Diagnosing Alzheimer’s Disease Severity: A Comparative Study of Deep Learning Algorithms

Abstract

Alzheimer’s disease emerges as a profoundly distressing neurological condition affecting older individuals, pre-ending itself as an insufficiently addressed and often overlooked ailment that poses a growing concern for public health. In the past decade, there has been a notable surge in endeavors aimed at unraveling the disease’s origins and devising pharmacological interventions. Recent advancements encompass enhanced clinical diagnostic criteria and refined approaches for managing cognitive impairments and behavioral challenges. The pursuit of symptomatic relief primarily centered on cholinergic therapy has been subject to rigorous scrutiny through randomized, double-blind, placebo-controlled studies assessing cognitive function, daily activities, and behavioral aspects. This research delves into the utilization of diverse algorithms for the classification of Alzheimer’s disease severity, employing CNN, DenseNet, VGG19, and ensemble learning approaches. The obtained accuracy scores underscore the supremacy of the Ensemble model, surpassing the performance of the other models with an impressive accuracy level of 94%.