To search, Click below search items.


All Published Papers Search Service


Predicting The Suspect of New Pulmonary Tuberculosis Case using SVM, C5.0 and Modified Moran’s I


Rusdah, Edi Winarko, Retantyo Wardoyo


Vol. 17  No. 12  pp. 164-171


Indonesia, one of the 22 high-burden countries, has the second largest numbers of tuberculosis (TB) cases in the world. According to WHO’s 2015 report, Indonesia was estimated to have one million new TB cases per year. Unfortunately, only one-third of new TB cases are detected. The number shows a serious delay in TB diagnosis and treatment. Delayed treatment of TB is associated with long-term lung damage, which can multiply and spread the bacilli as well. Diagnosis of TB is difficult, especially in the case of pediatric patients, extrapulmonary TB, and smear-negative pulmonary TB, due to various reasons. In addition, some of the tuberculosis symptoms have in common not only with lung cancer but also with other diseases. This study aims to build classification model to predict the suspect of new pulmonary tuberculosis case. The data were taken from the medical record of tuberculosis patients in Jakarta Respiratory Center. A modified Moran’s I was proposed in data transformation proses. The training data were classified using Support Vector Machine (SVM). The misclassified data were further used to generate rules using C5.0. The result showed that the proposed method in transforming data used in the proposed model could perform better than comparison model. The proposed model has an accuracy of 84.54%, specificity of 85.24%, and sensitivity of 85.24%.


Modified Moran’s I, medical data mining, tuberculosis data, preliminary diagnosis, TB Screening.