Optimalisasi Pengelompokan Gangguan Kecemasan dalam Mendukung Tujuan Pembangunan Berkelanjutan Menggunakan Algoritma K-Means dan K-Medoids

Abstract Data clustering is a data mining technique that aims to find hidden patterns in a dataset. The dataset used in this study was taken from the Kaggle public dataset on anxiety attacks. Anxiety disorder is a mental condition characterized by excessive and prolonged feelings of anxiety. Clustering anxiety disorders facilitates finding the cause, effect, and better treatment. Therefore, this study aims to group anxiety disorders using the K-Means and K-Medoids algorithms by considering attributes such as stress level, sleep patterns, and physical activity. The performance of the model is evaluated using the Davies-Bouldin Index (DBI). The results showed that the K-Means algorithm produced the lowest DBI value in cluster ten with an accuracy value of 2.331. This shows that the K-Means algorithm is able to identify significant patterns in anxiety disorder data. This study can be a recommendation for health professionals in making more precise diagnoses, understanding the characteristics of the causes of anxiety disorders. In addition, this study also supports the achievement of the Sustainable Development Goals in an effort to improve the overall health and welfare of the community. Keywords— K-Means, K-Medoids, Anxiety Disorders, Sustainable Development Go als