<![CDATA[Information technology can be applied to identify endemic diseases in an area, in this case Sabu Raijua Regency. Endemic diseases can be identified early using the Clustering K-Means method where this method partitions data into one or more clusters/groups, so that data with the same characteristics are grouped into the same cluster and data with different characteristics are grouped into groups. another group. The data used in this study are medical record data at the Seba Health Center as many as 1020 data with year, village, diagnosis, age and gender variables. Due to the large amount of data, the K-Means Clustering process will use Weka 8.5 as a tool. The results of this study indicate the characteristics and patterns of endemic diseases in the service area of the Seba Health Center with variables of year, village, diagnosis, age and gender, the characteristics used are based on the most optimal number of clusters. The most optimal number of clusters can be found using the Elbow Method. The results of clustering of 1020 medical record data showed that the most optimal number of clusters was 2 clusters with the characteristics of ARI diagnosis. Keywords:]]>
Copyrights © 2022
