Data Mining Pengelompokan Pasien Rawat Inap Peserta BPJS Menggunakan Metode Clustering (Studi Kasus : RSU.Bangkatan)

  • Novi Karolina Surbakti STMIK KAPUTAMA BINJAI
Keywords: Data Mining, K-means Algorithm, Inpatient.

Abstract

The system currently used by the hospital is still manual in managing patient data and information, therefore it is necessary to have a Bangkat Binjai Hospital Service system to provide complete and detailed information to hospital patients using BPJS. So in this case the author will design and build a system that will be used in grouping inpatients based on the BPJS Class and the variables determined using the clustering method, so that later it can make it easier for administrators to process data and information on inpatients using BPJS. From the tests carried out using the clustering method with the k-means algorithm, it can be seen that cluster 3 of the criteria for disease type, diagnosis result, and age, the group that has the highest set / value of BPJS Class patient data, namely in Cluster 1 totaling 435 patient data Inpatients using BPJS at the age of 20-39 years and the type of disease are benign tumors, then the BPJS class used is the Level 2 BPJS. Inpatients who use BPJS at the age of 20-39 years and the type of disease is heart complications, then the BPJS class used is BPJS Level 1. And the group that has the highest set / value of BPJS Class patient data, namely Cluster 3 totaling 270 inpatient data. who used BPJS at the age of 20-39 years and the type of disease was uric acid, then the BPJS class was used is BPJS Level 1.

References

[1] Adi Nugroho. 2005. Analisis dan Perancangan Sistem Informasi Dengan Metodologi Berorientasi Objek. Informatika. Bandung.
[2] B, Indra Y atini. (2010). Flowchart, Algoritma dan Pemrogaman Menggunakan Bahasa C++ Builder. Yogyakarta : Penerbit Graha Ilmu.
[3] Eko Prasetyo. (2014). Data Mining Mengolah Data Menjadi Informasi.
[4] Menggunakan Matlab. Yogyakarta: Andi Offset.
[5] Fajar Astuti Hermawati. (2013). Data Mining. Yogyakarta: Andi Offset
[6] Hend. (2006). Pengertian Unified Modeling Language (UML). Dipetik Oktober 05, 2015, darihttp://adwintaactivity.blogspot.co.id/2012/0 4/definisi-unified-modeling-language-uml.html.
[7] Muningsih, E., & Kiswati, S. (2015). Penerapan Metode K-Means Untuk Clustering Produk Online Shop. Jurnal Bianglala Informatika..
[8] Prasetyo, Eko.2012.Data Mining Konsep dan Aplikasi Menggunakan Matlab.Yogyakarta: Andi
[9] Santosa, Budi. 2007. “Data mining terapan dengan MATLAB”. Yogyakarta Graha Ilmu.
[10] Silitonga, P . D. P ., & Damanik, R. (2016). Implementasi Algoritma K-Means Clustering Pada Analisis Penyebaran Penyakit Pasien Pengguna Badan Penyelenggara Jaminan Sosial Kesehatan (BPJS). Jurnal Teknik Informatika UNIKA Santo Thomas. https://doi.org/10.17605/JTI.V1I2.34.G39t.
[11] Sumadikarta, I., & Abeiza, E. (2014). PENERAPAN ALGORITMA K-MEANS PADA DATA MINING UNTUK MEMILIH PRODUK DAN PELANGGAN POTENSIAL (Studi Kasus : PT Mega Arvia Utama). Jurnal Satya Informatika
[12] Nababan, Darsono, and Justin Eduardo Simarmata. "Analysis Of Student Satisfaction With Academic Services Using Fuzzy Mamdani Method."Solid State Technology63.3 (2020): 5069-5075.
Published
2021-08-24