The research examines disease clustering in Indonesia using the K-Medoids method, chosen due to the presence of outliers in the data. The variables used in this research include cases of infectious diseases such as malaria, pulmonary tuberculosis, pneumonia, leprosy, diarrhea, dengue fever, and HIV/AIDS. The objects of analysis are the provinces in Indonesia. The results from the Elbow method and Silhouette Coefficient indicate that the optimal number of clusters is three. Three distinct clusters were identified based on disease prevalence, with varying levels of health conditions across regions. The Parallel Coordinates Plot revealed the characteristics of each cluster. Cluster 1 reflects areas with generally low to medium disease prevalence, Cluster 2 indicates regions with significantly higher disease rates, and Cluster 3 represents areas with mixed disease profiles. These findings provide insights into disease distribution and prevalence, supporting the development of targeted public health strategies. The research highlights the ongoing challenges posed by infectious diseases in Indonesia and emphasizes the importance of data mining techniques for understanding disease characteristics and spatial patterns.