Prediction of neurocognition in youth from resting state fMRI

Flexible adaptation of task-positive brain networks predicts efficiency of evidence accumulation

Efficiency of evidence accumulation (EEA), an individual's ability to selectively gather goal-relevant information to make adaptive choices, is thought to be a key neurocomputational mechanism associated with cognitive functioning and transdiagnostic risk for psychopathology. However, the neural basis of individual differences in EEA is poorly understood, especially regarding the role of largescale brain network dynamics. We leverage data from 5198 participants from the Human Connectome Project and Adolescent Brain Cognitive Development Study to demonstrate a strong association between EEA and flexible adaptation to cognitive demand in the "task-positive" frontoparietal and dorsal attention networks. Notably, individuals with higher EEA displayed divergent task-positive network activation across n-back task conditions: higher activation under high cognitive demand (2-back) and lower activation under low demand (0-back). These findings suggest that brain networks' flexible adaptation to cognitive demands is a key neural underpinning of EEA.

Individual characteristics outperform resting-state fMRI for the prediction of behavioral phenotypes

In this study, we aimed to compare imaging-based features of brain function, measured by resting-state fMRI (rsfMRI), with individual characteristics such as age, gender, and total intracranial volume to predict behavioral measures. We developed a machine learning framework based on rsfMRI features in a dataset of 20,000 healthy individuals from the UK Biobank, focusing on temporal complexity and functional connectivity measures. Our analysis across four behavioral phenotypes revealed that both temporal complexity and functional connectivity measures provide comparable predictive performance. However, individual characteristics consistently outperformed rsfMRI features in predictive accuracy, particularly in analyses involving smaller sample sizes. Integrating rsfMRI features with demographic data sometimes enhanced predictive outcomes. The efficacy of different predictive modeling techniques and the choice of brain parcellation atlas were also examined, showing no significant influence on the results. To summarize, while individual characteristics are superior to rsfMRI in predicting behavioral phenotypes, rsfMRI still conveys additional predictive value in the context of machine learning, such as investigating the role of specific brain regions in behavioral phenotypes.

TractoSCR: a novel supervised contrastive regression framework for prediction of neurocognitive measures using multi-site harmonized diffusion MRI tractography

Neuroimaging-based prediction of neurocognitive measures is valuable for studying how the brain's structure relates to cognitive function. However, the accuracy of prediction using popular linear regression models is relatively low. We propose a novel deep regression method, namely TractoSCR, that allows full supervision for contrastive learning in regression tasks using diffusion MRI tractography. TractoSCR performs supervised contrastive learning by using the absolute difference between continuous regression labels (i.e., neurocognitive scores) to determine positive and negative pairs. We apply TractoSCR to analyze a large-scale dataset including multi-site harmonized diffusion MRI and neurocognitive data from 8,735 participants in the Adolescent Brain Cognitive Development (ABCD) Study. We extract white matter microstructural measures using a fine parcellation of white matter tractography into fiber clusters. Using these measures, we predict three scores related to domains of higher-order cognition (general cognitive ability, executive function, and learning/memory). To identify important fiber clusters for prediction of these neurocognitive scores, we propose a permutation feature importance method for high-dimensional data. We find that TractoSCR obtains significantly higher accuracy of neurocognitive score prediction compared to other state-of-the-art methods. We find that the most predictive fiber clusters are predominantly located within the superficial white matter and projection tracts, particularly the superficial frontal white matter and striato-frontal connections. Overall, our results demonstrate the utility of contrastive representation learning methods for regression, and in particular for improving neuroimaging-based prediction of higher-order cognitive abilities. Our code will be available at: https://github.com/SlicerDMRI/TractoSCR.

A robust brain network for sustained attention from adolescence to adulthood that predicts later substance use

Substance use, including cigarettes and cannabis, is associated with poorer sustained attention in late adolescence and early adulthood. Previous studies were predominantly cross-sectional or under-powered and could not indicate if impairment in sustained attention was a predictor of substance-use or a marker of the inclination to engage in such behaviour. This study explored the relationship between sustained attention and substance use across a longitudinal span from ages 14 to 23 in over 1,000 participants. Behaviours and brain connectivity associated with diminished sustained attention at age 14 predicted subsequent increases in cannabis and cigarette smoking, establishing sustained attention as a robust biomarker for vulnerability to substance use. Individual differences in network strength relevant to sustained attention were preserved across developmental stages and sustained attention networks generalized to participants in an external dataset. In summary, brain networks of sustained attention are robust, consistent, and able to predict aspects of later substance use.

Leveraging the adolescent brain cognitive development study to improve behavioral prediction from neuroimaging in smaller replication samples

Neuroimaging is a popular method to map brain structural and functional patterns to complex human traits. Recently published observations cast doubt upon these prospects, particularly for prediction of cognitive traits from structural and resting state functional magnetic resonance imaging (MRI). We leverage baseline data from thousands of children in the Adolescent Brain Cognitive DevelopmentSM Study to inform the replication sample size required with univariate and multivariate methods across different imaging modalities to detect reproducible brain-behavior associations. We demonstrate that by applying multivariate methods to high-dimensional brain imaging data, we can capture lower dimensional patterns of structural and functional brain architecture that correlate robustly with cognitive phenotypes and are reproducible with only 41 individuals in the replication sample for working memory-related functional MRI, and ~ 100 subjects for structural and resting state MRI. Even with 100 random re-samplings of 100 subjects in discovery, prediction can be adequately powered with 66 subjects in replication for multivariate prediction of cognition with working memory task functional MRI. These results point to an important role for neuroimaging in translational neurodevelopmental research and showcase how findings in large samples can inform reproducible brain-behavior associations in small sample sizes that are at the heart of many research programs and grants.

Functional brain connectivity predictors of prospective substance use initiation and their environmental correlates

Background

Early substance use initiation (SUI) places youth at substantially higher risk for later substance use disorders. Furthermore, adolescence is a critical period for the maturation of brain networks, the pace and magnitude of which are susceptible to environmental influences and may shape risk for SUI.

Methods

We examined whether patterns of functional brain connectivity during rest (rsFC), measured longitudinally in pre-and-early adolescence, can predict future SUI. In an independent sub-sample, we also tested whether these patterns are associated with key environmental factors, specifically neighborhood pollution and socioeconomic dimensions. We utilized data from the Adolescent Brain Cognitive Development (ABCD) Study®. SUI was defined as first-time use of at least one full dose of alcohol, nicotine, cannabis, or other drugs. We created a control group (N = 228) of participants without SUI who were matched with the SUI group (N = 233) on age, sex, race/ethnicity, and parental income and education.

Results

Multivariate analysis showed that whole-brain rsFC prior to SUI during 9-10 and 11-12 years of age successfully differentiated the prospective SUI and control groups. This rsFC signature was expressed more at older ages in both groups, suggesting a pattern of accelerated maturation in the SUI group in the years prior to SUI. In an independent sub-sample (N = 2,854) and adjusted for family socioeconomic factors, expression of this rsFC pattern was associated with higher pollution, but not neighborhood disadvantage.

Conclusion

Brain functional connectivity patterns in early adolescence that are linked to accelerated maturation and environmental exposures can predict future SUI in youth.

Childhood adversities characterize the heterogeneity in the brain pattern of individuals during neurodevelopment

BACKGROUND

Several factors shape the neurodevelopmental trajectory. A key area of focus in neurodevelopmental research is to estimate the factors that have maximal influence on the brain and can tip the balance from typical to atypical development.

METHODS

Utilizing a dissimilarity maximization algorithm on the dynamic mode decomposition (DMD) of the resting state functional MRI data, we classified subjects from the cVEDA neurodevelopmental cohort (n = 987, aged 6-23 years) into homogeneously patterned DMD (representing typical development in 809 subjects) and heterogeneously patterned DMD (indicative of atypical development in 178 subjects).

RESULTS

Significant DMD differences were primarily identified in the default mode network (DMN) regions across these groups (p < 0.05, Bonferroni corrected). While the groups were comparable in cognitive performance, the atypical group had more frequent exposure to adversities and faced higher abuses (p < 0.05, Bonferroni corrected). Upon evaluating brain-behavior correlations, we found that correlation patterns between adversity and DMN dynamic modes exhibited age-dependent variations for atypical subjects, hinting at differential utilization of the DMN due to chronic adversities.

CONCLUSION

Adversities (particularly abuse) maximally influence the DMN during neurodevelopment and lead to the failure in the development of a coherent DMN system. While DMN's integrity is preserved in typical development, the age-dependent variability in atypically developing individuals is contrasting. The flexibility of DMN might be a compensatory mechanism to protect an individual in an abusive environment. However, such adaptability might deprive the neural system of the faculties of normal functioning and may incur long-term effects on the psyche.

LATENT SUBGROUP IDENTIFICATION IN IMAGE-ON-SCALAR REGRESSION

Image-on-scalar regression has been a popular approach to modeling the association between brain activities and scalar characteristics in neuroimaging research. The associations could be heterogeneous across individuals in the population, as indicated by recent large-scale neuroimaging studies, for example, the Adolescent Brain Cognitive Development (ABCD) Study. The ABCD data can inform our understanding of heterogeneous associations and how to leverage the heterogeneity and tailor interventions to increase the number of youths who benefit. It is of great interest to identify subgroups of individuals from the population such that: (1) within each subgroup the brain activities have homogeneous associations with the clinical measures; (2) across subgroups the associations are heterogeneous, and (3) the group allocation depends on individual characteristics. Existing image-on-scalar regression methods and clustering methods cannot directly achieve this goal. We propose a latent subgroup image-on-scalar regression model (LASIR) to analyze large-scale, multisite neuroimaging data with diverse sociode-mographics. LASIR introduces the latent subgroup for each individual and group-specific, spatially varying effects, with an efficient stochastic expectation maximization algorithm for inferences. We demonstrate that LASIR outperforms existing alternatives for subgroup identification of brain activation patterns with functional magnetic resonance imaging data via comprehensive simulations and applications to the ABCD study. We have released our reproducible codes for public use with the software package available on Github.

Dissociation of Reliability, Heritability, and Predictivity in Coarse- and Fine-Scale Functional Connectomes during Development

The functional connectome supports information transmission through the brain at various spatial scales, from exchange between broad cortical regions to finer-scale, vertex-wise connections that underlie specific information processing mechanisms. In adults, while both the coarse- and fine-scale functional connectomes predict cognition, the fine scale can predict up to twice the variance as the coarse-scale functional connectome. Yet, past brain-wide association studies, particularly using large developmental samples, focus on the coarse connectome to understand the neural underpinnings of individual differences in cognition. Using a large cohort of children (age 9-10 years; n = 1,115 individuals; both sexes; 50% female, including 170 monozygotic and 219 dizygotic twin pairs and 337 unrelated individuals), we examine the reliability, heritability, and behavioral relevance of resting-state functional connectivity computed at different spatial scales. We use connectivity hyperalignment to improve access to reliable fine-scale (vertex-wise) connectivity information and compare the fine-scale connectome with the traditional parcel-wise (coarse scale) functional connectomes. Though individual differences in the fine-scale connectome are more reliable than those in the coarse-scale, they are less heritable. Further, the alignment and scale of connectomes influence their ability to predict behavior, whereby some cognitive traits are equally well predicted by both connectome scales, but other, less heritable cognitive traits are better predicted by the fine-scale connectome. Together, our findings suggest there are dissociable individual differences in information processing represented at different scales of the functional connectome which, in turn, have distinct implications for heritability and cognition.

Improved estimation of general cognitive ability and its neural correlates with a large battery of cognitive tasks

Elucidating the neural mechanisms of general cognitive ability (GCA) is an important mission of cognitive neuroscience. Recent large-sample cohort studies measured GCA through multiple cognitive tasks and explored its neural basis, but they did not investigate how task number, factor models, and neural data type affect the estimation of GCA and its neural correlates. To address these issues, we tested 1,605 Chinese young adults with 19 cognitive tasks and Raven's Advanced Progressive Matrices (RAPM) and collected resting state and n-back task fMRI data from a subsample of 683 individuals. Results showed that GCA could be reliably estimated by multiple tasks. Increasing task number enhances both reliability and validity of GCA estimates and reliably strengthens their correlations with brain data. The Spearman model and hierarchical bifactor model yield similar GCA estimates. The bifactor model has better model fit and stronger correlation with RAPM but explains less variance and shows weaker correlations with brain data than does the Spearman model. Notably, the n-back task-based functional connectivity patterns outperform resting-state fMRI in predicting GCA. These results suggest that GCA derived from a multitude of cognitive tasks serves as a valid measure of general intelligence and that its neural correlates could be better characterized by task fMRI than resting-state fMRI data.

Machine learning and artificial intelligence in neuroscience: A primer for researchers

Artificial intelligence (AI) is often used to describe the automation of complex tasks that we would attribute intelligence to. Machine learning (ML) is commonly understood as a set of methods used to develop an AI. Both have seen a recent boom in usage, both in scientific and commercial fields. For the scientific community, ML can solve bottle necks created by complex, multi-dimensional data generated, for example, by functional brain imaging or *omics approaches. ML can here identify patterns that could not have been found using traditional statistic approaches. However, ML comes with serious limitations that need to be kept in mind: their tendency to optimise solutions for the input data means it is of crucial importance to externally validate any findings before considering them more than a hypothesis. Their black-box nature implies that their decisions usually cannot be understood, which renders their use in medical decision making problematic and can lead to ethical issues. Here, we present an introduction for the curious to the field of ML/AI. We explain the principles as commonly used methods as well as recent methodological advancements before we discuss risks and what we see as future directions of the field. Finally, we show practical examples of neuroscience to illustrate the use and limitations of ML.

Shared functional connectome fingerprints following ritualistic ayahuasca intake

The knowledge that brain functional connectomes are unique and reliable has enabled behaviourally relevant inferences at a subject level. However, whether such "fingerprints" persist under altered states of consciousness is unknown. Ayahuasca is a potent serotonergic psychedelic which produces a widespread dysregulation of functional connectivity. Used communally in religious ceremonies, its shared use may highlight relevant novel interactions between mental state and functional connectome (FC) idiosyncrasy. Using 7T fMRI, we assessed resting-state static and dynamic FCs for 21 Santo Daime members after collective ayahuasca intake in an acute, within-subject study. Here, connectome fingerprinting revealed FCs showed reduced idiosyncrasy, accompanied by a spatiotemporal reallocation of keypoint edges. Importantly, we show that interindividual differences in higher-order FC motifs are relevant to experiential phenotypes, given that they can predict perceptual drug effects. Collectively, our findings offer an example of how individualised connectivity markers can be used to trace a subject's FC across altered states of consciousness.

Socioeconomic resources in youth are linked to divergent patterns of network integration and segregation across the brain's transmodal axis

Socioeconomic resources (SER) calibrate the developing brain to the current context, which can confer or attenuate risk for psychopathology across the lifespan. Recent multivariate work indicates that SER levels powerfully influence intrinsic functional connectivity patterns across the entire brain. Nevertheless, the neurobiological meaning of these widespread alterations remains poorly understood, despite its translational promise for early risk identification, targeted intervention, and policy reform. In the present study, we leverage the resources of graph theory to precisely characterize multivariate and univariate associations between household SER and the functional integration and segregation (i.e., participation coefficient, within-module degree) of brain regions across major cognitive, affective, and sensorimotor systems during the resting state in 5,821 youth (ages 9-10 years) from the Adolescent Brain Cognitive Development (ABCD) Study. First, we establish that decomposing the brain into profiles of integration and segregation captures more than half of the multivariate association between SER and functional connectivity with greater parsimony (100-fold reduction in number of features) and interpretability. Second, we show that the topological effects of SER are not uniform across the brain; rather, higher SER levels are related to greater integration of somatomotor and subcortical systems, but greater segregation of default mode, orbitofrontal, and cerebellar systems. Finally, we demonstrate that the effects of SER are spatially patterned along the unimodal-transmodal gradient of brain organization. These findings provide critical interpretive context for the established and widespread effects of SER on brain organization, indicating that SER levels differentially configure the intrinsic functional architecture of developing unimodal and transmodal systems. This study highlights both sensorimotor and higher-order networks that may serve as neural markers of environmental stress and opportunity, and which may guide efforts to scaffold healthy neurobehavioral development among disadvantaged communities of youth.

Brain Networks and Adolescent Alcohol Use

Importance

Alcohol misuse in adolescence is a leading cause of disability and mortality in youth and is associated with higher risk for alcohol use disorder. Brain mechanisms underlying risk of alcohol misuse may inform prevention and intervention efforts.

Objective

To identify neuromarkers of alcohol misuse using a data-driven approach, with specific consideration of neurodevelopmental sex differences.

Design, Setting, and Participants

Longitudinal multisite functional magnetic resonance imaging (fMRI) data collected at ages 14 and 19 years were used to assess whole-brain patterns of functional organization associated with current and future alcohol use risk as measured by the Alcohol Use Disorder Identification Test (AUDIT). Primary data were collected by the IMAGEN consortium, a European multisite study of adolescent neurodevelopment. Model generalizability was further tested using data acquired in a single-site study of college alcohol consumption conducted in the US. The primary sample was a developmental cohort of 1359 adolescents with neuroimaging, phenotyping, and alcohol use data. Model generalizability was further assessed in a separate cohort of 114 individuals.

Main Outcomes and Measures

Brain-behavior model accuracy, as defined by the correspondence between model-predicted and actual AUDIT scores in held-out testing data, Bonferroni corrected across the number of models run at each time point, 2-tailed α < .008, as determined via permutation testing.

Results

Among 1359 individuals in the study, the mean (SD) age was 14.42 (0.40) years, and 729 individuals (54%) were female. The data-driven, whole-brain connectivity approach identified networks associated with vulnerability for future and current AUDIT-defined alcohol use risk (primary outcome, as specified above, future: ρ, 0.22; P < .001 and present: ρ, 0.27; P < .001). Results further indicated sex divergence in the accuracies of brain-behavior models, such that female-only models consistently outperformed male-only models. Specifically, female-only models identified networks conferring vulnerability for future and current severity using data acquired during both reward and inhibitory fMRI tasks. In contrast, male-only models were successful in accurately identifying networks using data acquired during the inhibitory control-but not reward-task, indicating domain specificity of alcohol use risk networks in male adolescents only.

Conclusions and Relevance

These data suggest that interventions focusing on inhibitory control processes may be effective in combating alcohol use risk in male adolescents but that both inhibitory and reward-related processes are likely of relevance to alcohol use behaviors in female adolescents. They further identify novel networks of alcohol use risk in youth, which may be used to identify adolescents who are at risk and inform intervention efforts.

Image response regression via deep neural networks

Delineating associations between images and covariates is a central aim of imaging studies. To tackle this problem, we propose a novel non-parametric approach in the framework of spatially varying coefficient models, where the spatially varying functions are estimated through deep neural networks. Our method incorporates spatial smoothness, handles subject heterogeneity, and provides straightforward interpretations. It is also highly flexible and accurate, making it ideal for capturing complex association patterns. We establish estimation and selection consistency and derive asymptotic error bounds. We demonstrate the method's advantages through intensive simulations and analyses of two functional magnetic resonance imaging data sets.

Leveraging the Adolescent Brain Cognitive Development Study to improve behavioral prediction from neuroimaging in smaller replication samples

Magnetic resonance imaging (MRI) is a popular and useful non-invasive method to map patterns of brain structure and function to complex human traits. Recently published observations in multiple large scale studies cast doubt upon these prospects, particularly for prediction of cognitive traits from structural and resting state functional MRI, which seems to account for little behavioral variability. We leverage baseline data from thousands of children in the Adolescent Brain Cognitive DevelopmentSM (ABCD®) Study to inform the replication sample size required with both univariate and multivariate methods across different imaging modalities to detect reproducible brain-behavior associations. We demonstrate that by applying multivariate methods to high-dimensional brain imaging data, we can capture lower dimensional patterns of structural and functional brain architecture that correlate robustly with cognitive phenotypes and are reproducible with only 41 individuals in the replication sample for working memory-related functional MRI, and ~100 subjects for structural MRI. Even with 100 random re-samplings of 50 subjects in the discovery sample, prediction can be adequately powered with 98 subjects in the replication sample for multivariate prediction of cognition with working memory task functional MRI. These results point to an important role for neuroimaging in translational neurodevelopmental research and showcase how findings in large samples can inform reproducible brain-behavior associations in small sample sizes that are at the heart of many investigators' research programs and grants.

The challenges and prospects of brain-based prediction of behaviour

Relating individual brain patterns to behaviour is fundamental in system neuroscience. Recently, the predictive modelling approach has become increasingly popular, largely due to the recent availability of large open datasets and access to computational resources. This means that we can use machine learning models and interindividual differences at the brain level represented by neuroimaging features to predict interindividual differences in behavioural measures. By doing so, we could identify biomarkers and neural correlates in a data-driven fashion. Nevertheless, this budding field of neuroimaging-based predictive modelling is facing issues that may limit its potential applications. Here we review these existing challenges, as well as those that we anticipate as the field develops. We focus on the impacts of these challenges on brain-based predictions. We suggest potential solutions to address the resolvable challenges, while keeping in mind that some general and conceptual limitations may also underlie the predictive modelling approach.

Decoding individual differences in self-prioritization from the resting-state functional connectome

Although the self has traditionally been viewed as a higher-order mental function by most theoretical frameworks, recent research advocates a fundamental self hypothesis, viewing the self as a baseline function of the brain embedded within its spontaneous activities, which dynamically regulates cognitive processing and subsequently guides behavior. Understanding this fundamental self hypothesis can reveal where self-biased behaviors emerge and to what extent brain signals at rest can predict such biased behaviors. To test this hypothesis, we investigated the association between spontaneous neural connectivity and robust self-bias in a perceptual matching task using resting-state functional magnetic resonance imaging (fMRI) in 348 young participants. By decoding whole-brain connectivity patterns, the support vector regression model produced the best predictions of the magnitude of self-bias in behavior, which was evaluated via a nested cross-validation procedure. The out-of-sample generalizability was further authenticated using an external dataset of older adults. The functional connectivity results demonstrated that self-biased behavior was associated with distinct connections between the default mode, cognitive control, and salience networks. Consensus network and computational lesion analyses further revealed contributing regions distributed across six networks, extending to additional nodes, such as the thalamus, whose role in self-related processing remained unclear. These results provide evidence that self-biased behavior derives from spontaneous neural connectivity, supporting the fundamental self hypothesis. Thus, we propose an integrated neural network model of this fundamental self that synthesizes previous theoretical models and portrays the brain mechanisms by which the self emerges at rest internally and regulates responses to the external environment.

Intermediately synchronised brain states optimise trade-off between subject specificity and predictive capacity

Functional connectivity (FC) refers to the statistical dependencies between activity of distinct brain areas. To study temporal fluctuations in FC within the duration of a functional magnetic resonance imaging (fMRI) scanning session, researchers have proposed the computation of an edge time series (ETS) and their derivatives. Evidence suggests that FC is driven by a few time points of high-amplitude co-fluctuation (HACF) in the ETS, which may also contribute disproportionately to interindividual differences. However, it remains unclear to what degree different time points actually contribute to brain-behaviour associations. Here, we systematically evaluate this question by assessing the predictive utility of FC estimates at different levels of co-fluctuation using machine learning (ML) approaches. We demonstrate that time points of lower and intermediate co-fluctuation levels provide overall highest subject specificity as well as highest predictive capacity of individual-level phenotypes.

Generalizable prediction of childhood ADHD symptoms from neurocognitive testing and youth characteristics

Childhood attention-deficit/hyperactivity disorder (ADHD) symptoms are believed to result from disrupted neurocognitive development. However, evidence for the clinical and predictive value of neurocognitive assessments in this context has been mixed, and there have been no large-scale efforts to quantify their potential for use in generalizable models that predict individuals' ADHD symptoms in new data. Using data drawn from the Adolescent Brain Cognitive Development Study (ABCD), a consortium that recruited a diverse sample of over 10,000 youth (ages 9-10 at baseline) across 21 U.S. sites, we develop and test cross-validated machine learning models for predicting youths' ADHD symptoms using neurocognitive abilities, demographics, and child and family characteristics. Models used baseline demographic and biometric measures, geocoded neighborhood data, youth reports of child and family characteristics, and neurocognitive tests to predict parent- and teacher-reported ADHD symptoms at the 1-year and 2-year follow-up time points. Predictive models explained 15-20% of the variance in 1-year ADHD symptoms for ABCD Study sites that were left out of the model-fitting process and 12-13% of the variance in 2-year ADHD symptoms. Models displayed high generalizability across study sites and trivial loss of predictive power when transferred from training data to left-out data. Features from multiple domains contributed meaningfully to prediction, including neurocognition, sex, self-reported impulsivity, parental monitoring, and screen time. This work quantifies the information value of neurocognitive abilities and other child characteristics for predicting ADHD symptoms and provides a foundational method for predicting individual youths' symptoms in new data across contexts.

A functional connectome signature of blood pressure in >30 000 participants from the UK biobank

AIMS

Elevated blood pressure (BP) is a prevalent modifiable risk factor for cardiovascular diseases and contributes to cognitive decline in late life. Despite the fact that functional changes may precede irreversible structural damage and emerge in an ongoing manner, studies have been predominantly informed by brain structure and group-level inferences. Here, we aim to delineate neurobiological correlates of BP at an individual level using machine learning and functional connectivity.

METHODS AND RESULTS

Based on whole-brain functional connectivity from the UK Biobank, we built a machine learning model to identify neural representations for individuals' past (∼8.9 years before scanning, N = 35 882), current (N = 31 367), and future (∼2.4 years follow-up, N = 3 138) BP levels within a repeated cross-validation framework. We examined the impact of multiple potential covariates, as well as assessed these models' generalizability across various contexts.The predictive models achieved significant correlations between predicted and actual systolic/diastolic BP and pulse pressure while controlling for multiple confounders. Predictions for participants not on antihypertensive medication were more accurate than for currently medicated patients. Moreover, the models demonstrated robust generalizability across contexts in terms of ethnicities, imaging centres, medication status, participant visits, gender, age, and body mass index. The identified connectivity patterns primarily involved the cerebellum, prefrontal, anterior insula, anterior cingulate cortex, supramarginal gyrus, and precuneus, which are key regions of the central autonomic network, and involved in cognition processing and susceptible to neurodegeneration in Alzheimer's disease. Results also showed more involvement of default mode and frontoparietal networks in predicting future BP levels and in medicated participants.

CONCLUSION

This study, based on the largest neuroimaging sample currently available and using machine learning, identifies brain signatures underlying BP, providing evidence for meaningful BP-associated neural representations in connectivity profiles.

Bayesian interaction selection model for multimodal neuroimaging data analysis

Multimodality or multiconstruct data arise increasingly in functional neuroimaging studies to characterize brain activity under different cognitive states. Relying on those high-resolution imaging collections, it is of great interest to identify predictive imaging markers and intermodality interactions with respect to behavior outcomes. Currently, most of the existing variable selection models do not consider predictive effects from interactions, and the desired higher-order terms can only be included in the predictive mechanism following a two-step procedure, suffering from potential misspecification. In this paper, we propose a unified Bayesian prior model to simultaneously identify main effect features and intermodality interactions within the same inference platform in the presence of high-dimensional data. To accommodate the brain topological information and correlation between modalities, our prior is designed by compiling the intermediate selection status of sequential partitions in light of the data structure and brain anatomical architecture, so that we can improve posterior inference and enhance biological plausibility. Through extensive simulations, we show the superiority of our approach in main and interaction effects selection, and prediction under multimodality data. Applying the method to the Adolescent Brain Cognitive Development (ABCD) study, we characterize the brain functional underpinnings with respect to general cognitive ability under different memory load conditions.

Person-centred Approaches to Psychopathology in the ABCD Study: Phenotypes and Neurocognitive Correlates

Issues with classifying psychopathology using narrow diagnostic categories have prompted calls for the use of dimensional approaches. Yet questions remain about how closely dimensional approaches reflect the way symptoms cluster in individuals, whether known risk factors (e.g. preterm birth) produce distinct symptom phenotypes, and whether profiles reflecting symptom clusters are associated with neurocognitive factors. To identify distinct profiles of psychopathology, latent class analysis was applied to the syndrome scales of the parent-reported Child Behaviour Checklist for 11,381 9- and 10- year-olds from the Adolescent Brain Cognitive Development study. Four classes were identified, reflecting different profiles, to which children were assigned probabilistically; Class 1 (88.6%) reflected optimal functioning; Class 2 (7.1%), predominantly internalising; Class 3 (2.4%), predominantly externalising; and Class 4 (1.9%), universal difficulties. To investigate the presence of a possible preterm behavioural phenotype, the proportion of participants allocated to each class was cross-tabulated with gestational age category. No profile was specific to preterm birth. Finally, to assess the neurocognitive factors associated with class membership, elastic net regressions were conducted revealing a relatively distinct set of neurocognitive factors associated with each class. Findings support the use of large datasets to identify psychopathological profiles, explore phenotypes, and identify associated neurocognitive factors.

Relationship Between Prediction Accuracy and Feature Importance Reliability: an Empirical and Theoretical Study

There is significant interest in using neuroimaging data to predict behavior. The predictive models are often interpreted by the computation of feature importance, which quantifies the predictive relevance of an imaging feature. Tian and Zalesky (2021) suggest that feature importance estimates exhibit low split-half reliability, as well as a trade-off between prediction accuracy and feature importance reliability across parcellation resolutions. However, it is unclear whether the trade-off between prediction accuracy and feature importance reliability is universal. Here, we demonstrate that, with a sufficient sample size, feature importance (operationalized as Haufe-transformed weights) can achieve fair to excellent split-half reliability. With a sample size of 2600 participants, Haufe-transformed weights achieve average intra-class correlation coefficients of 0.75, 0.57 and 0.53 for cognitive, personality and mental health measures respectively. Haufe-transformed weights are much more reliable than original regression weights and univariate FC-behavior correlations. Original regression weights are not reliable even with 2600 participants. Intriguingly, feature importance reliability is strongly positively correlated with prediction accuracy across phenotypes. Within a particular behavioral domain, there is no clear relationship between prediction performance and feature importance reliability across regression models. Furthermore, we show mathematically that feature importance reliability is necessary, but not sufficient, for low feature importance error. In the case of linear models, lower feature importance error is mathematically related to lower prediction error. Therefore, higher feature importance reliability might yield lower feature importance error and higher prediction accuracy. Finally, we discuss how our theoretical results relate with the reliability of imaging features and behavioral measures. Overall, the current study provides empirical and theoretical insights into the relationship between prediction accuracy and feature importance reliability.

Resting-state brain functional alterations and their genetic mechanisms in drug-naive first-episode psychosis

Extensive research has established the presence of resting-state brain functional damage in psychosis. However, the genetic mechanisms of such disease phenotype are yet to be unveiled. We investigated resting-state brain functional alterations in patients with drug-naive first-episode psychosis (DFP) by performing a neuroimaging meta-analysis of 8 original studies comprising 500 patients and 469 controls. Combined with the Allen Human Brain Atlas, we further conducted transcriptome-neuroimaging spatial correlations to identify genes whose expression levels were linked to brain functional alterations in DFP, followed by a range of gene functional characteristic analyses. Meta-analysis revealed a mixture of increased and decreased brain function in widespread areas including the default-mode, visual, motor, striatal, and cerebellar systems in DFP. Moreover, these brain functional alterations were spatially associated with the expression of 1662 genes, which were enriched for molecular functions, cellular components, and biological processes of the cerebral cortex, as well as psychiatric disorders including schizophrenia. Specific expression analyses demonstrated that these genes were specifically expressed in the brain tissue, in cortical neurons and immune cells, and during nearly all developmental periods. Concurrently, the genes could construct a protein-protein interaction network supported by hub genes and were linked to multiple behavioral domains including emotion, attention, perception, and motor. Our findings provide empirical evidence for the notion that brain functional damage in DFP involves a complex interaction of polygenes with various functional characteristics.

Uncovering individual differences in fine-scale dynamics of functional connectivity

Functional connectivity (FC) profiles contain subject-specific features that are conserved across time and have potential to capture brain-behavior relationships. Most prior work has focused on spatial features (nodes and systems) of these FC fingerprints, computed over entire imaging sessions. We propose a method for temporally filtering FC, which allows selecting specific moments in time while also maintaining the spatial pattern of node-based activity. To this end, we leverage a recently proposed decomposition of FC into edge time series (eTS). We systematically analyze functional magnetic resonance imaging frames to define features that enhance identifiability across multiple fingerprinting metrics, similarity metrics, and data sets. Results show that these metrics characteristically vary with eTS cofluctuation amplitude, similarity of frames within a run, transition velocity, and expression of functional systems. We further show that data-driven optimization of features that maximize fingerprinting metrics isolates multiple spatial patterns of system expression at specific moments in time. Selecting just 10% of the data can yield stronger fingerprints than are obtained from the full data set. Our findings support the idea that FC fingerprints are differentially expressed across time and suggest that multiple distinct fingerprints can be identified when spatial and temporal characteristics are considered simultaneously.

Evidence from "big data" for the default-mode hypothesis of ADHD: a mega-analysis of multiple large samples

We sought to identify resting-state characteristics related to attention deficit/hyperactivity disorder, both as a categorical diagnosis and as a trait feature, using large-scale samples which were processed according to a standardized pipeline. In categorical analyses, we considered 1301 subjects with diagnosed ADHD, contrasted against 1301 unaffected controls (total N = 2602; 1710 males (65.72%); mean age = 10.86 years, sd = 2.05). Cases and controls were 1:1 nearest neighbor matched on in-scanner motion and key demographic variables and drawn from multiple large cohorts. Associations between ADHD-traits and resting-state connectivity were also assessed in a large multi-cohort sample (N = 10,113). ADHD diagnosis was associated with less anticorrelation between the default mode and salience/ventral attention (B = 0.009, t = 3.45, p-FDR = 0.004, d = 0.14, 95% CI = 0.004, 0.014), somatomotor (B = 0.008, t = 3.49, p-FDR = 0.004, d = 0.14, 95% CI = 0.004, 0.013), and dorsal attention networks (B = 0.01, t = 4.28, p-FDR < 0.001, d = 0.17, 95% CI = 0.006, 0.015). These results were robust to sensitivity analyses considering comorbid internalizing problems, externalizing problems and psychostimulant medication. Similar findings were observed when examining ADHD traits, with the largest effect size observed for connectivity between the default mode network and the dorsal attention network (B = 0.0006, t = 5.57, p-FDR < 0.001, partial-r = 0.06, 95% CI = 0.0004, 0.0008). We report significant ADHD-related differences in interactions between the default mode network and task-positive networks, in line with default mode interference models of ADHD. Effect sizes (Cohen's d and partial-r, estimated from the mega-analytic models) were small, indicating subtle group differences. The overlap between the affected brain networks in the clinical and general population samples supports the notion of brain phenotypes operating along an ADHD continuum.

Classification and prediction of cognitive performance differences in older age based on brain network patterns using a machine learning approach

Age-related cognitive decline varies greatly in healthy older adults, which may partly be explained by differences in the functional architecture of brain networks. Resting-state functional connectivity (RSFC) derived network parameters as widely used markers describing this architecture have even been successfully used to support diagnosis of neurodegenerative diseases. The current study aimed at examining whether these parameters may also be useful in classifying and predicting cognitive performance differences in the normally aging brain by using machine learning (ML). Classifiability and predictability of global and domain-specific cognitive performance differences from nodal and network-level RSFC strength measures were examined in healthy older adults from the 1000BRAINS study (age range: 55-85 years). ML performance was systematically evaluated across different analytic choices in a robust cross-validation scheme. Across these analyses, classification performance did not exceed 60% accuracy for global and domain-specific cognition. Prediction performance was equally low with high mean absolute errors (MAEs ≥ 0.75) and low to none explained variance (R2 ≤ 0.07) for different cognitive targets, feature sets, and pipeline configurations. Current results highlight limited potential of functional network parameters to serve as sole biomarker for cognitive aging and emphasize that predicting cognition from functional network patterns may be challenging.

Longitudinally stable, brain-based predictive models mediate the relationships between childhood cognition and socio-demographic, psychological and genetic factors

Cognitive abilities are one of the major transdiagnostic domains in the National Institute of Mental Health's Research Domain Criteria (RDoC). Following RDoC's integrative approach, we aimed to develop brain-based predictive models for cognitive abilities that (a) are developmentally stable over years during adolescence and (b) account for the relationships between cognitive abilities and socio-demographic, psychological and genetic factors. For this, we leveraged the unique power of the large-scale, longitudinal data from the Adolescent Brain Cognitive Development (ABCD) study (n ~ 11 k) and combined MRI data across modalities (task-fMRI from three tasks: resting-state fMRI, structural MRI and DTI) using machine-learning. Our brain-based, predictive models for cognitive abilities were stable across 2 years during young adolescence and generalisable to different sites, partially predicting childhood cognition at around 20% of the variance. Moreover, our use of 'opportunistic stacking' allowed the model to handle missing values, reducing the exclusion from around 80% to around 5% of the data. We found fronto-parietal networks during a working-memory task to drive childhood-cognition prediction. The brain-based, predictive models significantly, albeit partially, accounted for variance in childhood cognition due to (1) key socio-demographic and psychological factors (proportion mediated = 18.65% [17.29%-20.12%]) and (2) genetic variation, as reflected by the polygenic score of cognition (proportion mediated = 15.6% [11%-20.7%]). Thus, our brain-based predictive models for cognitive abilities facilitate the development of a robust, transdiagnostic research tool for cognition at the neural level in keeping with the RDoC's integrative framework.

Socioeconomic resources are associated with distributed alterations of the brain's intrinsic functional architecture in youth

Little is known about how exposure to limited socioeconomic resources (SER) in childhood gets "under the skin" to shape brain development, especially using rigorous whole-brain multivariate methods in large, adequately powered samples. The present study examined resting state functional connectivity patterns from 5821 youth in the Adolescent Brain Cognitive Development (ABCD) study, employing multivariate methods across three levels: whole-brain, network-wise, and connection-wise. Across all three levels, SER was associated with widespread alterations across the connectome. However, critically, we found that parental education was the primary driver of neural associations with SER. These parental education associations with the developing connectome exhibited notable concentrations in somatosensory and subcortical regions, and they were partially accounted for by home enrichment activities, child's cognitive abilities, and child's grades, indicating interwoven links between parental education, child stimulation, and child cognitive performance. These results add a new data-driven, multivariate perspective on links between household SER and the child's developing functional connectome.

Comparison of individualized behavioral predictions across anatomical, diffusion and functional connectivity MRI

A fundamental goal across the neurosciences is the characterization of relationships linking brain anatomy, functioning, and behavior. Although various MRI modalities have been developed to probe these relationships, direct comparisons of their ability to predict behavior have been lacking. Here, we compared the ability of anatomical T1, diffusion and functional MRI (fMRI) to predict behavior at an individual level. Cortical thickness, area and volume were extracted from anatomical T1 images. Diffusion Tensor Imaging (DTI) and approximate Neurite Orientation Dispersion and Density Imaging (NODDI) models were fitted to the diffusion images. The resulting metrics were projected to the Tract-Based Spatial Statistics (TBSS) skeleton. We also ran probabilistic tractography for the diffusion images, from which we extracted the stream count, average stream length, and the average of each DTI and NODDI metric across tracts connecting each pair of brain regions. Functional connectivity (FC) was extracted from both task and resting-state fMRI. Individualized prediction of a wide range of behavioral measures were performed using kernel ridge regression, linear ridge regression and elastic net regression. Consistency of the results were investigated with the Human Connectome Project (HCP) and Adolescent Brain Cognitive Development (ABCD) datasets. In both datasets, FC-based models gave the best prediction performance, regardless of regression model or behavioral measure. This was especially true for the cognitive component. Furthermore, all modalities were able to predict cognition better than other behavioral components. Combining all modalities improved prediction of cognition, but not other behavioral components. Finally, across all behaviors, combining resting and task FC yielded prediction performance similar to combining all modalities. Overall, our study suggests that in the case of healthy children and young adults, behaviorally-relevant information in T1 and diffusion features might reflect a subset of the variance captured by FC.

Interpreting Brain Biomarkers: Challenges and solutions in interpreting machine learning-based predictive neuroimaging

Predictive modeling of neuroimaging data (predictive neuroimaging) for evaluating individual differences in various behavioral phenotypes and clinical outcomes is of growing interest. However, the field is experiencing challenges regarding the interpretability of the results. Approaches to defining the specific contribution of functional connections, regions, or networks in prediction models are urgently needed, which may help explore the underlying mechanisms. In this article, we systematically review the methods and applications for interpreting brain signatures derived from predictive neuroimaging based on a survey of 326 research articles. Strengths, limitations, and the suitable conditions for major interpretation strategies are also deliberated. In-depth discussion of common issues in existing literature and the corresponding recommendations to address these pitfalls are provided. We highly recommend exhaustive validation on the reliability and interpretability of the biomarkers across multiple datasets and contexts, which thereby could translate technical advances in neuroimaging into concrete improvements in precision medicine.

Shared and unique brain network features predict cognitive, personality, and mental health scores in the ABCD study

How individual differences in brain network organization track behavioral variability is a fundamental question in systems neuroscience. Recent work suggests that resting-state and task-state functional connectivity can predict specific traits at the individual level. However, most studies focus on single behavioral traits, thus not capturing broader relationships across behaviors. In a large sample of 1858 typically developing children from the Adolescent Brain Cognitive Development (ABCD) study, we show that predictive network features are distinct across the domains of cognitive performance, personality scores and mental health assessments. On the other hand, traits within each behavioral domain are predicted by similar network features. Predictive network features and models generalize to other behavioral measures within the same behavioral domain. Although tasks are known to modulate the functional connectome, predictive network features are similar between resting and task states. Overall, our findings reveal shared brain network features that account for individual variation within broad domains of behavior in childhood.

A protocol for working with open-source neuroimaging datasets

Large, publicly available neuroimaging datasets are becoming increasingly common, but their use presents challenges because of insufficient knowledge of the tool options for data processing and proper data organization. Here, we describe a protocol to lessen these barriers. We describe the steps for the search and download of the open-source dataset. We detail the steps for proper data management and practical guidelines for data analysis. Finally, we give instructions for data and result sharing on public repositories and preprint services. For complete details on the use and execution of this profile, please refer to Horien et al. (2021).

Neuroimaging brain growth charts: A road to mental health

Mental disorders are common health concerns and contribute to a heavy global burden on our modern society. It is challenging to identify and treat them timely. Neuroimaging evidence suggests the incidence of various psychiatric and behavioral disorders is closely related to the atypical development of brain structure and function. The identification and understanding of atypical brain development provide chances for clinicians to detect mental disorders earlier, perhaps even prior to onset, and treat them more precisely. An invaluable and necessary method in identifying and monitoring atypical brain development are growth charts of typically developing individuals in the population. The brain growth charts can offer a series of standard references on typical neurodevelopment, representing an important resource for the scientific and medical communities. In the present paper, we review the relationship between mental disorders and atypical brain development from a perspective of normative brain development by surveying the recent progress in the development of brain growth charts, including four aspects on growth chart utility: 1) cohorts, 2) measures, 3) mechanisms, and 4) clinical translations. In doing so, we seek to clarify the challenges and opportunities in charting brain growth, and to promote the application of brain growth charts in clinical practice.

Brain-wide functional connectivity patterns support general cognitive ability and mediate effects of socioeconomic status in youth

General cognitive ability (GCA) is an individual difference dimension linked to important academic, occupational, and health-related outcomes and its development is strongly linked to differences in socioeconomic status (SES). Complex abilities of the human brain are realized through interconnections among distributed brain regions, but brain-wide connectivity patterns associated with GCA in youth, and the influence of SES on these connectivity patterns, are poorly understood. The present study examined functional connectomes from 5937 9- and 10-year-olds in the Adolescent Brain Cognitive Development (ABCD) multi-site study. Using multivariate predictive modeling methods, we identified whole-brain functional connectivity patterns linked to GCA. In leave-one-site-out cross-validation, we found these connectivity patterns exhibited strong and statistically reliable generalization at 19 out of 19 held-out sites accounting for 18.0% of the variance in GCA scores (cross-validated partial η²). GCA-related connections were remarkably dispersed across brain networks: across 120 sets of connections linking pairs of large-scale networks, significantly elevated GCA-related connectivity was found in 110 of them, and differences in levels of GCA-related connectivity across brain networks were notably modest. Consistent with prior work, socioeconomic status was a strong predictor of GCA in this sample, and we found that distributed GCA-related brain connectivity patterns significantly statistically mediated this relationship (mean proportion mediated: 15.6%, p < 2 × 10^-16). These results demonstrate that socioeconomic status and GCA are related to broad and diffuse differences in functional connectivity architecture during early adolescence, potentially suggesting a mechanism through which socioeconomic status influences cognitive development.

Altered neural networks and cognition in a hereditary colon cancer

Familial Adenomatous Polyposis (FAP) is an autosomal dominant disorder caused by mutation of the APC gene presenting with numerous colorectal adenomatous polyps and a near 100% risk of colon cancer. Preliminary research findings from our group indicate that FAP patients experience significant deficits across many cognitive domains. In the current study, fMRI brain metrics in a FAP population and matched controls were used to further the mechanistic understanding of reported cognitive deficits. This research identified and characterized any possible differences in resting brain networks and associations between neural network changes and cognition from 34 participants (18 FAP patients, 16 healthy controls). Functional connectivity analysis was performed using FSL with independent component analysis (ICA) to identify functional networks. Significant differences between cases and controls were observed in 8 well-established resting state networks. With the addition of an aggregate cognitive measure as a covariate, these differences were virtually non-existent, indicating a strong correlation between cognition and brain activity at the network level. The data indicate robust and pervasive effects on functional neural network activity among FAP patients and these effects are likely involved in cognitive deficits associated with this disease.

Exploring electroencephalography with a model inspired by quantum mechanics

An outstanding issue in cognitive neuroscience concerns how the brain is organized across different conditions. For instance, during the resting-state condition, the brain can be clustered into reliable and reproducible networks (e.g., sensory, default, executive networks). Interestingly, the same networks emerge during active conditions in response to various tasks. If similar patterns of neural activity have been found across diverse conditions, and therefore, different underlying processes and experiences of the environment, is the brain organized by a fundamental organizational principle? To test this, we applied mathematical formalisms borrowed from quantum mechanisms to model electroencephalogram (EEG) data. We uncovered a tendency for EEG signals to be localized in anterior regions of the brain during “rest”, and more uniformly distributed while engaged in a task (i.e., watching a movie). Moreover, we found analogous values to the Heisenberg uncertainty principle, suggesting a common underlying architecture of human brain activity in resting and task conditions. This underlying architecture manifests itself in the novel constant K_Brain, which is extracted from the brain state with the least uncertainty. We would like to state that we are using the mathematics of quantum mechanics, but not claiming that the brain behaves as a quantum object.

Beyond fingerprinting: Choosing predictive connectomes over reliable connectomes

Recent years have seen a surge of research on variability in functional brain connectivity within and between individuals, with encouraging progress toward understanding the consequences of this variability for cognition and behavior. At the same time, well-founded concerns over rigor and reproducibility in psychology and neuroscience have led many to question whether functional connectivity is sufficiently reliable, and call for methods to improve its reliability. The thesis of this opinion piece is that when studying variability in functional connectivity-both across individuals and within individuals over time-we should use behavior prediction as our benchmark rather than optimize reliability for its own sake. We discuss theoretical and empirical evidence to compel this perspective, both when the goal is to study stable, trait-level differences between people, as well as when the goal is to study state-related changes within individuals. We hope that this piece will be useful to the neuroimaging community as we continue efforts to characterize inter- and intra-subject variability in brain function and build predictive models with an eye toward eventual real-world applications.

Multi-Paradigm fMRI Fusion via Sparse Tensor Decomposition in Brain Functional Connectivity Study

Functional magnetic resonance imaging (fMRI) is a powerful technique with the potential to estimate individual variations in behavioral and cognitive traits. Joint learning of multiple datasets can utilize their complementary information so as to improve learning performance, but it also gives rise to the challenge for data fusion to effectively integrate brain patterns elicited by multiple fMRI data. However, most of the current data fusion methods analyze each single dataset separately and further infer the relationship among them, which fail to utilize the multidimensional structure inherent across modalities and may ignore complex but important interactions. To address this issue, we propose a novel sparse tensor decomposition method to integrate multiple task-stimulus (paradigm) fMRI data. Seeing each paradigm fMRI as one modality, our proposed method considers the relationships across subjects and modalities simultaneously. In specific, a third-order tensor is first modeled by using the functional network connectivity (FNC) of subjects in multiple fMRI paradigms. A novel sparse tensor decomposition with the regularization terms is designed to factorize the tensor into a series of rank-one components, which can extract the shared components across modalities as the embedded features. The L2,1-norm regularizer (i.e., group sparsity) is enforced to select a few common features among multiple subjects. Validation of the proposed method is performed on realistic three paradigm fMRI datasets from the Philadelphia Neurodevelopmental Cohort (PNC) study, for the study of the relationship between the FNC and human cognitive abilities. Experimental results show our method outperforms several other competing methods in the prediction of individuals with different cognitive behaviors via the wide range achievement test (WRAT). Furthermore, our method discovers the FNC related to the cognitive behaviors, such as the connectivity associated with the default mode network (DMN) for three paradigms, and the connectivity between DMN and visual (VIS) domains within the emotion task.

Individual Differences in Cognitive Performance Are Better Predicted by Global Rather Than Localized BOLD Activity Patterns Across the Cortex

Despite its central role in revealing the neurobiological mechanisms of behavior, neuroimaging research faces the challenge of producing reliable biomarkers for cognitive processes and clinical outcomes. Statistically significant brain regions, identified by mass univariate statistical models commonly used in neuroimaging studies, explain minimal phenotypic variation, limiting the translational utility of neuroimaging phenotypes. This is potentially due to the observation that behavioral traits are influenced by variations in neuroimaging phenotypes that are globally distributed across the cortex and are therefore not captured by thresholded, statistical parametric maps commonly reported in neuroimaging studies. Here, we developed a novel multivariate prediction method, the Bayesian polyvertex score, that turns a unthresholded statistical parametric map into a summary score that aggregates the many but small effects across the cortex for behavioral prediction. By explicitly assuming a globally distributed effect size pattern and operating on the mass univariate summary statistics, it was able to achieve higher out-of-sample variance explained than mass univariate and popular multivariate methods while still preserving the interpretability of a generative model. Our findings suggest that similar to the polygenicity observed in the field of genetics, the neural basis of complex behaviors may rest in the global patterning of effect size variation of neuroimaging phenotypes, rather than in localized, candidate brain regions and networks.

A hitchhiker's guide to working with large, open-source neuroimaging datasets

Large datasets that enable researchers to perform investigations with unprecedented rigor are growing increasingly common in neuroimaging. Due to the simultaneous increasing popularity of open science, these state-of-the-art datasets are more accessible than ever to researchers around the world. While analysis of these samples has pushed the field forward, they pose a new set of challenges that might cause difficulties for novice users. Here we offer practical tips for working with large datasets from the end-user's perspective. We cover all aspects of the data lifecycle: from what to consider when downloading and storing the data to tips on how to become acquainted with a dataset one did not collect and what to share when communicating results. This manuscript serves as a practical guide one can use when working with large neuroimaging datasets, thus dissolving barriers to scientific discovery.

Brain Mechanisms Supporting Flexible Cognition and Behavior in Adolescents With Autism Spectrum Disorder

Cognitive flexibility enables appropriate responses to a changing environment and is associated with positive life outcomes. Adolescence, with its increased focus on transitioning to independent living, presents particular challenges for youths with autism spectrum disorder (ASD) who often struggle to behave in a flexible way when faced with challenges. This review focuses on brain mechanisms underlying the development of flexible cognition during adolescence and how these neural systems are affected in ASD. Neuroimaging studies of task switching and set-shifting provide evidence for atypical lateral frontoparietal and midcingulo-insular network activation during cognitive flexibility task performance in individuals with ASD. Recent work also examines how intrinsic brain network dynamics support flexible cognition. These dynamic functional connectivity studies provide evidence for alterations in the number of transitions between brain states, as well as hypervariability of functional connections in adolescents with ASD. Future directions for the field include addressing issues related to measurement of cognitive flexibility using a combination of metrics with ecological and construct validity. Heterogeneity of executive function ability in ASD must also be parsed to determine which individuals will benefit most from targeted training to improve flexibility. The influence of pubertal hormones on brain network development and cognitive maturation in adolescents with ASD is another area requiring further exploration. Finally, the intriguing possibility that bilingualism might be associated with preserved cognitive flexibility in ASD should be further examined. Addressing these open questions will be critical for future translational neuroscience investigations of cognitive and behavioral flexibility in adolescents with ASD.

The ABCD study: understanding the development of risk for mental and physical health outcomes

Following in the footsteps of other large "population neuroscience" studies, the Adolescent Brain Cognitive Development℠ (ABCD) study is the largest in the U.S. assessing brain development. The study is examining approximately 11,875 youth from 21 sites from age 9 to 10 for approximately ten years into young adulthood. The ABCD Study® has completed recruitment for the baseline sample generally using a multi-stage probability sample including a stratified random sample of schools. The dataset has a wealth of measured attributes of youths and their environment, including neuroimaging, cognitive, biospecimen, behavioral, youth self-report and parent self-report metrics, and environmental measures. The initial goal of the ABCD Study was to examine risk and resiliency factors associated with the development of substance use, but the project has expanded far beyond this initial set of questions and will also greatly inform our understanding of the contributions of biospecimens (e.g., pubertal hormones), neural alterations, and environmental factors to the development of both healthy behavior and brain function as well as risk for poor mental and physical outcomes. This review outlines how the ABCD Study was designed to elucidate factors associated with the development of negative mental and physical health outcomes and will provide a selective overview of results emerging from the ABCD Study. Such emerging data includes initial validation of new instruments, important new information about the prevalence and correlates of mental health challenges in middle childhood, and promising data regarding neural correlates of both healthy and disordered behavior. In addition, we will discuss the challenges and opportunities to understanding both healthy development and the emergence of risk from ABCD Study data. Finally, we will overview the future directions of this large undertaking and the ways in which it will shape our understanding of the development of risk for poor mental and physical health outcomes.

Neuroimaging-based Individualized Prediction of Cognition and Behavior for Mental Disorders and Health: Methods and Promises

The neuroimaging community has witnessed a paradigm shift in biomarker discovery from using traditional univariate brain mapping approaches to multivariate predictive models, allowing the field to move toward a translational neuroscience era. Regression-based multivariate models (hereafter "predictive modeling") provide a powerful and widely used approach to predict human behavior with neuroimaging features. These studies maintain a focus on decoding individual differences in a continuously behavioral phenotype from neuroimaging data, opening up an exciting opportunity to describe the human brain at the single-subject level. In this survey, we provide an overview of recent studies that utilize machine learning approaches to identify neuroimaging predictors over the past decade. We first review regression-based approaches and highlight connectome-based predictive modeling, which has grown in popularity in recent years. Next, we systematically describe recent representative studies using these tools in the context of cognitive function, symptom severity, personality traits, and emotion processing. Finally, we highlight a few challenges related to combining multimodal data, longitudinal prediction, external validations, and the employment of deep learning methods that have emerged from our review of the existing literature, as well as present some promising and challenging future directions.

Altered Resting State Brain Networks and Cognition in Familial Adenomatous Polyposis

Familial Adenomatous Polyposis (FAP) is an autosomal dominant disorder caused by mutation of the APC gene presenting with numerous colorectal adenomatous polyps and a near 100% risk of colon cancer. Preliminary research findings from our group indicate that FAP patients experience significant deficits across many cognitive domains. In the current study, fMRI brain metrics in a FAP population and matched controls were used to further the mechanistic understanding of reported cognitive deficits. This research identified and characterized any possible differences in resting brain networks and associations between neural network changes and cognition from 34 participants (18 FAP patients, 16 healthy controls). Functional connectivity analysis was performed using FSL with independent component analysis (ICA) to identify functional networks. Significant differences between cases and controls were observed in 8 well-established resting state networks. With the addition of an aggregate cognitive measure as a covariate, these differences were virtually non-existent, indicating a strong correlation between cognition and brain activity at the network level. The data indicate robust and pervasive effects on functional neural network activity among FAP patients and these effects are likely involved in cognitive deficits associated with this disease.

Network communication models improve the behavioral and functional predictive utility of the human structural connectome

The connectome provides the structural substrate facilitating communication between brain regions. We aimed to establish whether accounting for polysynaptic communication in structural connectomes would improve prediction of interindividual variation in behavior as well as increase structure-function coupling strength. Connectomes were mapped for 889 healthy adults participating in the Human Connectome Project. To account for polysynaptic signaling, connectomes were transformed into communication matrices for each of 15 different network communication models. Communication matrices were (a) used to perform predictions of five data-driven behavioral dimensions and (b) correlated to resting-state functional connectivity (FC). While FC was the most accurate predictor of behavior, communication models, in particular communicability and navigation, improved the performance of structural connectomes. Communication also strengthened structure-function coupling, with the navigation and shortest paths models leading to 35-65% increases in association strength with FC. We combined behavioral and functional results into a single ranking that provides insight into which communication models may more faithfully recapitulate underlying neural signaling patterns. Comparing results across multiple connectome mapping pipelines suggested that modeling polysynaptic communication is particularly beneficial in sparse high-resolution connectomes. We conclude that network communication models can augment the functional and behavioral predictive utility of the human structural connectome.

Correlation Guided Graph Learning to Estimate Functional Connectivity Patterns From fMRI Data

OBJECTIVE

Recently, functional magnetic resonance imaging (fMRI)-derived brain functional connectivity (FC) patterns have been used as fingerprints to predict individual differences in phenotypic measures, and cognitive dysfunction associated with brain diseases. In these applications, how to accurately estimate FC patterns is crucial yet technically challenging.

METHODS

In this article, we propose a correlation guided graph learning (CGGL) method to estimate FC patterns for establishing brain-behavior relationships. Different from the existing graph learning methods which only consider the graph structure across brain regions-of-interest (ROIs), our proposed CGGL takes into account both the temporal correlation of ROIs across time points, and the graph structure across ROIs. The resulting FC patterns reflect substantial inter-individual variations related to the behavioral measure of interest.

RESULTS

We validate the effectiveness of our proposed CGGL on the Philadelphia Neurodevelopmental Cohort data for separately predicting three behavioral measures based on resting-state fMRI. Experimental results demonstrate that the proposed CGGL outperforms other competing FC pattern estimation methods.

CONCLUSION

Our method increases the predictive power of the constructed FC patterns when establishing brain-behavior relationships, and gains meaningful insights into relevant biological mechanisms.

SIGNIFICANCE

The proposed CGGL offers a more powerful, and reliable method to estimate FC patterns, which can be used as fingerprints in many brain network studies.