Predicting Alzheimer’s Disease Progression through Machine Learning Algorithms
M. Bharath, S. Gowtham, S Vedanth, Ashwini Kodipalli, Trupthi Rao, B R Rohini
Abstract
This study revolves around the crucial task of early Alzheimer's disease (AD) detection using machine learning algorithms. Leveraging a dataset of 6400 preprocessed MRI images, the research rigorously evaluates a spectrum of models, encompassing Support Vector Machines (SVM) with diverse kernels, multidimensional Linear Discriminant Analysis (LDA), comprehensive Principal Component Analysis (PCA), and Convolutional Neural Networks (CNN) integrated within the architecture of EfficientNetB0. Significantly, the SVM model, utilizing a linear kernel, emerges as a standout performer, achieving an impressive accuracy of 98% in AD detection and a remarkable 98.7% in AD classification. These findings distinctly underscore the efficacy of SVM models, particularly when harnessed with linear kernels, as potent tools for precise AD detection and classification.