<![CDATA[Flooding in Binjai City increases post-flood disease incidence in slum settlements due to inadequate sanitation and high environmental vulnerability, while disease records are often scattered, poorly organized, and late, slowing health interventions. This study groups post-flood disease data in affected residential areas using K-Means clustering based on disease type, village, and slum level. A total of 1,100 records were collected from five districts in Binjai City; after excluding incomplete records, 850 valid records were used in the 2-cluster scenario and 1,086 in the 3-cluster scenario, implemented in a Matlab-based application. In the 2-cluster scenario, Cluster 1 contained 536 records with centroid (3.64, 12.48, 2.41) and Cluster 2 contained 314 records with centroid (4.18, 16.25, 2.09). In the 3-cluster scenario, Cluster 1 contained 498 records with centroid (3.45, 11.62, 2.31), Cluster 2 contained 312 records with centroid (4.02, 16.47, 2.05), and Cluster 3 contained 276 records with centroid (2.91, 8.35, 2.76), all dominated by diarrhea in medium-to-high slum-level areas. Internal validity indices (Silhouette, Davies-Bouldin, Calinski-Harabasz), computed on a reference sample, support retaining the 3-cluster scheme for its finer, more actionable risk stratification. The results show that K-Means clustering groups affected areas by disease and slum characteristics, and a centroid-derived priority ranking of the clusters is proposed to support health priority setting, medical resource distribution, and data-driven post-flood disease mitigation.]]>
Copyrights © 2026
