Abstract

One of the most prevalent diseases in the world is Alzheimer’s (AD). It is a neurological condition that can lead to cognitive decline and memory loss. Both the senior population and the prevalence of diseases affecting them have dramatically increased in recent years. It is critical to categorize the progression of Alzheimer’s disease. Alzheimer's disease (AD) is a complicated neurological ailment that progresses in different ways for each individual. In this study, we present a novel approach to personalised Alzheimer's disease progression prediction using machine learning techniques. Our goal is to create a model that can forecast the stage of the condition for specific individuals and classify them into one of four categories: Normal, Mild, Average, or Critical. Our method uses Convolutional Neural Networks (CNN) to extract characteristics from various MRI scans, capturing complex patterns in Alzheimer's progression. The CNN is extensively trained on a diverse dataset. Traditional classifiers such as Support Vector Machines (SVM) and Decision Trees supplement the CNN, improving the classification process. Furthermore, ensemble learning, specifically majority voting, harmonises predictions from CNN, SVM, and Decision Trees, increasing accuracy by using their individual strengths to predict Alzheimer's disease development.