Feature selection using efficient fusion of Fisher Score and greedy searching for Alzheimer’s classification

Abstract

Alzheimer’s disease is one of the deadly progressive neurodegenerative diseases among aged populations. But, the progression of the disease can be reduced by proper treatment of the disease during the early stages of cognitive impairment. The main objective of this study is to implement an efficient feature selection algorithm for the detection of Alzheimer’s patients at the baseline stage itself using multimodal data. In this paper, we propose an efficient fusion of Fisher Score ranking and greedy searching heuristic as feature selection criteria for Alzheimer’s prediction. The proposed algorithm provides a Balanced Classification Accuracy of 90% and 91% and Multi Area Under the Curve of 0.97, 0.98 using Support Vector Machine, K-Nearest Neighbor respectively for classifying Normal Controls, Mild Cognitive Impairment, and Alzheimer’s patients on Alzheimer’s Disease Neuroimaging Initiative-TADPOLE dataset at baseline visit itself. Moreover, the proposed algorithm also provides better sensitivity, specificity of 84%, 82.5% using Support Vector Machine, K-Nearest Neighbor for binary classification of Mild Cognitive Impairment, and Alzheimer’s patients on the Australian Imaging and Biomarker Lifestyle dataset also. Our results indicate that the proposed methodology with efficient feature selection is promising and can outperform the state of the art methods for early detection of Alzheimer’s.