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

Abstrak

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.