Resting state brain network segregation is associated with walking speed and working memory in older adults

Abstract

Older adults exhibit larger individual differences in walking ability and cognitive function than young adults. Characterizing intrinsic brain connectivity differences in older adults across a wide walking performance spectrum may provide insight into the mechanisms of functional decline in some older adults and resilience in others. Thus, the objectives of this study were to: (1) determine whether young adults and high- and low-functioning older adults show group differences in brain network segregation, and (2) determine whether network segregation is associated with working memory and walking function in these groups. The analysis included 21 young adults and 81 older adults. Older adults were further categorized according to their physical function using a standardized assessment; 54 older adults had low physical function while 27 were considered high functioning. Structural and functional resting state magnetic resonance images were collected using a Siemens Prisma 3T scanner. Working memory was assessed with the NIH Toolbox list sorting test. Walking speed was assessed with a 400 m-walk test at participants' self-selected speed. We found that network segregation in mobility-related networks (sensorimotor, vestibular) was higher in older adults with higher physical function compared to older adults with lower physical function. There were no group differences in laterality effects on network segregation. We found multivariate associations between working memory and walking speed with network segregation scores. The interaction of left sensorimotor network segregation and age groups was associated with higher working memory function. Higher left sensorimotor, left vestibular, right anterior cingulate cortex, and interaction of left anterior cingulate cortex network segregation and age groups were associated with faster walking speed. These results are unique and significant because they demonstrate higher network segregation is largely related to higher physical function and not age alone.

Keywords: Functional connectivity; aging; behavior; fMRI; resting state; segregation.

Figure 1.

Network segregation analysis. A. Network connectivity nodes included in the study. In total, 279 nodes in 10 networks were identified for analysis. BrainNet Viewer (https://www.nitrc.org/projects/bnv/; Xie et al., 2013) was used to illustrate the nodes. B. For each network, mean within-network connectivity was calculated as the mean z-values between the nodes within the network (i.e., Left sensorimotor within-network connectivity = mean z-value of all nodes in the network to all other nodes in the left sensorimotor network). Between-network connectivity was calculated as the mean of z-values between each node in the network and all the nodes in other networks (i.e., Left sensorimotor between-network connectivity = mean z-value between all nodes in left sensorimotor network and all other nodes in the brain). Network segregation score for each network was quantified as the difference of the mean within-network connectivity and the mean between-network connectivity divided by the mean within-network connectivity.

Figure 2.

Network segregation score for left and right sensorimotor (A), vestibular (B), dorsolateral prefrontal cortex, (C) and anterior cingulate cortex (D) networks. Brackets indicate statistically significant comparisons (p< 0.05) between groups from post-hoc tests. Color scheme for network nodes follow Figure 1. DLPFC = Dorsolateral Prefrontal Cortex. ACC = Anterior Cingulate Cortex. HF = High physical function. LF = Low physical function. * = p-value 0.010 ≤ p < 0.050. ** = p-value 0.001 ≤ p < 0.009. ***= p < 0.001

Figure 3.

Network segregation (A-B), within-network connectivity (C-D) and between-network connectivity (E-F) for default mode (A, C, E), visual (B, D, F) networks. Brackets indicate statistically significant comparisons (p< 0.05) between groups from post-hoc tests. Color scheme for network nodes follow Figure 1. DLPFC = Dorsolateral Prefrontal Cortex. ACC = Anterior Cingulate Cortex. HF = High physical function. LF = Low physical function. * = p-value 0.010 ≤ p < 0.050. ** = p-value 0.001 ≤ p < 0.009. ***= p < 0.001

Figure 4.

Within-network connectivity (A-D) and between-network connectivity (E-H) for sensorimotor (A, E), vestibular (B, F), dorsolateral prefrontal cortex (C, G), and anterior cingulate cortex (D, H) networks. Brackets indicate statistically significant comparisons (p< 0.05) between groups from post-hoc tests. DLPFC = Dorsolateral Prefrontal Cortex. ACC = Anterior Cingulate Cortex. HF = High physical function. LF = Low physical function. * = p-value 0.010 ≤ p < 0.050. ** = p-value 0.001 ≤ p < 0.009.

Figure 5.

Canonical correlation analysis for age groups. A. Canonical correlation analysis (CCA) was conducted to assess the relationship between the ‘function dataset’, which included walking speed, cognitive function, age group, and biological sex, and the ‘network segregation dataset’, which included network segregation scores from the 10 identified networks. First dimension showed significant association of variance between the two datasets. B. Standardized correlation coefficient for the first dimension. White bars = Coefficients for the Function dataset; Black bars = Coefficients for the Network segregation dataset. C. Canonical variates for the first dimension. Canonical variates are values of the canonical variables which is computed by multiplying the normalized variables by the canonical coefficients. L = Left; R = Right; SM = Sensorimotor; OP2 = Vestibular; DLPFC = Dorsolateral prefrontal cortex; ACC = Anterior cingulate cortex; DMN = Default mode network.

Figure 6.

Canonical correlation analysis for physical function groups. Canonical correlation analysis (CCA) was conducted to assess the relationship between the ‘function dataset’, which included walking speed, cognitive function, physical function group, and biological sex, and the ‘network segregation dataset’, which included network segregation scores from the 10 identified networks. First dimension showed significant association of variance between the two datasets. A. Standardized correlation coefficient for the first and second dimensions. White bars = Coefficients for the Function dataset; Black bars = Coefficients for the Network segregation dataset. B. Canonical variates for the first dimension. Canonical variates are values of the canonical variables which is computed by multiplying the normalized variables by the canonical coefficients. L = Left; R = Right; SM = Sensorimotor; OP2 = Vestibular; DLPFC = Dorsolateral prefrontal cortex; ACC = Anterior cingulate cortex; DMN = Default mode network.