Alzheimer’s Disease (AD) is a progressive neurodegenerative disorder that affects cognitive functions, leading to memory loss and impairment [8]. Early detection is crucial for effective intervention, yet traditional diagnostic methods remain limited [12]. This research presents a comparative analysis of multiple machine learning approaches for automated classification of AD stages. Utilizing MRI images from the OASIS dataset, the study evaluates Convolutional Neural Networks (CNNs), Convolutional Recurrent Neural Networks (CRNNs), Naive Bayes, K-Means clustering, Transfer Learning with DenseNet, and ResNet [1][5][6]. Experimental results demonstrate varying performance across models, highlighting their strengths and weaknesses [2][3]. This comparative analysis provides insights into the suitability of different architectures for real-time Alzheimer’s diagnosis [4][7].