Comparative Analysis of Random Forest, Explainable Boosting Machine and Ensemble Stacking Performance for Hepatitis C Disease Classification

Anastasia Ngeni Bagur; Irfan Pratama

doi:10.57152/malcom.v6i2.2561

Authors

Anastasia Ngeni Bagur Mercu Buana University of Yogyakarta
Irfan Pratama Mercu Buana University of Yogyakarta

DOI:

https://doi.org/10.57152/malcom.v6i2.2561

Keywords:

Explainable Boosting Machine, Hepatitis C, Random Forest, SMOTE, Stacking Ensemble

Abstract

This study analyzed and compared the performance of three machine learning methods: Random Forest, Explainable Boosting Machine, and a Stacking Ensemble method for Hepatitis C disease classification. The study evaluated the effects of handling extreme values using the interquartile range method and applying class-balancing oversampling to the training data. A dataset of 615 patient samples, categorized into five severity classes, was used. Experiments were conducted across four scenarios: with and without outlier correction, and with and without class balancing. Model performance was assessed using accuracy, precision, recall, F1-score, and the area under the receiver operating characteristic curve. Results showed that class balancing consistently improved all macro-averaged performance metrics. The combination of Random Forest with oversampling prior to outlier correction achieved the highest F1-score of 0.8086 and an area under the curve of 0.9710. These findings highlighted the importance of addressing class imbalance to improve the recognition of minority classes in clinical datasets and demonstrated the potential of ensemble methods for reliable severity classification in Hepatitis C.

Downloads

Download data is not yet available.

References

H. M. Farghaly, M. Y. Shams, and T. A. Abd El Hafeez, “Hepatitis C virus prediction based on a machine learning framework: a real-world case study,” Knowl. Inf. Syst., vol. 65, no. 6, pp. 2595–2617, 2023.

S. K. J. Jang and M. P. Lee, “Development and validation of a machine-learning screening algorithm to improve hepatitis C detection and resource allocation,” Open Forum Infect. Dis., vol. 12, no. 8, p. ofaf496, 2025, doi: DOI?: 10.1093/ofid/ofaf496.

Abdul-Mohsen G. and Alhejaily, “Artificial intelligence in healthcare,” Biomed. Rep., vol. 22, no. 1, p. 11, 2024, doi: DOI?: 10.3892/br.2024.1889.

E. C. O. P. Rajpurkar, O. Chen, and E. T. Banerjee, “AI in health and medicine,” Nat. Med., vol. 28, pp. 31–38, 2021, doi: DOI?: 10.1038/s41591-021-01614-0.

A. M. Edeh, “Artificial intelligence-based ensemble learning model for prediction of hepatitis C disease and fibrosis stage,” J. Med. Syst., vol. 46, pp. 1–12, 2022, doi: DOI?: 10.1007/s10916-022-01800-x.

A. M. Alam and et al., “Handling imbalanced medical datasets: review of a decade of progress,” Artif. Intell. Rev., vol. 54, no. 3, pp. 2101–2140, 2024, doi: DOI?: 10.1007/s10462-024-10884-2.

Y. X. Li, S. Zhang, and Liu, “Recent advances in SMOTE-based oversampling for imbalanced classification: a survey,” Inf. Process. Manag., vol. 60, p. 102789, 2023, doi: DOI?: 10.1016/j.ipm.2023.102789.

X. Wang and Y. Zhao, “Evaluation metrics for imbalanced classification in medical applications: a practical guideline,” J. Biomed. Inform., vol. 128, p. 104000, 2022, doi: DOI?: 10.1016/j.jbi.2022.104000.

J. Zhang, “Advancements of outlier detection: A survey and medical applications,” Electronics / MDPI (survey 2023), vol. 13, no. 16, p. 3339, 2023, doi: DOI?: 10.3390/electronics13163339.

V. Hodge and J. Austin, “A survey of outlier detection methodologies,” Artif. Intell. Rev., vol. 53, pp. 1275–1308, 2020.

J. Han, M. Kamber, and J. Pei, “Data mining concepts and techniques for medical data analysis,” IEEE Access, vol. 9, pp. 135889–135903, 2021.

M. L. Wallace, “Use and misuse of random forest variable importance metrics in medicine,” BMC Med. Res. Methodol., vol. 23, pp. 1–12, 2023, doi: DOI?: 10.1186/s12874-023-01965-x.

A. Cutler, D. R. Cutler, and J. R. Stevens, “Random forests in healthcare data classification,” WIREs Data Mining and Knowledge Discovery, vol. 11, no. 4, p. e1407, 2021.

Harsha Nori, Rich Caruana, J. Zhiqi Bu, udy H. Shen, and Janardhan Kulkarni, “Accuracy, interpretability, and differential privacy via Explainable Boosting (DP-EBM),” PMLR (ICML proceedings), Proceedings of ICML 2021 (PMLR 139), 2021.

H. Nori, S. Jenkins, P. Koch, and R. Caruana, “Interpretable machine learning for healthcare,” Commun. ACM, vol. 64, no. 10, pp. 46–55, 2021.

R. Kablan, “Evaluation of stacked ensemble model performance to analyze clinical data,” Information Fusion, 2023, doi: DOI?: PubMed ID 37172507 (2023).

N. Das, “Hepatitis prediction with an explainable machine learning pipeline (includes stacking and SMOTE),” PLoS One, 2025, doi: DOI?: 10.1371/journal.pone.0319078.

S. Zhou and Y. Zhang, “Enhancing SMOTE for imbalanced data with abnormal minority instances,” Pattern Recognit. Lett., vol. 182, pp. 12–24, 2023, doi: DOI?: 10.1016/j.patrec.2023.10.012.

R. Ningsih, A. U. Dullah, and M. A. Muslim, “Hepatitis C classification using neural networks and SMOTE oversampling,” Jurnal Nasional Riset Aplikasi dan Teknik Informatika, vol. 6, no. 2, pp. 45–54, 2024.

M. S. Alam, M. M. Rahman, and M. A. Hossain, “A review of machine learning algorithms for hepatitis diagnosis,” Indonesian Journal of Computer Science, vol. 13, no. 3, pp. 721–735, 2024.

Jianchang Hu and Silke Szymczak, “A review on longitudinal data analysis with random forest,” Brief. Bioinform., vol. 24, no. 2, p. bbad002, 2023, doi: DOI?: 10.1093/bib/bbad002.

Ricardo Gonzalez and et al. Ashirbani Saha, “Seeing the random forest through the decision trees — Supporting learning health systems from histopathology with machine learning models: Challenges and opportunities,” J. Pathol. Inform., vol. 15, p. 100347, 2024, doi: DOI?: 10.1016/j.jpi.2023.100347.

Simon P. Couch and Max Kuhn, “Stacks: Stacked ensemble modeling with tidy data principles,” Journal of Open Source Software (JOSS), vol. 7, p. 4471, 2022, doi: DOI?: 10.21105/joss.04471.

I. H. Sarker, “Machine learning: Algorithms, real-world applications and research directions,” SN Comput. Sci., vol. 2, p. 160, 2021.

H. Khan, M. T. Rasheed, S. Zhang, X. Wang, and H. Liu, “Empirical study of outlier impact in classification context,” Expert Syst. Appl., vol. 256, p. 124953, Dec. 2024, doi: 10.1016/j.eswa.2024.124953.

M. Salmi, D. Atif, D. Oliva, A. Abraham, and S. Ventura, “Handling imbalanced medical datasets: review of a decade of research,” Artif. Intell. Rev., vol. 57, no. 10, p. 273, Sep. 2024, doi: 10.1007/s10462-024-10884-2.

Y. Yang, H. A. Khorshidi, and U. Aickelin, “A review on over-sampling techniques in classification of multi-class imbalanced datasets: insights for medical problems,” Front. Digit. Health, vol. 6, Jul. 2024, doi: 10.3389/fdgth.2024.1430245.