<![CDATA[This study aims to optimize outpatient service time at Maryam Citra Medika Hospital, which has been facing long waiting times due to linear queues without considering the patient's urgency level. This results in patients with urgent conditions having to wait with patients with lower needs, resulting in ineffective service time and increasing health risks. The K-Means Clustering method was applied to group patients based on urgency level and determine efficient service time allocation. The data used were 8,308 outpatient visit records from January to December 2024, covering clinic service times, vital signs, chief complaints, and the patient's general condition. Data was processed using attribute selection and Min-Max Scaling normalization. Determining the optimal number of clusters (k) using the Elbow method identified k=3 as the best value. The implementation of K-Means Clustering with k=3 resulted in three patient clusters with unique clinical characteristics. Model performance evaluation using the Davies-Bouldin Index yielded a value of 0.164, which is excellent and close to ideal, indicating that the clusters formed are internally cohesive and externally well separated. Based on the characteristics of each cluster, recommendations for patient service time allocation are based on clinical condition priority. Cluster 0 (elderly patients with severe hypertension) is recommended to receive the shortest wait time (<30 minutes) and the longest consultation time (15 minutes), while Cluster 2 (healthy young adults) is allocated the maximum wait time (55 minutes) and the minimum consultation time (5 minutes). This implementation is expected to optimize patient flow, improve service safety and quality, and serve as a basis for operational decision-making for hospital management.]]>
