<![CDATA[Patient segmentation based on perceptions of service quality is a crucial step in improving patient experiences, optimizing resources, and enhancing healthcare service quality. However, understanding patients' needs and priorities in depth poses a challenge, particularly for hospitals serving populations with diverse demographic backgrounds. This study aims to cluster patients in a private hospital in Jambi City based on their perceptions of service quality using the K-Means algorithm. Data were collected from a 2022-2023 survey, covering patient demographics and perceptions of service quality. The data were processed through preprocessing steps, including missing value imputation, normalization, and encoding. The optimal number of clusters was determined using the Elbow and Silhouette Score methods. The results revealed three main clusters with distinct characteristics. The first cluster (34.29%) includes patients prioritizing service speed and procedural ease. The second cluster (46.12%) consists of patients who emphasize staff competence and cost fairness as their main priorities. The third cluster (19.59%) comprises patients with higher educational backgrounds who are more critical of facility quality and complaint handling. Evaluation using the Davies-Bouldin index demonstrated good cluster separation (score -0.645). This study concludes that patient segmentation based on perceptions of service quality can serve as a foundation for strategic decision-making to improve hospital service quality. Recommendations for future research include applying other algorithms such as DBSCAN, integrating sentiment analysis, and employing a hybrid approach to predict patient needs. These approaches are expected to provide a deeper understanding and more effective personalization of patient care.]]>
