Integrating functional connectivity and MVPA through a multiple constraint network analysis

The Differential Effects of Adiposity and Fitness on Functional Connectivity in Preadolescent Children

PURPOSE

Childhood obesity is a global health concern, with >340 million youth considered overweight or obese. In addition to contributing greatly to health care costs, excess adiposity associated with obesity is considered a major risk factor for premature mortality from cardiovascular and metabolic diseases and is also negatively associated with cognitive and brain health. A complementary line of research highlights the importance of cardiorespiratory fitness, a by-product of engaging in physical activity, on an abundance of health factors, including cognitive and brain health.

METHODS

This study investigated the relationship among excess adiposity (visceral adipose tissue [VAT], subcutaneous abdominal adipose tissue), total abdominal adipose tissue, whole-body percent fat [WB%FAT], body mass index (BMI), and fat-free cardiorespiratory fitness (FF-V̇O 2max ) on resting-state functional connectivity (RSFC) in 121 ( f = 68) children (7-11 yr) using a data-driven whole-brain multivoxel pattern analysis.

RESULTS

Multivoxel pattern analysis revealed brain regions that were significantly associated with VAT, BMI, WB%FAT, and FF-V̇O 2 measures. Yeo's (2011) RSFC-based seven-network cerebral cortical parcellation was used for labeling the results . Post hoc seed-to-voxel analyses found robust negative correlations of VAT and BMI with areas involved in the visual, somatosensory, dorsal attention, ventral attention, limbic, frontoparietal, and default mode networks. Further, positive correlations of FF-V̇O 2 were observed with areas involved in the ventral attention and frontoparietal networks. These novel findings indicate that negative health factors in childhood may be selectively and negatively associated with the 7 Yeo-defined functional networks, yet positive health factors (FF-V̇O 2 ) may be positively associated with these networks.

CONCLUSIONS

These novel results extend the current literature to suggest that BMI and adiposity are negatively associated with, and cardiorespiratory fitness (corrected for fat-free mass) is positively associated with, RSFC networks in children.

The Connectivity Fingerprints of Highly-Skilled and Disordered Reading Persist Across Cognitive Domains

The capacity to produce and understand written language is a uniquely human skill that exists on a continuum, and foundational to other facets of human cognition. Multivariate classifiers based on support vector machines (SVM) have provided much insight into the networks underlying reading skill beyond what traditional univariate methods can tell us. Shallow models like SVM require large amounts of data, and this problem is compounded when functional connections, which increase exponentially with network size, are predictors of interest. Data reduction using independent component analyses (ICA) mitigates this problem, but conventionally assumes linear relationships. Multilayer feedforward networks, in contrast, readily find optimal low-dimensional encodings of complex patterns that include complex nonlinear or conditional relationships. Samples of poor and highly-skilled young readers were selected from two open access data sets using rhyming and mental multiplication tasks, respectively. Functional connectivity was computed for the rhyming task within a functionally-defined reading network and used to train multilayer feedforward classifier models to simultaneously associate functional connectivity patterns with lexicality (word vs. pseudoword) and reading skill (poor vs. highly-skilled). Classifiers identified validation set lexicality with significantly better than chance accuracy, and reading skill with near-ceiling accuracy. Critically, a series of replications used pre-trained rhyming-task models to classify reading skill from mental multiplication task participants' connectivity with near-ceiling accuracy. The novel deep learning approach presented here provides the clearest demonstration to date that reading-skill dependent functional connectivity within the reading network influences brain processing dynamics across cognitive domains.

Linking ADHD and Behavioral Assessment Through Identification of Shared Diagnostic Task-Based Functional Connections

A mixed literature implicates atypical connectivity involving attentional, reward and task inhibition networks in ADHD. The neural mechanisms underlying the utility of behavioral tasks in ADHD diagnosis are likewise underexplored. We hypothesized that a machine-learning classifier may use task-based functional connectivity to compute a joint probability function that identifies connectivity signatures that accurately predict ADHD diagnosis and performance on a clinically-relevant behavioral task, providing an explicit neural mechanism linking behavioral phenotype to diagnosis. We analyzed archival MRI and behavioral data of 80 participants (64 male) who had completed the go/no-go task from the longitudinal follow-up of the Multimodal Treatment Study of ADHD (MTA 168) (mean age = 24 years). Cross-mutual information within a functionally-defined mask measured functional connectivity for each task run. Multilayer feedforward classifier models identified the subset of functional connections that predicted clinical diagnosis (ADHD vs. Control) and split-half performance on the Iowa Gambling Task (IGT). A sample of random models trained on functional connectivity profiles predicted validation set clinical diagnosis and IGT performance with 0.91 accuracy and d' > 2.9, indicating very high sensitivity and specificity. We identified the most diagnostic functional connections between visual and ventral attentional networks and the anterior default mode network. Our results show that task-based functional connectivity is a biomarker of ADHD. Our analytic framework provides a template approach that explicitly ties behavioral assessment measures to both clinical diagnosis, and functional connectivity. This may differentiate otherwise similar diagnoses, and promote more efficacious intervention strategies.