Classification of Tuberculosis in Rumah Sakit Paru Sumatera Barat Using the C5.0 Algorithm

Abstrak

Tuberculosis (TB) continues to be a significant public health concern, including in West Sumatra Province, where the number of reported cases has shown an upward trend in recent years. Therefore, effective approaches are needed to facilitate early detection and classification of TB patients. This study aims to classify the TB status of patients at the West Sumatra Pulmonary Hospital using the C5.0 algorithm. The data utilized in this research were secondary data obtained from patients’ medical records from October to December 2024, comprising a total of 150 patient records. The dataset consisted of eight predictor variables related to clinical symptoms and one target variable, namely sputum smear (BTA) examination results. The analytical process involved data preprocessing, dividing the dataset into training and testing sets with a ratio of 70:30, constructing a classification model using the C5.0 algorithm, and assessing model performance through a confusion matrix. The findings revealed that the C5.0 algorithm achieved an accuracy of 91.11%, precision of 95.83%, sensitivity of 88.46%, and specificity of 94.74%. Night sweats were identified as the most influential variable in the decision tree construction. These results suggest that the C5.0 algorithm exhibits excellent performance and can be applied as a decision support method for classifying tuberculosis based on patients’ clinical symptoms.