We proposed a novel computational approach for modeling the normal elderly subjects's brain age by connectivity analyses of networks of the brain.
Principal component analysis (PCA) is applied to reduce the redundancy in network topological parameters.
BP artificial neural network (BPANN) is improved by hybrid genetic algorithm (GA) and Levenberg–Marquardt (LM) algorithm to model the relation among principal components (PCs) and brain age.
The method has shown good performance for old cohort with limited samples.