Tuberculosis (TB) is an infectious disease caused by Mycobacterium tuberculosis and remains a major public health problem in Indonesia, particularly in East Java Province. This study aims to group tuberculosis risk levels across 38 districts/cities in East Java Province based on health determinants using the Fuzzy Gustafson-Kessel (FGK) clustering method. The data were obtained from the Central Statistics Agency of East Java Province and the East Java Provincial Health Office in 2024, using four main variables: the number of Diabetes Mellitus (DM) patients, malnourished toddlers, Human Immunodeficiency Virus (HIV) patients, and productive-age active smokers. The FGK method was applied because it can form elliptical clusters through the Mahalanobis distance approach, making it suitable for data with non-homogeneous distribution characteristics. The optimal number of clusters was determined using the Modified Partition Coefficient (MPC). The results show that the four-cluster solution achieved the highest MPC value of 0,987 indicating good cluster partition quality. These four clusters represent tuberculosis risk groups categorized as low priority, medium priority, and high priority across districts/cities in East Java Province. The clustering results can serve as a basis for determining intervention priorities and supporting more targeted public health policy planning
Copyrights © 2026