Noviandi Noviandi


Diabetes mellitus (DM) is a chronic disease that causes death. Uncontrolled, identified and unpredictable increases in blood sugar quickly lead to complications. In data mining, many have used approaches to predict the disease, one of which is the use of algortima decison tree C4.5. The motive of this study is to build a predictive model of the likelihood of diabetic patients with the C4.5 algorithm and see the akurasi of the resulting model. Prediction models are made using Pima Indians Diabetes Databases (PPID) data sourced from the UCI Machine Learning Repository. Prediction model with C4.5 decision tree algorithm has 70.32% akurasi by producing 9 rules, with the number of classes “not” as many as 4 rules and classes “yes” as many as 5 rule to predict DM disease.

Teks Lengkap:

PDF (English)


Perveen S, Shahbaz M, Guergachi A, Keshavjee K. Performance Analysis of Data Mining Classification Techniques to Predict Diabetes. Procedia Comput Sci [Internet]. 2016;82(March):115–21. Available from: .016

Wu H, Yang S, Huang Z, He J, Wang X. Type 2 diabetes mellitus prediction model based on data mining. Informatics Med Unlocked [Internet]. 2018;10(August 2017):100–7. Available from: 6

Sisodia D, Sisodia DS. Prediction of Diabetes using Classification Algorithms. Procedia Comput Sci [Internet]. 2018;132(Iccids):1578–85. Available from: 22

Rohman A, Suhartono V, Supriyanto C. Penerapan algoritma c4.5 berbasis. 2017;13:13–9.

Choubey D, Paul S, Kumar S, Kumar S. Classification of Pima indian diabetes dataset using naive bayes with genetic algorithm as an attribute selection. Commun Comput Syst [Internet]. 2017;451–5. Available from: 9781315364094-82

Santosa B, Umam A. Data Mining dan Big Data Analytics: Teori dan Implementasi Menggunakan Python & Apache Spark. 1st ed. Isa, editor. Yogyakarta: Penebar Media Pustaka; 2018.

Mochammad Yusa, Utami E, Luthfi ET. Evaluasi Performa Algoritma Klasifikasi Decision tree ID3 , C4,5 dan Cart pada Dataset Readmisi Pasien Diabetes. InfoSys J. 2016;4(1):23–34.


  • Saat ini tidak ada refbacks.