<![CDATA[Human Immunodeficiency Virus (HIV) remains a major public health challenge in Papua, Indonesia, where geographical barriers and limited resources complicate service delivery. This study applies clustering methods to HIV screening data from 22 Health Service Units (UPK) in Teluk Bintuni Regency during 2024–2025. The final dataset consisted of 29 valid unit-year observations containing variables related to total tests, HIV-positive cases, and sex-disaggregated distributions. Data preprocessing followed the Knowledge Discovery in Database (KDD) framework, including data selection, cleaning, log transformation, normalization, and the construction of derived variables such as positivity rate and gender ratios. Four clustering algorithms were compared, namely K-Means, Hierarchical Clustering, Fuzzy C-Means, and DBSCAN, using Silhouette Score, Davies-Bouldin Index, and Calinski-Harabasz Index. The results indicate that K-Means produced the most stable and interpretable clustering structure, forming three groups of UPKs: intermediate screening units with moderate coverage and low positivity, priority units with limited testing but high positivity rates, and active screening units with the highest testing volume and case detection. These findings reveal heterogeneity in HIV screening performance across UPKs and support differentiated intervention strategies. Units with high apparent positivity but low testing coverage require expanded outreach, field verification, and improved access to HIV screening services, while active screening units should be strengthened through counseling, referral, and follow-up services. This study demonstrates the usefulness of clustering analysis in identifying service gaps and supporting evidence-based HIV intervention planning at the local level.]]>
