Deteksi Dini Diabetes Mellitus Tipe 2 Pada Usia Dewasa Muda Menggunakan Algoritma Decision Tree - C4.5
Abstract
The shift in the epidemiological pattern of metabolic diseases is indicated by the increasing incidence of Type 2 Diabetes Mellitus (T2DM) in young individuals. The increasing incidence of glucose metabolism disorders is largely due to changes in modern lifestyles, such as high calorie intake and lack of physical activity. Early detection during productive age is crucial to prevent long-term problems. Based on clinical data, this study created a model for early detection of type 2 diabetes using the Decision Tree C4.5 algorithm. The dataset was filtered for people aged between 20 and 40 years after being obtained from Kaggle. The study phase included data pre-processing, data splitting for testing and training, and model development using entropy and information gain. Accuracy, precision, recall, F1-score, and ROC-AUC were used to evaluate the model. The accuracy was 92.4% and the ROC-AUC was 0.938. The completed model can be used as a data-driven interpretive health screening tool.
Keywords: Early diagnosis; Decision Tree algorithm; C4.5; Classification model
Abstrak
Pergeseran pola epidemiologi penyakit metabolik ditunjukkan oleh meningkatnya kejadian Diabetes Melitus Tipe 2 (T2DM) pada individu muda. Meningkatnya kejadian gangguan metabolisme glukosa sebagian besar disebabkan oleh perubahan gaya hidup modern, seperti pola asupan kalori tinggi dan kurangnya aktivitas fisik. Deteksi dini pada usia produktif sangat penting untuk mencegah masalah jangka panjang. Berdasarkan data klinis, penelitian ini menciptakan model deteksi dini diabetes tipe 2 menggunakan algoritma Decision Tree C4.5. Dataset difilter untuk orang berusia antara 20 dan 40 tahun setelah diperoleh dari Kaggle. Fase studi meliputi pra-pemrosesan data, pemisahan data untuk pengujian dan pelatihan, serta pengembangan model menggunakan entropi dan perolehan informasi. Akurasi, presisi, recall, F1-score, dan ROC-AUC digunakan untuk menilai model tersebut. Akurasinya adalah 92,4% dan ROC-AUC adalah 0,938. Model yang telah selesai dapat digunakan sebagai alat skrining kesehatan interpretatif berbasis data.
Keywords
References
A. K. Jaggi, A. Sharma, N. Sharma, R. Singh, and P. S. Chakraborty, “Diabetes Prediction Using Machine Learning,” Lecture Notes in Networks and Systems, vol. 185 LNNS, no. 09, pp. 383–392, 2021, doi: 10.1007/978-981-33-6081-5_34.
W. H. O. G. Report, Global Report on Diabetes, vol. 978. 2016. [Online]. Available: http://www.who.int/about/licensing/copyright_form/index.html%0Ahttp://www.who.int/about/licensing/copyright_form/index.html%0Ahttps://apps.who.int/iris/handle/10665/204871%0Ahttp://www.who.int/about/licensing/
IDF, “IDF Diabetes Atlas. In IDF Diabetes Atlas,” International Diabetes Federation, vol. 11th editi, p. 131, 2025, [Online]. Available: https://www.idf.org/aboutdiabetes/type-2-diabetes.html
F. A. Ahda and M. Zainuddin, “Prediksi Kepuasan Pelayanan Perpustakaan Menggunakan Algoritma Decision Tree (C4.5),” Jurnal Teknologi Informasi, vol. 10, pp. 143–150, 2019, doi: 10.36382/jti-tki.v10i2.368.
A. Iyer, J. S, and R. Sumbaly, “Diagnosis of Diabetes Using Classification Mining Techniques,” International Journal of Data Mining & Knowledge Management Process, vol. 5, no. 1, pp. 01–14, 2015, doi: 10.5121/ijdkp.2015.5101.
Y. Nuryamin and F. Risyda, “Analisis Prediksi Penyakit Diabetes Menggunakan Metode Decision Tree C4.5 Dan Naive Bayes,” Jurnal Sistem Informasi Universitas Suryadarma, vol. 12, no. 2, pp. 234–242, 2014, doi: 10.35968/jsi.v12i2.1549.
D. A. Sulistyo, D. D. Prasetya, F. A. Ahda, and A. P. Wibawa, “Pivoted Low Resource Multilingual Translation with NER Optimization,” ACM Transactions on Asian and Low-Resource Language Information Processing, vol. 24, no. 5, 2025, doi: 10.1145/3727876.
Daw Khin Po, “Simulation of Process Scheduling Algorithms,” International Journal of Trend in Scientific Research and Development, vol. 3, no. 4, pp. 1629–1632, 2019, doi: https://doi.org/10.31142/ijtsrd25124.
F. A. Ahda, A. P. Wibawa, D. D. Prasetya, D. A. Sulistyo, and A. Nafalski, “Minangkabau Language Stemming: A New Approach with Modified Enhanced Confix Stripping,” Jurnal RESTI, vol. 9, no. 3, pp. 677–687, 2025, doi: 10.29207/resti.v9i3.6511.
S. Liu, “Diabetes Prediction by KNN, SVM, Random Forest and XGBoost,” Highlights in Science, Engineering and Technology, vol. 72, pp. 1113–1120, 2023, doi: 10.54097/8h8dff76.
Y. Tian, “Machine Learning Models for Diabetes Prediction: Logistic Regression, SVM, Random Forest, and Neural Networks,” Applied and Computational Engineering, vol. 211, no. 1, pp. 174–179, 2025, doi: 10.54254/2755-2721/2026.tj30648.
H. Setiani, M. N. Arridho, and S. Supriyanto, “Early Detection of Type 2 Diabetes Using C4.5 Decision Tree Algorithm on Clinical Health Records,” Journal of Applied Informatics and Computing, vol. 9, no. 4, pp. 1663–1669, 2025, doi: 10.30871/jaic.v9i4.10190.
F. Almu’iini Ahda, A. Prasetya Wibawa, D. Prasetya, and A. Sulistyo, “International Journal On Informatics Visualization journal homepage : www.joiv.org/index.php/joiv International Journal On Informatics Visualization Comparison of Adam Optimization and RMSprop in Minangkabau-Indonesian Bidirectional Translation with Neura,” vol. 8, no. March, pp. 231–238, 2024, [Online]. Available: www.joiv.org/index.php/joiv
A. W. Wicaksono and T. Setiadi, “Penerapan Klasifikasi Decision Tree (C4.5) untuk Memprediksi Kelulusan Siswa Sekolah Dasar di Kecamatan Juai,” Format : Jurnal Ilmiah Teknik Informatika, vol. 12, no. 2, p. 151, 2023, doi: 10.22441/format.2023.v12.i2.008.
T. H. Sinaga, A. Wanto, I. Gunawan, and Z. Masruro, “Journal of Computer Networks , Architecture and High Performance Computing Implementation of Data Mining Using C4 . 5 Algorithm on Customer Satisfaction in Tirta Lihou PDAM Journal of Computer Networks , Architecture and High Performance Computing,” vol. 3, no. 1, pp. 9–20, 2021.
Fatmawati, “Perbandingan Algoritma Klasifikasi Data Mining Model C4.5 Dan Naive Bayes Untuk Prediksi Penyakit Diabetes,” Jurnal Techno Nusa Mandiri, vol. XIII, no. 1, p. 50, 2016.
P. B. Khokhar, V. Pentangelo, F. Palomba, and C. Gravino, “Towards Transparent and Accurate Diabetes Prediction Using Machine Learning and Explainable Artificial Intelligence,” 2025, [Online]. Available: http://arxiv.org/abs/2501.18071
H. Afandi, D. A. Sulistyo, and S. A. Malang, “Sistem Pakar Untuk Diagnosa Hama dan Penyakit Pada Bunga Krisan Menggunakan Forward Chaining,” vol. 13, no. 2, pp. 101–114, 2019.
H. K. Ashwin, K. K. Poojari, S. R. Rahul, and S. C. I. L, “Design of an automobile instrument cluster using CAN protocol,” no. June, pp. 5722–5725, 2020.
V. Venecia, G. Hoendarto, & T. Darmanto, “Design of Diabetes Prediction Interface Using E-ss and Classification Tree Algorithm. Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi, vol. 14, no. 3, pp. 1856-1867, 2025.
How To Cite This :
Refbacks
- There are currently no refbacks.
