<![CDATA[Diabetes Mellitus is a Chronic disease with a continuously increasing global prevalance, including in Indonesia, posing a serious challenge to healthcare systems. Early detection and risk stratification of individuals are crucial for implementing effective prevention and management strategies. This research utilizes the K-Means Clustering algorithm, an unsupervised learning method in data mining, to identify and group individuals based on their diabetes risk profiles from available medical data. The dataset used is the popular Pima Indian Indian Dataset, comprising eight clinical attributes such as glucose level, blood pressure, skin thickness, BMI, and age. The methodological process includes data preprocessing with standardization using StandardScaler, determining the optimal number of clusters through the Elbow Method, Implementing K-Means clustering, and evaluating clustering quality using the Silhouette Coefficient. The research results demonstrate that this algorithm can group patients into low, medium, and high-risk categories with sufficient cluster accuracy. This approach can be used as a supporting tool in medical decision systems.]]>
Copyrights © 2025
