Application of Data Mining for Tuberculosis Disease Classification Using K-Nearest Neighbor

Abstract

This study aims to find out how much the application of the K-NN method and the accuracy value obtained by the K-NN method in clarifying data of Tuberculosis patients. This research focuses on improving public health and developing science to help people prevent and overcome tuberculosis. This type of research is quantitative. The literature study used is the documentation study. The method used by the K-Nearest Neighbor Algorithm. The results of the study showed that the process of applying data mining for the classification of tuberculosis disease using the K-Nearest Neighbor method obtained a final result of 80% accuracy. Thus, it can be concluded that the K-Nearest Neighbor algorithm is good.

Keywords

• tuberculosis
• k-nearest neighbors
• classification