Alzheimer's Disease Prediction and Classification Using Machine Learning Models

This study addresses the critical challenge of early Alzheimer’s disease (AD) detection through machine learning algorithms, leveraging a dataset of 6400 preprocessed MRI images. We explore several models, including Support Vector Machines (SVM), Linear Discriminant Analysis (LDA) and Convolutional Neural Networks (CNNs) integrated with VGG16 and EfficientNetB0 architectures. Among these, both CNN models demonstrate exceptional performance, achieving an accuracy of 96% in AD classification. The results underscore the efficacy of deep learning models, particularly CNNs, in accurately distinguishing between various stages of Alzheimer’s disease. This study highlights the potential of these models to significantly enhance early AD detection, offering a reliable tool for clinical applications.