Klasterisasi Data Rekam Medis pada Penyakit Kulit Menggunakan K-Means Clustering

Abstract

Clustering medical record data has become an effective approach for analyzing and grouping patient information in the medical field. This study aims to apply the K-means clustering method to patient medical records with skin diseases. The dataset consists of clinical attributes such as symptoms, medical history, and laboratory test results. In the initial stage, irrelevant and incomplete data are removed, and significant attributes are selected. Then, the K-means clustering method is applied to group the medical records data into similar clusters. The optimal number of clusters is determined using the elbow method and silhouette validation. The results of the study show that the K-means clustering method successfully groups skin disease medical records into different clusters based on the age and address characteristics of the patients. In conclusion, the K-means clustering method proves to be effective in clustering medical records data for skin diseases. By using this approach, an improved understanding of the characteristics and patterns of skin diseases can be expected, as well as improvements in patient management based on similar clinical groups. The results of this study indicate that Cluster 0 has a total of 527 patients, characterized by an age range of 30 to 45 years and a dominant location in Medan Labuhan. Cluster 1 has a total of 184 patients, characterized by an age range of 53 to 61 years and a dominant location in Medan Johor. Cluster 2 has a total of 271 patients, characterized by an age range of 55 to 71 years and a dominant location in Medan Petisah. Cluster 3 has a total of 269 patients, characterized by an age range of 24 to 33 years and a dominant location in Medan Denai. Lastly, Cluster 4 has a total of 313 patients, characterized by an age range of 11 to 25 years and a dominant location in Medan Marelan.