Almerya Indriastuti
Faculty of Economics and Business, Budi Luhur University, Jakarta, Indonesia

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Strategic Patient Segmentation Based on Age, Length of Stay, and Hospital Revenue Using K-Means Clustering:: a Hospital Management Perspective Almerya Indriastuti; Arief Wibowo
Vifada Management and Social Sciences Vol. 4 No. 2 (2026): July - December
Publisher : Yayasan Vifada Cendikia Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70184/v1kq1v81

Abstract

Purpose: This study aims to identify strategic patient segments based on age, length of stay, and hospital revenue using K-Means clustering and to interpret the resulting segments from a hospital management perspective. Research Method: A quantitative descriptive-exploratory design was employed using anonymized secondary inpatient data from a private international-standard hospital in South Tangerang, Banten, Indonesia. The variables included patient age, length of stay, and hospital revenue. Data were cleaned, transformed, normalized, and analyzed using the K-Means algorithm in RapidMiner Studio, resulting in three clusters. Results and Discussion: Three patient segments with distinct service-utilization and financial profiles were identified. Cluster 0 generated average revenue of IDR 163,171,150, Cluster 1 generated IDR 330,793,288, and Cluster 2 recorded the highest average revenue of IDR 994,300,700. Despite relatively similar patient ages and lengths of stay, substantial revenue differences suggest variations in case complexity, medical procedures, and resource intensity. Implications: The segmentation model can support differentiated service strategies, resource allocation, capacity planning, and data-driven revenue management. Future studies should incorporate clinical severity, payment methods, treatment types, and alternative clustering techniques. Originality: This study demonstrates the managerial application of K-Means clustering by integrating demographic, service-utilization, and financial variables to develop actionable patient segmentation for hospital decision-makingĀ