Implementation of Ensemble Machine Learning with Voting Classifier for Reliable Tuberculosis Detection Using Chest X-ray Images with Imbalance Dataset

Jauhari, Muhammad I
Wirakusuma, Muhammad P.
Sidqi, Anka
Putra, I Gusti Ngurah R. A.
Wijayanto, Inung
Rizal, Achmad
Hadiyoso, Sugondo

Journal of Electronics, Electromedical Engineering, and Medical Informatics
Vol 6 No 4 (2024): October

Tuberculosis (TB) is an infectious disease caused by bacteria. Tuberculosis is spread through the air and saliva that contain mycobacterium tuberculosis. If not treated immediately, it can spread to other vital organs, such as the heart and liver, and can even lead to death. In this study, we developed a severe tuberculosis detection system using the Tuberculosis (TB) dataset with simple computation. We used 4200 data points (3500 Normal and 700 TB). In other words, this research aimed to create lightweight computation with Machine Learning (Voting Classifier in Ensemble Learning) as the classifier using Imbalance data. Initial experiments used single machine learning with the best-performing models, Support Vector Machine (SVM), and Random Forest as classifiers. With an accuracy of 98.6% and 98%, they were combined using Ensemble Learning without feature extraction; the accuracy, AUC, Recall, Precision, and F1-score using the voting classifier were 99.1%, 99.3%, 99%, 98%, and 98%, respectively.