Analysis of Tuberculosis Cases in Indonesian by Using K-means Clustering Technique

Indonesia is the country with the second largest number of tuberculosis cases in the world after India. The cases are growing from year to year. This study aims to analyze the differences of tuberculosis cases among provinces in Indonesia focusing on the cases for different groups of ages. The analysis is carried out by clustering the provinces based on the similarity of tuberculosis cases ratio for each province. This paper has conducted an analysis of tuberculosis cases by using one of clustering method, i.e., k-means algorithm. The result of the research found that DKI Jakarta is the province with the highest number of tuberculosis cases for 5 groups of ages among 7 groups. On the contrary, DKI Jakarta is the 2nd best province of National Health Index. This finding needs more attentions from the government to find out what are the real problems exist in DKI Jakarta.