<![CDATA[Diabetes Mellitus is a chronic disease with an increasing prevalence worldwide and poses serious health risks if not detected early. Early prediction of diabetes is crucial to support preventive actions and improve healthcare decision-making. This study aims to analyze and compare the performance of several machine learning classification algorithms in predicting Diabetes Mellitus based on clinical data. The dataset used in this research is the Pima Indians Diabetes dataset, which consists of medical attributes such as glucose level, blood pressure, insulin, body mass index, and age. Data preprocessing was conducted to handle missing values and improve data quality. Three classification algorithms, namely Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbor (KNN), were implemented and evaluated using k-fold cross-validation. The performance of each algorithm was measured using accuracy, precision, recall, F1-score, and confusion matrix. The experimental results show that the Random Forest algorithm achieved the highest performance compared to SVM and KNN, with superior accuracy and more balanced classification results. This indicates that ensemble-based methods are more effective in handling medical data with complex patterns. In conclusion, machine learning algorithms can be effectively applied to predict Diabetes Mellitus, and Random Forest is recommended as the most suitable algorithm for this dataset. The results of this study are expected to contribute to the development of intelligent decision support systems in the healthcare domain. Keywords: Classification; Diabetes Mellitus; Machine Learning; Random Forest; Support Vector Machine; K-Nearest Neighbor]]>
Copyrights © 2025
