K-Medoids Analysis Based On Health Risks And Medical Records In Health Insurance Premium Policies

Ratna Apriyanti; Titin Prihatin; Maksum Maksum

doi:10.55227/ijhet.v5i3.1206

Authors

Ratna Apriyanti Universitas Bina Sarana Informatika
Titin Prihatin Universitas Bina Sarana Informatika
Maksum Maksum Universitas Bina Sarana Informatika

DOI:

https://doi.org/10.55227/ijhet.v5i3.1206

Keywords:

K-Medoids, Gower Distance, Silhouette Score, Health Risk, Health Insurance

Abstract

This study is motivated by the need to group policyholders based on health risk levels and medical records to inform the formulation of health insurance premium policies. The methodology employs the K-Medoids algorithm combined with Gower Distance to process a mix of numerical and categorical variables, while the Silhouette Score is used to determine the optimal number of clusters. The dataset comprises 7,500 policyholders, with variables representing health risks and medical history specifically BMI, smoking status, physical activity level, alcohol consumption, chronic diseases, annual doctor visits, and a history of hospitalization in the previous year. The study yielded a Silhouette Score of 0.093783 (for k=3), indicating the data is best divided into three clusters. The analysis identified three distinct health risk and medical record groups: Cluster 2 (low risk), containing 3,431 policyholders with the lowest medical costs, chronic disease counts, and healthcare service utilization; Cluster 0 (medium risk), containing 1,975 policyholders characterized by the presence of chronic diseases leading to increased healthcare utilization despite having a normal BMI; and Cluster 1 (high risk), containing 2,094 policyholders with obese BMIs, the highest number of chronic diseases, and the highest medical costs, thereby presenting a higher potential risk for claims. The findings demonstrate that clustering using K-Medoids with Gower Distance can support the development of more proportional, risk-based health insurance premium policies.

Downloads

Download data is not yet available.

References

Alfiah, F., Almadayani, A., Al Farizi, D., & Widodo, E., “Analisis Clustering K-Medoids Berdasarkan Indikator Kemiskinan di Jawa Timur Tahun 2020,” Jurnal Ilmiah Sains, vol. 22(1), pp. 1-7, 2022.

Algiffary, A., & Sutabri, T. (2023). Perbandingan algoritma K-Means dan K-Medoids untuk pengelompokan program BPJS Ketenagakerjaan. Indonesian Journal of Computer Science, 12(2), 284–301.

Ananda, M. D., Malik, K. N., Masruriyah, A. F. N., & Mardiah, M. (2025). Studi komparatif algoritma K-Means dan K-Medoids untuk segmentasi informasi kesehatan. Computer Science (CO-SCIENCE), 5(2), 103–112.

BPJS Kesehatan. (2025). Monthly Report Monitoring JKN 31 Juli 2025. Dewan Jaminan Sosial Nasional (DJSN), 2023–2024.

C. Sukmayadi, A. Primajaya, And I. Maulana, “Penerapan Algoritma K-Medoids Dalam Menentukan Daerah Rawan Banjir Di Kabupaten Karawang,” Vol. 6, No. 3, Pp. 187–196, 2021.

E. Tasia and M. Afdal, “Comparison Of K-Meians And K-Meidoid Algorithms For Clusteiring Of Flood-Pronei Areias In Rokan Hilir District Peirbandingan Algoritma K-Meians Dan K-Meidoids Untuk Clusteiring Daeirah Rawan Banjir Di Kabupatein Rokan Hilir,” vol. 3, no. 1, pp. 65–73, 2023.

Fatunnisa, A., & Marcos, H. (2024). Prediksi Kelulusan Tepat Waktu Siswa SMK Teknik Komputer Menggunakan Algoritma Random Forest. Jurnal Manajemen Informatika (JAMIKA), 14(1), 101–111.

Hendrastuty, N. (2024). Penerapan data mining menggunakan algoritma K-Means Clustering dalam evaluasi hasil pembelajaran siswa. Jurnal Ilmiah Informatika dan Ilmu Komputer (JIMA-ILKOM), 3(1), 46–56.

Khalif, A., Hasanah, A. N., Ridwan, M. H., & Sari, B. N., “Klasterisasi Tingkat Kemiskinan di Indonesia menggunakan Algoritma K-Means,” Generation Journal, Vols. 8, no. 1, pp. 54-62, 2024.

Kurniati, D., Fauzi, M. Z., Ripangi, Falegas, A., & Indria. (2021). Clustering of Earthquake Prone Areas in Indonesia Using K-Medoids Algorithm. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 1(1), 47–57.

Laksono, B., Syahidin, Y., & Yunengsih, Y. (2024). Implementasi data mining clusterisasi data pasien rawat inap dengan algoritma K-Means Clustering. Jurnal Teknologi Sistem Informasi dan Aplikasi, 7(2), 621–627.

Organization, W. H. (2026). World health statistics 2026: Monitoring health for the SDGs, Sustainable Development Goals. World Health Organization.

Paembonan, S., & Abduh, H. (2021). Penerapan metode Silhouette Coeficient untuk evaluasi clutering obat. PENA TEKNIK: Jurnal Ilmiah Ilmu-Ilmu Teknik, 6(2), 44–54.

Purwayoga, V., Lukmana, H. H., & Anggraini, W. A. (2024). Pengukuran skala prioritas data logistik bencana dengan K-Means Cluster dan Skyline Query. JASIEK: Jurnal Aplikasi Sains, Informasi, Elektronika dan Komputer, 6(2), 135–144.

S. Bahri And D. M. Midyanti, “Penerapan Metode K-Medoids Untuk Pengelompokan Mahasiswa Application Of K-Medoids Method For Dropout,” Vol. 10, No. 1, Pp. 165–172, 2023.

Sudrajat, R., Hadiana, A. I., & Melina, M. (2025). Evaluasi kualitas cluster wilayah rawan bencana menggunakan K-Means dengan Silhouette dan Elbow Method. Jurnal Algoritma, 22(2), 127–139.