Nowadays, Alzheimer’s Disease (AD) is a brain-related illness that is chronic, long-lasting, and incurable. AD is considered the primary source of dementia in elderly people. A timely and accurate diagnosis of AD has the potential to enhance greatly patient assistance and treatment. Our study intends to build a high performing Machine Learning (ML) model to assist doctors in early AD detection and provide efficient treatments to prevent the deterioration of patient’s health. Using a public AD dataset, we developed numerous ML classifiers, namely, Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbors (KNN) and Decision Tree (DT), leveraging K-Fold cross-validation to assess the performance and to help ensuring generalization. Since DT algorithm achieved the highest performance compared to the other classifiers, we optimized it using Grid Search method. Accordingly, the optimized DT outperformed the other models with 95% accuracy, 95% precision, 92% recall, 93% F1-score and 93% average precision. Thus, our study shows the power of ML classifiers to achieve an effective and accurate AD diagnosis, which certainly has the potential to become a reliable tool for assisting clinicians in timely AD detection.