<![CDATA[Transformation Digital transformation in the healthcare sector necessitates optimal utilization of medical record data to facilitate more effective decision-making processes. Prima Melati Clinic continues to experience limitations in managing medical record data, which has not undergone systematic analysis to distinguish prevailing disease patterns. The purpose of this study is to analyze and apply the K-Means Clustering algorithm to identify dominant diseases based on patient medical record data at Prima Melati Clinic. The research methodology used is a quantitative approach that utilizes data mining techniques through the Knowledge Discovery in Database (KDD) stages, which include data preprocessing, application of the K-Means algorithm, and interpretation of clustering results. The dataset used consists of approximately 1000 patient medical records covering the period of January 2025 to May 2025. The data preprocessing phase includes data cleaning, missing value management, and data normalization using the StandardScaler technique. Determining the optimal number of clusters is achieved through the Elbow method, using the Sum of Squared Errors (SSE) calculation. The findings indicate that the K-Means algorithm with a cluster size of 3 (k) effectively categorizes patient data into three main clusters based on disease diagnostic characteristics classified by severity (mild, moderate, and severe). Each cluster reveals distinct dominant disease patterns, providing insight into disease distribution in relation to the severity of the patient's condition. The results of this analysis can be utilized by clinics in developing drug procurement strategies, scheduling medical personnel, and designing more targeted disease prevention strategies. Consequently, the implementation of the K-Means Clustering algorithm has demonstrated effectiveness in identifying dominant disease patterns and in strengthening data-driven decision-making at Prima Melati Clinic.]]>
