Application of Data Mining in Disease Clustering at Klinik Keluarga

Abstract

The purpose of this study is to provide recommendations for counseling materials to assist the Promkes and Marketing Coordinator at the Klinik Keluarga in determining appropriate health counseling materials in an area. Counseling is conducted on a scheduled basis to a predetermined area. However, many of the materials presented are not in accordance with the majority of diseases suffered by the community in the area. This causes clinic services to be not optimal due to lack of awareness of a disease in the region. Data Mining with Clustering method and K-Means algorithm is used in this study to determine the pattern of disease distribution based on its characteristics from the data sources used, consisting of visit data, parent disease data, disease category data, sub-district data, and village data. The evaluation results show that the disease clustering process produces an average accuracy of 0.263. These results show that data mining with the clustering method can help the Promkes and Marketing Coordinator at the Family Clinic in determining the right counseling material for the community.