Klasterisasi Pasien Rawat Inap BPJS pada RS Islam Assyifa Sukabumi menggunakan Metode K-Means

Irfan Nafis Sjamsuddin; Dasya Arief Firmansyah; Yuni Laferani

doi:10.53863/kst.v7i01.1617

Authors

Irfan Nafis Sjamsuddin Universitas Siliwangi, Tasikamalaya, Indonesia
Dasya Arief Firmansyah Universitas Bina Sarana Informatika, Jakarta Pusat, Indonesia
Yuni Laferani Universitas Siliwangi, Tasikamalaya, Indonesia

DOI:

https://doi.org/10.53863/kst.v7i01.1617

Keywords:

BPJS, Clustering, K-Means, Hospital

Abstract

Hospitals as providers of quality health services face challenges in managing increasingly complex patient data. The data has not been optimally utilized by hospital management and has great potential to be analyzed and become a basis for decision-making. Optimization can be utilized by BPJS inpatient data at the Assyifa Sukabumi Islamic Hospital in the fourth quarter of 2024 using data mining techniques. The technique proposed in this study is the K-Means method to group BPJS patients based on certain variables such as age, gender, disease diagnosis, inpatient class, and length of hospitalization. The results of this study revealed that there were 3 clusters of 3526 patient data. Cluster 1 consists of 1545 patients with infectious diseases caused by microorganisms. Cluster 2 consists of 712 patients with diseases related to pregnancy, childbirth, or symptoms that must be identified through further clinical or laboratory examinations. Cluster 3 consists of 1269 patients with diseases associated with the respiratory system, digestive system, and blood circulation system. The evaluation showed that the grouping of BPJS patients with 3 cluster results had the best quality, with a Davies-Bouldin Index (DBI) value of 0.561. The study results can be a reference in planning the allocation of hospital resources. Suggestions for further research are the application of other data mining techniques in optimizing hospital data management

References

Ali, A., & Masyfufah, L. (2020). Klasterisasi Pasien BPJS Dengan Metode K-Means Clustering Guna Menunjang Program Jaminan Kesehatan Nasional Di Rumah Sakit Anwar Medika Balong Bendo Sidoarjo. Jurnal Wiyata, 8(1), 8–22. https://doi.org/p://dx.doi.org/10.56710/wiyata.v8i1.427

BPJS Kesehatan. (2024). Laporan Pengelolaan Program Tahun 2023 & Laporan Keuangan Tahun 2023 (Auditan).

Firmansah, D. A., Rohman, R. S., & Ermawati, E. (2021). Penerapan Metode Ward and Peppard - Cassidy Pada Perencanaan Strategis Sistem Informasi Rumah Sakit Islam Assyifa Sukabumi. Simpatik: Jurnal Sistem Informasi Dan Informatika, 1(1), 43–52. https://doi.org/10.31294/simpatik.v1i1.407

Herdiaman, E. A., Sudiarjo, A., Hikmatyar, M., Informatika, T., Perjuangan, U., & Barat, J. (2024). Klasterisasi Pasien pada RSUD Ciamis Menggunakan Metode K-Means. JITET (Jurnal Informatika Dan Teknik Elektro Terapan), 12(3), 3558–3546. https://doi.org/http://dx.doi.org/10.23960/jitet.v12i3S1.5124

Jain, A. K. (2010). Data clustering: 50 years beyond K-means. Pattern Recognition Letters, 31(8), 651–666. https://doi.org/10.1016/j.patrec.2009.09.011

Ningsih, Y. G., Samosir, K., & Satria, B. (2025). Segmentasi Pasien Rumah Sakit Berdasarkan Pola Kunjungan Menggunakan Algoritma K-Means Clustering untuk Optimasi Layanan Medis. Jurnal Pendidikan Sains Dan Komputer, 5(1), 59–69. https://doi.org/https://doi.org/10.47709/jpsk.v5i01.5492 Segmentasi

Peraturan Menteri Kesehatan Republik Indonesia Nomor 24 Tahun 2022 Tentang Rekam Medis, Kementerian Kesehatan Republik Indonesia 1 (2022).

Saputra, I. (2023). Belajar Mudah Data Mining untuk Pemula (Cetakan 1). Informatika Bandung.

Sulastri, H., & Gufroni, A. I. (2017). Penerapan Data Mining Dalam Pengelompokan Penderita Thalassaemia. Jurnal Nasional Teknologi Dan Sistem Informasi, 3(2), 299–305. https://doi.org/10.25077/teknosi.v3i2.2017.299-305

WHO. (2010). International Statistical Classification of Diseases 10th Revision, Version for 2010. In World Health Organization (Vols. 1 & 3). https://www.who.int/publications/m/item/icd-10-updates-2010