Group functional connectivity magnetic resonance imaging (fcMRI) studies have documented reliable changes in human functional brain maturity over development. Here we show that support vector machine-based multivariate pattern analysis extracts sufficient information from fcMRI data to make accurate predictions about individuals’ brain maturity across development. The use of only 5 minutes of resting-state fcMRI data from 238 scans of typically developing volunteers (ages 7 to 30 years) allowed prediction of individual brain maturity as a functional connectivity maturation index. The resultant functional maturation curve accounted for 55% of the sample variance and followed a nonlinear asymptotic growth curve shape. The greatest relative contribution to predicting individual brain maturity was made by the weakening of short-range functional connections between the adult brain’s major functional networks.
Figure (click to enlarge): fcMVPA (functional connectivity multivariate pattern analysis) connection and region weights. The functional connections driving the SVR (support vector machines regression) brain maturity predictor are displayed on a surface rendering of the brain. The thicknesses of the 156 consensus functional connections scale with their weights. Connections positively correlated with age are shown in orange, whereas connections negatively correlated with age are shown in light green. Also displayed are the 160 ROIs (regions of interest) scaled by their weights (1/2 sum of the weights of all the connections to and from that ROI). The ROIs are color-coded according to the adult rs-fcMRI (resting state functional connectivity MRI networks) (cingulo-opercular, black; frontoparietal, yellow; default, red; sensorimotor, cyan; occipital, green; and cerebellum, dark blue).