Alzheimer’s Disease Detection Using m-Random Forest Algorithm with Optimum Features Extraction

Abstract

Alzheimer’s disease is basically a neurodegenerative disease that is impossible to fully be cured. It is one kind of dementia that occurs along with aging. It not only damages human memory but also affects behavior, movement, and responses to external stimulations. Moreover, AD breaks the connections of the neurons and spoils the brain cells. The worst sequel of AD is death. Though it can not be properly cured, pre-detection can make an early treatment that might reduce the symptoms. AD can also be detected by analyzing brain images captured from several imaging techniques like Electroencephalogram, Magnetic Resonance Imaging, etc with the aid of machine learning algorithms. Machine learning algorithms are highly successful techniques in the case of processing and classifying the images to determine the stages of AD. In this paper, we propose an upgraded machine learning algorithm named Modified Random Forest (m-RF) to individualize between normal people and people with the risk of having Alzheimer’s disease. We have achieved an accuracy of 96.43% that is far better than other algorithms like Support Vector Machine, Adaptive Boosting, K-Nearest Neighbors, etc.