Statistical Approaches for the Study of Cognitive and Brain Aging

Abstract

Neuroimaging studies of cognitive and brain aging often yield massive datasets that create many analytic and statistical challenges. In this paper, we discuss and address several limitations in the existing work. (1) Linear models are often used to model the age effects on neuroimaging markers, which may be inadequate in capturing the potential nonlinear age effects. (2) Marginal correlations are often used in brain network analysis, which are not efficient in characterizing a complex brain network. (3) Due to the challenge of high-dimensionality, only a small subset of the regional neuroimaging markers is considered in a prediction model, which could miss important regional markers. To overcome those obstacles, we introduce several advanced statistical methods for analyzing data from cognitive and brain aging studies. Specifically, we introduce semiparametric models for modeling age effects, graphical models for brain network analysis, and penalized regression methods for selecting the most important markers in predicting cognitive outcomes. We illustrate these methods using the healthy aging data from the Active Brain Study.

Keywords: functional connectivity; graphical model; penalized regression methods; semiparametric model; structural covariance.

Figure 1

Age trajectories of the normalized lateral ventricle and putamen volumes using the semiparametric model, loess fit, linear, and quadratic regression models.

Figure 2

Cortical thickness based cortical network. The top two patterns are Pearson's correlation map (left) and partial correlation map (from the Glasso; right) for the cortical network. The bottom two patterns are adjacency matrix of the undirected graph (from the node-wise regression; left) and graphical map of the frontal lobe (right).

Figure 3

Solution paths from the penalized regression with lasso penalty.