Combining multiple data sources can provide a comprehensive approach to Alzheimer’s disease (AD) staging analysis. This study presents a deep learning (DL) and machine learning (ML) approach for Alzheimer’s disease (AD) diagnosis using MRI images and clinical test data. Traditional MRI analysis struggles to distinguish normal aging from AD, whereas DL models offer superior accuracy. We fine-tuned EfficientNet-B0 and developed a Convolutional Neural Network (CNN) model, complemented by ML classifiers, including Random Forest (RF), Gradient Boosting (GB), Decision Tree (DT), and an ensemble Voting Classifier. Trained on the Open Access Series of Imaging Studies (OASIS) dataset with 80,000 MRI images, our model integrates image and clinical data to improve classification accuracy. Explainable AI (XAI) techniques, Gradient-weighted Class Activation Mapping (Grad-CAM) and Local Interpretable Model-agnostic Explanations (LIME), were applied for interpretability. Our ensemble model achieved a classification accuracy of up to 99.9%.