Model Berbasis Logika Fuzzy untuk Mengukur Risiko Menderita Diabetes Melitus
Abstract
Diabetes Mellitus (DM) is a global health issue. DM is a non-communicable disease that spreads quickly. In general, type 2 diabetes mellitus (DMt2) is the most common type of diabetes suffered by people caused by irregular lifestyles. From these health issues, early identification of the risk of individuals having the opportunity to suffer from DMt2 is needed as an early warning of DMt2. A prediction model was proposed in the results of this study using the fuzzy logic (FL) Sugeno technique as the primary basis for predicting DMt2 risk numbers. The prediction model uses four parameters (glucose, BMI, HDL, and systolic) considered relevant to DMt2 cases sourced from Kaggle's public dataset. A combination of triangular (trimf) and trapezium (trapmf) curves is used for the three linguistic levels of each parameter. The final model interprets each predicted outcome into three risk levels, including no risk (NR), risky (R), and very risky (VR). The results of the FL-Sugeno model verification and validation test are based on the application of all parameters used in the model with a prediction accuracy rate of 100%.
Keywords: Fuzzy Logic; Sugeno; Risk Suffering; Diabetes Mellitus
Abstrak
Diabetes Melitus (DM) adalah masalah kesehatan global. DM adalah penyakit tidak menular yang menyebar dengan cepat. Secara umum, diabetes melitus tipe 2 (DMt2) adalah jenis diabetes yang paling umum diderita oleh orang-orang yang disebabkan oleh gaya hidup yang tidak teratur. Dari masalah kesehatan tersebut, identifikasi dini risiko individu berkesempatan menderita DMt2 diperlukan sebagai peringatan dini DMt2. Model prediksi diusulkan dalam hasil penelitian ini dengan menggunakan teknik fuzzy logic (FL) Sugeno sebagai dasar utama untuk memprediksi angka risiko DMt2. Model prediksi menggunakan empat parameter (glukosa, BMI, HDL, dan sistolik) yang dianggap relevan dengan kasus DMt2 yang bersumber dari dataset publik Kaggle. Kombinasi kurva segitiga (trimf) dan trapesium (trapmf) digunakan untuk tiga tingkat linguistik dari setiap parameter. Model yang diusulkan menafsirkan setiap hasil yang diprediksi menjadi tiga tingkat risiko, termasuk tidak ada risiko (NR), berisiko (R), dan sangat berisiko (VR). Hasil pengujian verifikasi dan validasi model FL-Sugeno berdasarkan penerapan seluruh parameter yang digunakan pada model dengan tingkat akurasi prediksi sebesar 100%.
Kata kunci: Logika Fuzzy; Sugeno; Risiko menderita; Diabetes Melitus
References
U. I. Lestari, A. Y. Nadhiroh, and C. Novia, “Penerapan Metode K-Nearest Neighbor Untuk Sistem Pendukung Keputusan Identifikasi Penyakit Diabetes Melitus,” JATISI (Jurnal Teknik Informatika dan Sistem Informasi), vol. 8, no. 4, pp. 2071–2082, Dec. 2021, doi: 10.35957/jatisi.v8i4.1235.
J. Ginting, R. Ginting, and H. Hartono, “Deteksi Dan Prediksi Penyakit Diabetes Melitus Tipe 2 Menggunakan Machine Learning (Scooping Review),” Jurnal Keperawatan Priority, vol. 5, no. 2, pp. 93–105, Aug. 2022, doi: 10.34012/jukep.v5i2.2671.
S. W. Hovi, A. I. Hadiana, and F. R. Umbara, “Prediksi Penyakit Diabetes Menggunakan Algoritma Support Vector Machine (SVM),” Informatics and Digital Expert (INDEX), vol. 4, no. 1, pp. 40–45, Jul. 2022, doi: 10.36423/index.v4i1.895.
P. Piko, N. A. Werissa, S. Fiatal, J. Sandor, and R. Adany, “Impact of Genetic Factors on the Age of Onset for Type 2 Diabetes Mellitus in Addition to the Conventional Risk Factors,” J Pers Med, vol. 11, no. 6, pp. 1–17, Dec. 2020, doi: 10.3390/jpm11010006.
A. Izzo, E. Massimino, G. Riccardi, and G. Della Pepa, “A Narrative Review on Sarcopenia in Type 2 Diabetes Mellitus: Prevalence and Associated Factors,” Nutrients, vol. 13, no. 183, pp. 1–18, Jan. 2021, doi: 10.3390/nu13010183.
M. A. B. Khan, M. J. Hashim, J. K. King, R. D. Govender, H. Mustafa, and J. Al Kaabi, “Epidemiology of Type 2 Diabetes – Global Burden of Disease and Forecasted Trends,” J Epidemiol Glob Health, vol. 10, no. 1, p. 107, 2019, doi: 10.2991/jegh.k.191028.001.
R. Ohno et al., “Association of Body Mass Index and Its Change With Incident Diabetes Mellitus,” J Clin Endocrinol Metab, Jun. 2023, doi: 10.1210/clinem/dgad374.
K. R. Widiasari, I. M. K. Wijaya, and P. A. Suputra, “Diabetes Melitus Tipe 2: Faktor Risiko, Diagnosis, Dan Tatalaksana,” Ganesha Medicine, vol. 1, no. 2, p. 114, Dec. 2021, doi: 10.23887/gm.v1i2.40006.
G. I. Perdana and D. N. Utama, “The Multistage Fuzzy Logic-Based Decision Support Model to Determine the Salary of New Employees,” Journal of Computer Science, vol. 19, no. 7, pp. 812–824, 2023, doi: 10.3844/jcssp.2023.812.824.
L. A. Zadeh, “Fuzzy logic,” Computer (Long Beach Calif), vol. 21, no. 4, pp. 83–93, Apr. 1988, doi: 10.1109/2.53.
D. Kurniawan and D. N. Utama, “Decision Support Model using FIM Sugeno for Assessing the Academic Performance,” Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 1, pp. 605–611, Jan. 2021, doi: 10.25046/aj060165.
D. N. Utama and D. Kurniawan, “Fuzzy based Decision Support Model for Deciding the Students’ Academic Performance,” International Journal of Emerging Technology and Advanced Engineering, vol.
, no. 10, pp. 118–130, Oct. 2021, doi: 10.46338/ ijetae1021_15.
R. Yandri, Suharjito, D. N. Utama, and A. Zahra, “Evaluation Model for the Implementation of Information Technology Service Management using Fuzzy ITIL,” Procedia Comput Sci, vol. 157, pp. 290–297, 2019, doi: 10.1016/j.procs.2019.08.169.
G. K. Ramadhan and D. N. Utama, “Fuzzy Tsukamoto based Decision Support Model for Purchase Decision in Pharmacy Company,” International Journal of Recent Technology and Engineering (IJRTE), vol. 8, no. 4, pp. 3868–3874, Nov. 2019, doi: 10.35940/ijrte. D8243.118419.
D. N. Utama and N. Wibowo, “A Simple Fuzzy Decision Support Model for Determining the Indonesian Green Cities,” in IOP Conference Series: Earth and Environmental Science, Apr. 2023, p. 012058. doi: 10.1088/1755-1315/1169/1/012058.
R. Furqan Ramadhan and K. Eliyen, “Implementasi Metode Fuzzy Sugeno Pada Pemodelan Pertumbuhan Tanaman Kedelai Dengan Variasi Dosis Pupuk,” Jurnal Mnemonic, vol. 6, no. 1, pp. 28–34, May 2023, doi: 10.36040/mnemonic.v6i1.5831.
C. Maisyarah, E. Haryatmi, R. Y. Fajriatifah, and Y. H. Puspita, “Prediksi Penyakit Diabetes menggunakan Algoritma Artificial Neural Network,” Jurnal Data Science & Informatika, vol. 2, no. 1, pp. 46–52, 2022.
D. Abdianto Nggego, R. R. Taufik Bau, and N. Patawaran, “FA-KNN: Hybrid Algoritma Untuk Klasifikasi Penyakit Diabetes Melitus,” MJRICT : Musamus Journal Of Research Information and Communication Technology, vol. 5, no. 2, pp. 71–80, 2023, [Online]. Available: https://ejournal.unmus.ac.id/index.php/mjrict
Q. R. Cahyani, M. J. Finandi, J. Rianti, D. L. Arianti, A. D. Pratama, and Putra, “Prediksi Risiko Penyakit Diabetes Menggunakan Algoritma Regresi Logistik Diabetes Risk Prediction Using Logistic Regression Algorithm,” JOMLAI: Journal of Machine Learning and Artificial Intelligence, vol. 1, no. 2, pp. 2828–9099, 2022, doi: 10.55123/jomlai.v1i2.598.
R. Putri Fadhillah et al., “Klasifikasi Penyakit Diabetes Mellitus Berdasarkan Faktor-Faktor Penyebab Diabetes Menggunakan Algoritma C4.5,” JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), vol. 7, no. 4, pp. 1265–1270, 2022, [Online]. Available: www.kaggle.com
G. I. Perdana, M. D. Devanda, and D. N. Utama, “Fuzzy Based Butterfly Life Cycle Algorithm for Measuring Company’s Growth Performance,” Journal of Advances in Information Technology, vol. 14, no. 1, pp. 1–6, 2023, doi: 10.12720/jait.14.1.1-6.
D. N. Utama, L. I. Lazuardi, H. A. Qadrya, B. M. Caroline, T. Renanda, and A. P. Sari, “Worth eat: An intelligent application for restaurant recommendation based on customer preference (Case study: Five types of restaurant in Tangerang Selatan region, Indonesia),” in 2017 5th International Conference on Information and Communication Technology (ICoIC7), IEEE, May 2017, pp. 1–4. doi: 10.1109/ICoICT.2017.8074654.
S. Kodama et al., “Predictive ability of current machine learning algorithms for type 2 diabetes mellitus: A meta‐analysis,” J Diabetes Investig, vol. 13, no. 5, pp. 900–908, May 2022, doi: 10.1111/jdi.13736.
How To Cite This :
Refbacks
- There are currently no refbacks.
