Prediksi Diabetes Berdasarkan Faktor Medis Pasien Menggunakan Algoritma Decision Tree

Ahmad Reza (Universitas Pamulang)
Amar Naufal Al-kharits (Universitas Pamulang)
Muhamad Bustomi (Universitas Pamulang)
Nazar Maulana (Universitas Pamulang)
Taupik Abdul Rahman (Universitas Pamulang)

Journal of Information Technology and Informatics Engineering
Vol 1 No 1 (2025): Journal of Information Technology and Informatics Engineering (JITIE)

Early detection of diabetes risk is crucial to prevent severe complications. This study develops a predictive model for diabetes using the Decision Tree algorithm based on patient medical data. The dataset consists of 768 records with eight health-related attributes, of which 99 labeled instances are used to train the model. The process includes data cleaning, target attribute assignment, and model construction using RapidMiner. Results indicate that variables such as age and glucose levels significantly influence diabetes classification. Although the initial findings show promising potential, further validation with larger and more balanced datasets is needed to improve the model's accuracy.