Linking structural and functional changes during aging using multilayer brain network analysis

Abstract

Brain structure and function are intimately linked, however this association remains poorly understood and the complexity of this relationship has remained understudied. Healthy aging is characterised by heterogenous levels of structural integrity changes that influence functional network dynamics. Here, we use the multilayer brain network analysis on structural (diffusion weighted imaging) and functional (magnetoencephalography) data from the Cam-CAN database. We found that the level of similarity of connectivity patterns between brain structure and function in the parietal and temporal regions (alpha frequency band) is associated with cognitive performance in healthy older individuals. These results highlight the impact of structural connectivity changes on the reorganisation of functional connectivity associated with the preservation of cognitive function, and provide a mechanistic understanding of the concepts of brain maintenance and compensation with aging. Investigation of the link between structure and function could thus represent a new marker of individual variability, and of pathological changes.

Fig. 1. Overview of the creation of the multiplex network from MEG and DWI data.

This multiplex network was built with two layers: one representing functional connectivity (FC) from MEG data, either PLV or TE data; the other layer representing structural connectivity (SC) from DWI (anisotropic fraction) data, i.e., FA data. MEG magnetoencephalography, DWI diffusion-weighted imaging, PLV phase locking value, TE transfer entropy, FC functional connectivity, SC structural connectivity.

Fig. 2. Multiplex participation coefficient level differences between young and old groups and association with cognition.

a Distribution of the young and old groups in the left inferior temporal region (t-test) for the multiplex participation coefficient in the alpha frequency band for the measure of synchrony (PLV) and positive association between this level of multiplex participation coefficient and MMSE score. b Distribution of the young and old groups in the right parietal region (t-test) for the multiplex participation coefficient in the alpha frequency band for the measure of synchrony (PLV) and positive association between this level of multiplex participation coefficient and MMSE score in older adults. The level of education was controlled as a covariate. All results were adjusted for multiple comparisons using FDR corrections at q < 0.05. n = 46 participants per group. The black vertical line represents the standard error of the mean. *p < 0.05 **p < 0.01.

Fig. 3. Multiplex participation coefficient level differences between young and older subgroups and association with cognition.

a Distribution of young adults and older adults’ subgroups for the multiplex participation coefficient in the left temporal region for the measure of synchrony (PLV) in the alpha frequency band. The positive association between participation in the left temporal region and VSTM scores for the Low participation subgroup (regression test; no association with cognition for the High participation older subgroup). b Distribution of the young adults and older adults’ subgroups for the multiplex participation coefficient in the right parietal region in the alpha frequency band. The positive association between participation in the right parietal region and VSTM scores for the Low participation older subgroup (regression test; no association with cognition for the high participation older subgroup). c Distribution of young adults and older adults’ subgroups for the multiplex participation coefficient in the right parietal region in the alpha frequency band for the measure of directionality (TE). The positive association between the participation of the right parietal region and VSTM scores for the Low participation subgroup (regression test; negative association with cognition for the High participation older subgroup: r = −0.491, p = 0.033). The level of education was controlled as a covariate. All results were adjusted for multiple comparisons using FDR corrections at q < 0.05. n = 46 participants per group. The black vertical line represents the standard error of the mean. *p < 0.05; **p < 0.01; ***p < 0.001.

Fig. 4. Multiplex participation coefficient level differences between young and older subgroups and association with cognition.

a Increased inward directionality (i.e., directed towards the right parietal region) in older adults relative to younger adults (t-test) for the right parietal region in the alpha frequency band. b Preserved outward direction (i.e., directed towards other regions of the network) in older adults relative to the younger group for the right parietal region in the alpha frequency band. c Positive association between the increased multiplex participation coefficient in the inward direction for the right parietal region in an alpha frequency band and VSTM test scores (regression test) in the older group. The level of education was controlled as a covariate. All results were adjusted for multiple comparisons using FDR corrections at q < 0.05. n = 46 participants per group. The black vertical line represents the standard error of the mean.*p < 0.05.

Fig. 5. Schematic representation of the proposed model for the left inferior temporal region.

a Level of contribution for PLV and TE. b Participation coefficient for PLV/DWI and TE/DWI multiplex network. c Summary of the relation between the level of similarity of contribution from PLV/TE, participation coefficient and concepts of ageing. DWI diffusion tensor imaging, PLV phase locking value, TE transfer entropy, FC functional connectivity, SC structural connectivity.