SEGMENTASI PROFIL KESEHATAN PROVINSI DI INDONESIA MENGGUNAKAN ANALISIS FAKTOR DAN K-MEANS CLUSTERING
CLUSTERING INDONESIAN PROVINCES BASED ON HEALTH INDICATORS USING FACTOR ANALYSIS AND K-MEANS
DOI:
https://doi.org/10.52972/hoaq.vol17no2.p362-372Keywords:
Analisis Faktor, K-Means Clustering, Indikator Kesehatan, Ketimpangan Wilayah, Silhouette ScoreAbstract
Indonesia sebagai negara kepulauan dengan 38 provinsi menyimpan berbagai ketimpangan kondisi kesehatan yang kompleks. Tujuan dari penelitian ini yaitu untuk mengidentifikasi pola kategorisasi provinsi di Indonesia menurut parameter kesehatan melalui pendekatan analisis faktor dan klasterisasi K-Means. Riset ini menggunakan dataset yang memuat 12 variabel kesehatan provinsi Indonesia. Kelayakan data dan variabel diverifikasi dengan uji Kaiser-Meyer-Olkin (KMO) dan Bartlett's Test. Kemudian diekstrak ke faktor-faktor yang menghasilkan 3 faktor. Faktor yang dihasilkan selanjutnya digunakan sebagai input klasterisasi K-Means, dengan jumlah klaster optimal ditentukan melalui Elbow Method, Davies-Bouldin Index, dan Calinski-Harabasz Index, serta divalidasi menggunakan Silhouette Score. Hasil penelitian mengangkat empat klaster yang divalidasi dengan Silhouette Score sebesar 0,4563. Klaster yang dihasilkan mengungkapkan segmentasi wilayah yang kontras secara detail, di mana klaster 0 yang mencerminkan wilayah berprofil rata-rata atau menengah nasional, klaster 1 yang mencerminkan outlier tunggal dengan tingkat kerentanan tertinggi dan kritis, klaster 2 yang mencerminkan pusat demografi dengan kapasitas infrastruktur medis berskala masif, dan klaster 3 yang mencerminkan wilayah terluar yang rentan dan jauh. Analisis ini menegaskan bahwa pendekatan analisis faktor dan klasterisasi K-Means mampu menghasilkan pola-pola dalam kesehatan nasional, sehingga pemerintah mampu mempertimbangkan profil tiap klaster secara spesifik demi intervensi yang efektif dan berkeadilan.
As an archipelagic nation with 38 provinces, Indonesia faces a range of complex health disparities. The purpose of this study is to identify characteristics of provincial categorization in Indonesia according to health parameters using factor analysis and K-Means clustering. This study uses a dataset containing 16 health variables for Indonesian provinces. The eligibility of the data and variables was verified using the Kaiser-Meyer-Olkin (KMO) test and Bartlett’s test. The data was then extracted into factors, yielding three factors. These factors were then used as input for K-Means clustering, with the optimal number of clusters determined using the Elbow Method, the Davies-Bouldin Index, and the Calinski-Harabasz Index, and validated using Silhouette Score. The result identified four clusters, validated by a Silhouette Score of 0.4563. The resulting clusters reveal a detailed segmentation of regions with contrasting characteristics: Cluster 0 represents regions with an average or national-level profile; Cluster 1 represents a single outlier with the highest and most critical vulnerability level; Cluster 2 represents a demographic center with massive medical infrastructure capacity; and Cluster 3 represents vulnerable and remote outlying regions. This analysis confirms that factor analysis and K-means clustering can identify patterns in national health, enabling the government to consider the specific profile of each cluster in order to implement effective and equitable interventions.
References
GBD 2019 Indonesia Subnational Collaborators, "The State of Health In Indonesia's Provinces, 1990–2019: a Systematic Analysis for the Global Burden of Disease Study 2019," The Lancet Global Health, vol. 10, no. 11, pp. e1632–e1645, Nov. 2022, doi: 10.1016/S2214-109X(22)00371-0.
H. Maryani, A. Rizkianti, and N. Izza, "Classification of Healthy Family Indicators in Indonesia Based on a K-Means Cluster Analysis," Journal of Preventive Medicine and Public Health, vol. 57, no. 3, pp. 234–241, May 2024, doi: 10.3961/jpmph.23.497.
O. Arnilia, S. I. Ishak, T. Widodo, and I. G. N. A. B. Tatwa, "Clustering of Provincial Health Vulnerability Levels in Indonesia Using the K-Means Method," Jurnal Informatika dan Rekayasa Perangkat Lunak, vol. 7, no. 1, pp. 26–34, Mar. 2026, doi: 10.33365/jatika.v7i1.1469.
World Health Organization, "New WHO Publication Highlights Importance of Health Inequality Monitoring to Advance Health Equity," WHO Indonesia. [Online]. Apr. 4, 2025. Available: https://www.who.int/indonesia/news/detail/04-04-2025-new-who-publication-highlights-the-importance-of-health-inequality-monitoring-to-advance-health-equity. [Accessed: May 30, 2026].
G. F. Ibanez, G. W. Wiriasto, and Rosmaliati, "Kombinasi Principal Component Analysis dengan Algoritma K-Means untuk Klasterisasi Data Stunting," KLIK: Kajian Ilmiah Informatika dan Komputer, vol. 5, no. 1, 2024, doi: 10.30865/klik.v5i1.1977.
A. K. Jain, "Data Clustering: 50 Years Beyond K-Means," Pattern Recognition Letters, vol. 31, no. 8, pp. 651–666, Jun. 2010, doi: 10.1016/j.patrec.2009.09.011
M. Shutaywi and N. N. Kachouie, "Silhouette Analysis for Performance Evaluation in Machine Learning with Applications to Clustering," Entropy, vol. 23, no. 6, p. 759, Jun. 2021, doi: 10.3390/e23060759.
B. Sowan, T.-P. Hong, A. Al-Qerem, and C.-H. Chen, "Ensembling Validation Indices to Estimate the Optimal Number of Clusters," Applied Intelligence, vol. 53, pp. 9933–9957, Aug. 2022, doi: 10.1007/s10489-022-03939-w.
A. Karanikola, C. M. Liapis, and S. Kotsiantis, "A comparative Study of Validity Indices on Estimating the Optimal Number of Clusters," in Proc. 2021 12th Int. Conf. Information, Intelligence, Systems and Applications (IISA), IEEE, 2021, pp. 1–8, doi: 10.1109/IISA52424.2021.9555497.
S. Haben, C. Singleton, and P. Grindrod, "Analysis and Clustering of Residential Customers Energy Behavioral Demand Using Smart Meter Data," IEEE Transactions on Smart Grid, vol. 7, no. 1, pp. 136–144, Jan. 2016, doi: 10.1109/TSG.2014.2325587.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Jurnal HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi diterbitkan berdasarkan lisensi Creative Commons Attribution 4.0 International License (CC BY 4.0). Lisensi ini memungkinkan setiap orang untuk Berbagi: menyalin dan mendistribusikan kembali materi ini dalam format atau bentuk apapun; Adaptasi: merombak, mengubah, dan membuat turunan dari materi ini untuk keperluan apa pun, termasuk keperluan komersial, asalkan mereka memberikan pengakuan kepada Penulis Asli atas hasil karya aslinya.
