen, C.-L., Chen, X., & Ma, Y. (2022). An effective data enhancement method for classification of ECG arrhythmia. Measurement, 203, 111978. https://doi.org/10.1016/j.measurement.2022.111978
  6. Jahangir, R., Islam, M. N., Islam, M. S., et al. (2025). ECG-based heart arrhythmia classification using feature engineering and a hybrid stacked machine learning. BMC Cardiovascular Disorders, 25, 260. https://doi.org/10.1186/s12872-025-04678-9
  7. Anshor, A. H., & Wiyatno, T. N. (2024). Comparative analysis of random forest and support vector machine for Sundanese dialect classification using speech recognition features. Sisfokom (Jurnal Sistem Informasi dan Komputer), 14(2). https://doi.org/10.32736/sisfokom.v14i2.2347
  8. Boldini, D., Grisoni, F., Kuhn, D., et al. (2023). Practical guidelines for the use of gradient boosting for molecular property prediction. Journal of Cheminformatics, 15, 73. https://doi.org/10.1186/s13321-023-00743-7
  9. Dorogush, A. V., Ershov, V., & Gulin, A. (2018). CatBoost: Gradient boosting with categorical features support (Version 1). arXiv. https://doi.org/10.48550/arXiv.1810.11363
  10. Prasanna Venkatesh, P. V. N., Pradeep Kumar, R., Neelapu, B. C., Pal, K., & Sivaraman, J. (2023). CatBoost-based improved detection of P-wave changes in sinus rhythm and tachycardia conditions: A lead selection study. Physical and Engineering Sciences in Medicine, 46(2), 925–944. https://doi.org/10.1007/s13246-023-01274-z
  11. Wu, J., Tao, G., Xie, S., Yang, H., Qi, F., Bao, N., Li, Z., Chang, G., & Xiao, H. (2025). Prediction of three-year all-cause mortality in patients with heart failure and atrial fibrillation using the CatBoost model. BMC Cardiovascular Disorders, 25(1), 466. https://doi.org/10.1186/s12872-025-04928-w
  12. Schnermann, M. E., Schulz, C. A., Herder, C., Alexy, U., & Nöthlings, U. (2021). A lifestyle pattern during adolescence is associated with cardiovascular risk markers in young adults: Results from the DONALD cohort study. Journal of Nutritional Science, 10, e92. https://doi.org/10.1017/jns.2021.84
  13. Presta, V., Guarnieri, A., Laurenti, F., Mazzei, S., Arcari, M. L., Mirandola, P., Vitale, M., Chia, M. Y. H., Condello, G., & Gobbi, G. (2024). The impact of digital devices on children's health: A systematic literature review. Journal of Functional Morphology and Kinesiology, 9(4), 236. https://doi.org/10.3390/jfmk9040236
  14. Santini, M., Di Fusco, S. A., Colivicchi, F., & Gargaro, A. (2018). Electrocardiographic characteristics, anthropometric features, and cardiovascular risk factors in a large cohort of adolescents. Europace, 20(11), 1833–1840. https://doi.org/10.1093/europace/euy073
  15. Luong, T. T., et al. (2021). Analysis of noisy and complex student ECG signals using ML methods. Biomedical Signal Processing and Control, 70. https://doi.org/10.1016/j.bspc.2021.103061
  16. Kaushik, C., McRae, A. D., Davenport, M. A., & Muthukumar, V. (2023). New equivalences between interpolation and SVMs: Kernels and structured features. arXiv. https://doi.org/10.48550/arXiv.2305.02304
  17. Kull, M., Silva Filho, T. M., & Flach, P. (2017). Beyond sigmoids: How to obtain well-calibrated probabilities from binary classifiers with beta calibration. Electronic Journal of Statistics, 11(2), 5052–5080. https://doi.org/10.1214/17-EJS1338SI
  18. Salman, H. A., Kalakech, A., & Steiti, A. (2024). Random Forest algorithm overview. Babylonian Journal of Machine Learning, 2024, 69–79. https://doi.org/10.58496/BJML/2024/007
  19. Zhu, J., Zhang, A., & Zheng, H. (2023). Research on predictive model based on ensemble learning. Highlights in Science, Engineering and Technology, 57, 311–319. https://doi.org/10.54097/hset.v57i.10023
  20. Airlangga, G. (2025). Comparative analysis of voting and stacking ensemble learning for heart disease prediction: A machine learning approach. Jurnal Teknologi Informatika dan Komputer, 11(1), 1–10. https://doi.org/10.37012/jtik.v11i1.2584

Similar Articles

1 2 > >> 

You may also start an advanced similarity search for this article.