<![CDATA[This study examines the use of machine learning models to classify diabetes mellitus status based on laboratory test data. The dataset consists of 484 laboratory test results with 10 clinical parameters, which were used as the main input for model development. Three algorithms, Random Forest, Extreme Gradient Boosting, and Light Gradient Boosting Machine, were compared by applying several resampling techniques and hyperparameter tuning using Optuna to address class imbalance and improve overall model performance. The results show that each algorithm responded differently to the applied resampling methods and tuning strategies, indicating that model performance is influenced by these approaches. Among the evaluated models, Random Forest combined with Synthetic Minority Oversampling Technique and hyperparameter optimization achieved the best performance, with an accuracy of 72.60% and an area under the receiver operating characteristic curve of 76.74%. This performance indicates a moderate ability to distinguish between diabetes and non-diabetes cases based on the available laboratory parameters. Overall, the findings suggest that machine learning can be considered as a potential tool to support clinical decision making, especially when using structured laboratory data. However, given that the performance is still not optimal, further improvement, validation, and exploration of additional data are necessary before considering its implementation in real clinical settings.]]>
