An Algorithmic Approach for Alzheimer’s Disease detection from Non-Image Data

Abstract

In this paper an exploratory data analysis model is proposed to create a suitable reference knowledge base from Alzheimer’s disease dataset. The knowledge of the reference base is expressed in terms of zones with each zone carrying a weightage factor. The learnt knowledge is used to quantify the similarity of a test sample with respect to the demented class. Evaluation of the model on OASIS longitudinal database of Alzheimer subjects shows that the designed model successfully explores the data set for useful information and assigns test samples to either non-demented or demented class with non-overlapping and measurable similarity indices.