Paper Contents
Abstract
Alzheimer's disease, which falls under the category of dementia, is also known as senile dementia. Memory loss and difficulty performing simple activities cognitively are the most common symptoms. Despite the disease's prevalence, therapy is sometimes delayed because there aren't any obvious biomarkers. There are extremely few patients that undergo a proper diagnosis and obtain the right treatment. Many folks typically acquire a diagnosis when it's too late. Since there is no known treatment for this illness, the only ways to delay its onset are early detection and prevention action. When used to examine the disease's biomarkers, both machine learning and deep neural network algorithms are effective. The likelihood of underlying AD is determined by biomarkers like as plaques and tangles in the grey matter as well as historical trends noticed by the algorithm. Both numerical and neuroimaging data can be used for the analysis. SVM, Random Forest, and Regression are examples of machine learning algorithms that use numerical data to represent the percentage change in the hippocampus and entorhinal cortex. CNN (convolutional neural network), a deep learning algorithm, uses TW1 images from MRI scans to classify Alzheimer's disease into mild, moderate, and severe forms
Copyright
Copyright © 2023 P.vineela. This is an open access article distributed under the Creative Commons Attribution License.
