Early detection of alzheimer's disease using predictive k-nn instance based approach and t-test method

Abstract

Nowadays various neural network algorithms are used in the classification of clinical data for human conditions such as Alzheimer’s disease, which can extract low-to-high-level features. Classification of clinical data for Alzheimer’s disease has always been challenging as currently there is no clinical test for Alzheimer’s disease. Doctors diagnose it by conducting assessments of patients’ cognitive decline. But it’s particularly difficult for them to identify mild cognitive impairment at an early stage when symptoms are less obvious. Also, it is difficult to predict whether patients will develop Alzheimer’s disease or not. The accurate diagnosis of Alzheimer's disease in the early stage is important in order to take preventive measures and to reduce the severity and progression before irreversible brain damages occur. The effectiveness of abnormality detection depends on the accuracy and robustness of the algorithm used. Different machine learning techniques with different levels of sensitivity, efficiency, and accuracy have been developed. In this paper, a feature selection using T-Test method for joint regression and classification via instance based k-Nearest Neighbor classifier is proposed for Alzheimer's disease detection. Also, we compare the accuracy measures and performance of the proposed method with existing techniques in Alzheimer’s disease detection. The new method gives a better accuracy results compared to conventional methods.