Application of Logistic Regression Method for Predicting Diabetes Mellitus

Dendi Pratama Riawan (Faletehan University)
Dede Brahma Arianto (Faletehan University)

Ambidextrous : Journal of Innovation, Efficiency and Technology in Organization
Vol. 4 No. 03 (2026): Ambidextrous: Journal of Innovation, Efficiency and Technology in Organization

Diabetes is a chronic disease that requires early detection to prevent complications. This study refers to the analysis of diabetes prediction using the Logistic Regression algorithm. The data used comes from the open dataset platform, namely Kaggle, including health attributes such as Pregnancies, Glucose, Blood Pressure, Skin Thickness, Insulin, BMI, Age, Outcome. The process in this study includes data cleaning, model development, and prediction. Model assessment was carried out using Confusion Matrix to calculate accuracy, Precision, Recall, and F1-Score, which is supported by ROC Curve analysis. The findings in this study show that the Logistic Regression model achieved an accuracy level of 75.32% and an AUC of 0.8232, indicating that the classification performance is quite good in predicting diabetes conditions