Performance Evaluation of Bagging Meta-Estimator in Lung Disease Detection: A Case Study on Imbalanced Dataset

Abstract

In this study, titled "Performance Evaluation of Bagging Meta-Estimator in Lung Disease Detection: A Case Study on Imbalanced Dataset," we explore the effectiveness of the Bagging Meta-Estimator in diagnosing lung diseases, focusing on the challenges of imbalanced datasets. Utilizing a dataset segmented and characterized by Hu moments and encompassing categories of Normal, Bacterial Pneumonia, and Tuberculosis, the algorithm's performance was assessed through a 5-fold cross-validation. Results indicated moderate effectiveness with an average accuracy of 60.574%, precision of 60.749%, recall of 59.753%, and F1-Score of 59.416%, highlighting variable performance across folds. These findings suggest that while the Bagging Meta-Estimator has potential in medical imaging, further refinement is needed for consistent and reliable lung disease detection, especially in imbalanced datasets.