Introduction: Type 2 diabetes mellitus (T2DM) is a chronic metabolic disease that causes serious health problems worldwide. Multiple risk factors contribute to the development of this disease. Recently, researchers have used artificial intelligence and machine learning (ML) methods to identify these risk factors. This study aims to evaluate the risk factors for T2DM using ML methods.
Materials and Methods: This analytical study was conducted over a 2-month period. Data were collected through face-to-face interviews using a personal information form. The obtained data were analyzed using different ML models and performance parameters such as F1 score, accuracy (ACC), and area under the curve (AUC), which represents the area under the receiver operating characteristic curve.
Results: In this study, the most important risk factors for T2DM were identified as age, gender, high blood pressure, genetic predisposition, and education status. Moreover, seven different ML models were analyzed using F1 score, ACC, and AUC parameters, and support vector machine, random forest (RF), and logistic regression (LR) models provided the highest performance.
Discussion and Conclusion: Accurate classification of T2DM risk factors is important for disease prevention and risk assessment in clinical practice. The results suggest that RF or LR models may affect populations with different sociocultural characteristics.