Alzheimer’s disease is an essential process that negatively affects the quality of life. Analysis of the dataset used in this study reveals significant differences in the performance of different machine learning models. Among the classifiers evaluated, the XGBoost model emerged as the most effective, achieving consistently high performance across key metrics. Specifically, XGBoost demonstrated F1 scores of 0.93 or higher, along with an impressive ROC AUC score of 0.97 and an overall accuracy of 0.96. These results indicate that XGBoost is well-suited for accurately classifying instances in the Alzheimer’s dataset. In contrast, the Gaussian Naive Bayes model showed the lowest performance across all evaluated metrics, suggesting that it is not an appropriate choice for this dataset. The comparative analysis is conducted following a structured methodology, which includes essential steps such as data pre-processing, applying multiple machine learning algorithms, hyperparameter tuning using grid search, and a comprehensive comparison of the models’ predictive outcomes. This systematic approach highlights the importance of selecting appropriate algorithms for classifying Alzheimer’s disease. The superior performance of the XGBoost model underscores its potential as a robust tool for this purpose, making it a recommended choice for future studies and applications in the field.