OPTIMIZING PATIENT SERVICE PRIORITY DETERMINATION IN THE EMERGENCY DEPARTMENT USING THE K-MEANS ALGORITHM AT RSUD LANGSA ACEH
DOI:
https://doi.org/10.54314/jssr.v9i2.6232Keywords:
K-Means Clustering, Medical Informatics, Patient Care Prioritization, Patient Segmentation, Healthcare Data MiningAbstract
Abstract: Emergency Department (ED) services require speed, accuracy, and coordination among medical staff. Langsa Aceh Regional General Hospital, a Type B hospital, faces a high volume of patient visits that could lead to inefficiencies, particularly in determining service priorities. This study aims to optimize ED patient segmentation to support service prioritization using the K-Means clustering algorithm. The data used consists of 31,761 ED patient records from Langsa Regional General Hospital in 2025; after preprocessing, 24,062 records meeting the analysis criteria were obtained. Research variables included visit frequency, visit interval, type of service, duration of service, and patient urgency level. The research method employed a quantitative approach using data mining techniques with the K-Means algorithm. The results showed the formation of three clusters with a Silhouette Score of 0.6213, indicating good clustering quality. The resulting clusters represent the categories of non-urgent, semi-urgent, and complex care needs patients. These segmentation results can support more systematic service prioritization, improve efficiency, accelerate response times, and support a data-driven triage system at the Langsa Regional General Hospital Emergency Department in Aceh.
Keywords: K-Means Clustering, Medical Informatics, Patient Care Prioritization, Patient Segmentation, Healthcare Data Mining
Abstrak: Pelayanan pada Instalasi Gawat Darurat (IGD) menuntut kecepatan, ketepatan, dan koordinasi antar tenaga medis. RSUD Langsa Aceh sebagai rumah sakit tipe B menghadapi tingginya jumlah kunjungan pasien yang berpotensi menimbulkan ketidakefisienan, khususnya dalam penentuan prioritas pelayanan. Penelitian ini bertujuan mengoptimalkan segmentasi pasien IGD untuk mendukung penentuan prioritas pelayanan menggunakan algoritma K-Means clustering. Data yang digunakan merupakan data pasien IGD RSUD Langsa tahun 2025 sebanyak 31.761 record, dan setelah preprocessing diperoleh 24.062 data yang memenuhi kriteria analisis. Variabel penelitian meliputi frekuensi kunjungan, interval kunjungan, jenis layanan, durasi pelayanan, dan tingkat urgensi pasien. Metode penelitian menggunakan pendekatan kuantitatif melalui teknik data mining dengan algoritma K-Means. Hasil penelitian menunjukkan terbentuk tiga cluster dengan nilai Silhouette Score sebesar 0,6213 yang mengindikasikan kualitas pengelompokan baik. Cluster yang dihasilkan merepresentasikan kategori pasien non-urgensi, semi-urgensi, dan kebutuhan pelayanan kompleks. Hasil segmentasi ini dapat mendukung penentuan prioritas pelayanan secara lebih sistematis, meningkatkan efisiensi, mempercepat waktu respon, serta mendukung sistem triase berbasis data di IGD RSUD Langsa Aceh.
Kata Kunci: K-Means Clustering, Informatika Medis, Prioritas Pelayanan Pasien, Segmentasi Pasien, Data Mining Kesehatan
Downloads
References
Di, P. et al. (2025) “Pengaruh Pelayanan Kegawatdaruratan Terhadap Response Time Perawat Di Igd Di Rsud Toto Kabila Kabupaten Bone Bolango,” 10(2), pp. 27–39.
World Health Organization. (2010). Framework for action on interprofessional education and collaborative practice. WHO Press.
Badan Pusat Statistik Provinsi Aceh.
(2026). Statistik kesehatan Provinsi Aceh 2025. BPS Provinsi Aceh. https://aceh.bps.go.id
Han, J., Kamber, M., & Pei, J. (2012). Data mining: Concepts and techniques (3rd ed.). Morgan Kaufmann.
Tan, P. N., Steinbach, M., & Kumar, V. (2019). Introduction to data mining (2nd ed.). Pearson
Nugroho, Y. (2021). Analisis clustering K-Means pada data kesehatan. Jurnal Teknologi Informasi, 8(1), 12-20.
Sari, R., & Putra, A. (2022). Penerapan data mining dalam segmentasi pasien rumah sakit. Jurnal Informatika Kesehatan, 10(2), 45-52.
Jain, A. K. (2010). Data clustering: 50 years beyond K-means. Pattern Recognition Letters, 31(8), 651–666.
Xu, R., & Wunsch, D. (2005). Survey of clustering algorithms. IEEE Transactions on Neural Networks, 16(3), 645–678.
Prasetyo, E. (2012). Data mining: Konsep dan aplikasi menggunakan MATLAB. Andi.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Salwa Nur JB, Muhammad Irfan Sarif, Lola Astri Nadita, Fachrurazy, Lewika Tampubolon
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
