Fuzzy Inference System for Metabolic Syndrome prediction for people with Chronic Kidney Disease

  • Muhammad Zainudin Al Amin Magister Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia
  • Sri Kusumadewi Magister Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia
  • Linda Rosita Departemen Patologi Koinik, Fakultas Kedokteran, Universitas Islam Indonesia

Abstract

Patients with Chronic Kidney Disease (CKD) are increasing every year. One of the risk factors is due to metabolic syndrome because components in the metabolic syndrome are the cause of risk factors for CKD. The purpose of this study is to build a fuzzy inference system to predict metabolic syndrome for people with CKD. The method in this research is through literature study in building fuzzy rules and forming a fuzzy inference system. The variables used are body mass index, blood pressure, triglycerides, HDL and fasting blood sugar. System testing was carried out on eight hemodialysis patient data. The results of the system test are able to provide information related to the percentage of metabolic syndrome risk levels in 7 patients with chronic kidney disease.

References

[1] E. Pranita, “Penyakit Ginjal di Indonesia Meningkat 2 Kali Lipat, Bisakah Dicegah?,” kompas.com, 2020.
[2] Kemenkes RI, Hasil Utama Riset Kesehata Dasar (RISKESDAS). 2018.
[3] R. S. Padmawati, Y. W. Subronto, and B. S. Zega, “Edukasi Kesehatan Bagi Pasien Penderita Gagal Ginjal Kronis yang Menjalani Terapy Hemodialisis di RSUP Dr Sarjito Yogyakarta,” 2018.
[4] W. Wahyuti, I. Permana, and F. N. Salisah, “Aplikasi Sistem Pakar Berbasis Android untuk Diagnosa Awal Penyakit Ginjal Manusia Menggunakan Metode Forward Chaining,” Sntiki, vol. 10, no. November, pp. 121–128, 2018.
[5] WHO, “Definition, diagnosis and classification of diabetes mellitus and its complications: report of a WHO consultation. Part 1, Diagnosis and classification of diabetes mellitus,” World Health Organization, 1999.
[6] S. Rini, “SINDROM METABOLIK,” Jan. 2015.
[7] Depkes RI, “Infodatin Pusat Data dan Informasi Kementerian Kesehatan RI: Situasi Penyakit Ginjal Kronis,” 2017.
[8] K. Ikawati, S. Chasani, S. Suhartono, S. Hadisaputro, and S. Budijitno, “Komponen Sindrom Metabolik sebagai Faktor Risiko Penyakit Ginjal Kronik Stadium Terminal (Studi di RSUP Dr.Kariadi dan RSUD Kota Semarang),” Jurnal Epidemiologi Kesehatan Komunitas, vol. 3, no. 1, p. 18, 2018.
[9] P. Ayu, Y. Kandarini, G. Widiana, W. Sudhana, J. Loekman, and K. Suwitra, “Prevalensi Dan Hubungan Sindrom Metabolik Dengan Penyakit Ginjal Kronik Pada Populasi Desa Legian, Kuta Bali,” Journal of Internal Medicine, vol. 12, no. 2, 2011.
[10] S. Kusumadewi, Artificial Intelligence (Teknik dan Aplikasinya). Yogyakarta: Graha Media, 2003.
[11] H. Nasution, “Implementasi Logika Fuzzy pada Sistem Kecerdasan Buatan,” Jurnal ELKHA, vol. 4, no. 2, 2012.
[12] N. F. Susanto, “Deteksi dini penyakit demam berdarah dengan metode fuzzy expert system.” Universitas Islam Negeri Maulana Malik Ibrahim, 2016.
[13] S. Kusumadewi, L. Rosita, and E. G. Wahyuni, Model Sistem Pendukung Keputusan Klinis untuk Sindrom Metabolik. Yogyakarta: UII Press, 2020.
[14] E. E et al., “Pedoman Tatalaksana Dislipidemia PERKI 2013,” Indonesian Journal of Cardiology, pp. 245–70, Apr. 2015.
Published
2021-09-14