Accurate prediction of individual subject identity and task, but not autism diagnosis, from functional connectomes

Replication of a neuroimaging biomarker for striatal dysfunction in psychosis

To bring biomarkers closer to clinical application, they should be generalizable, reliable, and maintain performance within the constraints of routine clinical conditions. The functional striatal abnormalities (FSA), is among the most advanced neuroimaging biomarkers in schizophrenia, trained to discriminate diagnosis, with post-hoc analyses indicating prognostic properties. Here, we attempt to replicate its diagnostic capabilities measured by the area under the curve (AUC) in receiver operator characteristic curves discriminating individuals with psychosis (n = 101) from healthy controls (n = 51) in the Human Connectome Project for Early Psychosis. We also measured the test-retest (run 1 vs 2) and phase encoding direction (i.e., AP vs PA) reliability with intraclass correlation coefficients (ICC). Additionally, we measured effects of scan length on classification accuracy (i.e., AUCs) and reliability (i.e., ICCs). Finally, we tested the prognostic capability of the FSA by the correlation between baseline scores and symptom improvement over 12 weeks of antipsychotic treatment in a separate cohort (n = 97). Similar analyses were conducted for the Yeo networks intrinsic connectivity as a reference. The FSA had good/excellent diagnostic discrimination (AUC = 75.4%, 95% CI = 67.0-83.3%; in non-affective psychosis AUC = 80.5%, 95% CI = 72.1-88.0%, and in affective psychosis AUC = 58.7%, 95% CI = 44.2-72.0%). Test-retest reliability ranged between ICC = 0.48 (95% CI = 0.35-0.59) and ICC = 0.22 (95% CI = 0.06-0.36), which was comparable to that of networks intrinsic connectivity. Phase encoding direction reliability for the FSA was ICC = 0.51 (95% CI = 0.42-0.59), generally lower than for networks intrinsic connectivity. By increasing scan length from 2 to 10 min, diagnostic classification of the FSA increased from AUC = 71.7% (95% CI = 63.1-80.3%) to 75.4% (95% CI = 67.0-83.3%) and phase encoding direction reliability from ICC = 0.29 (95% CI = 0.14-0.43) to ICC = 0.51 (95% CI = 0.42-0.59). FSA scores did not correlate with symptom improvement. These results reassure that the FSA is a generalizable diagnostic - but not prognostic - biomarker. Given the replicable results of the FSA as a diagnostic biomarker trained on case-control datasets, next the development of prognostic biomarkers should be on treatment-response data.

Brain Functional Connectivity and Anatomical Features as Predictors of Cognitive Behavioral Therapy Outcome for Anxiety in Youths

Background

Because pediatric anxiety disorders precede the onset of many other problems, successful prediction of response to the first-line treatment, cognitive-behavioral therapy (CBT), could have major impact. However, existing clinical models are weakly predictive. The current study evaluates whether structural and resting-state functional magnetic resonance imaging can predict post-CBT anxiety symptoms.

Methods

Two datasets were studied: (A) one consisted of n=54 subjects with an anxiety diagnosis, who received 12 weeks of CBT, and (B) one consisted of n=15 subjects treated for 8 weeks. Connectome Predictive Modeling (CPM) was used to predict treatment response, as assessed with the PARS; additionally we investigated models using anatomical features, instead of functional connectivity. The main analysis included network edges positively correlated with treatment outcome, and age, sex, and baseline anxiety severity as predictors. Results from alternative models and analyses also are presented. Model assessments utilized 1000 bootstraps, resulting in a 95% CI for R2, r and mean absolute error (MAE).

Outcomes

The main model showed a mean absolute error of approximately 3.5 (95%CI: [3.1-3.8]) points a R2 of 0.08 [-0.14 - 0.26] and r of 0.38 [0.24 - 0.511]. When testing this model in the left-out sample (B) the results were similar, with a MAE of 3.4 [2.8 - 4.7], R2-0.65 [-2.29 - 0.16] and r of 0.4 [0.24 - 0.54]. The anatomical metrics showed a similar pattern, where models rendered overall low R2.

Interpretation

The analysis showed that models based on earlier promising results failed to predict clinical outcomes. Despite the small sample size, the current study does not support extensive use of CPM to predict outcome in pediatric anxiety.

Unifying pairwise interactions in complex dynamics

Scientists have developed hundreds of techniques to measure the interactions between pairs of processes in complex systems, but these computational methods-from contemporaneous correlation coefficients to causal inference methods-define and formulate interactions differently, using distinct quantitative theories that remain largely disconnected. Here we introduce a large assembled library of 237 statistics of pairwise interactions, and assess their behavior on 1,053 multivariate time series from a wide range of real-world and model-generated systems. Our analysis highlights commonalities between disparate mathematical formulations of interactions, providing a unified picture of a rich interdisciplinary literature. Using three real-world case studies, we then show that simultaneously leveraging diverse methods can uncover those most suitable for addressing a given problem, facilitating interpretable understanding of the quantitative formulation of pairwise dependencies that drive successful performance. Our results and accompanying software enable comprehensive analysis of time-series interactions by drawing on decades of diverse methodological contributions.

Replication of a neuroimaging biomarker for striatal dysfunction in psychosis

To bring biomarkers closer to clinical application, they should be generalizable, reliable, and maintain performance within the constraints of routine clinical conditions. The functional striatal abnormalities (FSA), is among the most advanced neuroimaging biomarkers in schizophrenia, trained to discriminate diagnosis, with post-hoc analyses indicating prognostic properties. Here, we attempt to replicate its diagnostic capabilities measured by the area under the curve (AUC) in receiver operator characteristic curves discriminating individuals with psychosis (n=101) from healthy controls (n=51) in the Human Connectome Project for Early Psychosis. We also measured the test-retest (run 1 vs 2) and phase encoding direction (i.e., AP vs PA) reliability with intraclass correlation coefficients (ICC). Additionally, we measured effects of scan length on classification accuracy (i.e., AUCs) and reliability (i.e., ICCs). Finally, we tested the prognostic capability of the FSA by the correlation between baseline scores and symptom improvement over 12 weeks of antipsychotic treatment in a separate cohort (n=97). Similar analyses were conducted for the Yeo networks intrinsic connectivity as a reference. The FSA had good/excellent diagnostic discrimination (AUC=75.4%, 95%CI=67.0%-83.3%; in non-affective psychosis AUC=80.5%, 95%CI=72.1-88.0%, and in affective psychosis AUC=58.7%, 95%CI=44.2-72.0%). Test-retest reliability ranged between ICC=0.48 (95%CI=0.35-0.59) and ICC=0.22 (95%CI=0.06-0.36), which was comparable to that of networks intrinsic connectivity. Phase encoding direction reliability for the FSA was ICC=0.51 (95%CI=0.42-0.59), generally lower than for networks intrinsic connectivity. By increasing scan length from 2 to 10 minutes, diagnostic classification of the FSA increased from AUC=71.7% (95%CI=63.1%-80.3%) to 75.4% (95%CI=67.0%-83.3%) and phase encoding direction reliability from ICC=0.29 (95%CI=0.14-0.43) to ICC=0.51 (95%CI=0.42-0.59). FSA scores did not correlate with symptom improvement. These results reassure that the FSA is a generalizable diagnostic - but not prognostic - biomarker. Given the replicable results of the FSA as a diagnostic biomarker trained on case-control datasets, next the development of prognostic biomarkers should be on treatment-response data.

Replication of a neuroimaging biomarker for striatal dysfunction in psychosis

To bring biomarkers closer to clinical application, they should be generalizable, reliable, and maintain performance within the constraints of routine clinical conditions. The functional striatal abnormalities (FSA), is among the most advanced neuroimaging biomarkers in schizophrenia, trained to discriminate diagnosis, with post-hoc analyses indicating prognostic properties. Here, we attempt to replicate its diagnostic capabilities measured by the area under the curve (AUC) in receiver operator characteristic curves discriminating individuals with psychosis (n=101) from healthy controls (n=51) in the Human Connectome Project for Early Psychosis. We also measured the test-retest (run 1 vs 2) and phase encoding direction (i.e., AP vs PA) reliability with intraclass correlation coefficients (ICC). Additionally, we measured effects of scan length on classification accuracy (i.e., AUCs) and reliability (i.e., ICCs). Finally, we tested the prognostic capability of the FSA by the correlation between baseline scores and symptom improvement over 12 weeks of antipsychotic treatment in a separate cohort (n=97). Similar analyses were conducted for the Yeo networks intrinsic connectivity as a reference. The FSA had good/excellent diagnostic discrimination (AUC=75.4%, 95%CI=67.0%-83.3%; in non-affective psychosis AUC=80.5%, 95%CI=72.1-88.0%, and in affective psychosis AUC=58.7%, 95%CI=44.2-72.0%). Test-retest reliability ranged between ICC=0.48 (95%CI=0.35-0.59) and ICC=0.22 (95%CI=0.06-0.36), which was comparable to that of networks intrinsic connectivity. Phase encoding direction reliability for the FSA was ICC=0.51 (95%CI=0.42-0.59), generally lower than for networks intrinsic connectivity. By increasing scan length from 2 to 10 minutes, diagnostic classification of the FSA increased from AUC=71.7% (95%CI=63.1%-80.3%) to 75.4% (95%CI=67.0%-83.3%) and phase encoding direction reliability from ICC=0.29 (95%CI=0.14-0.43) to ICC=0.51 (95%CI=0.42-0.59). FSA scores did not correlate with symptom improvement. These results reassure that the FSA is a generalizable diagnostic - but not prognostic - biomarker. Given the replicable results of the FSA as a diagnostic biomarker trained on case-control datasets, next the development of prognostic biomarkers should be on treatment-response data.

Functional Connectome-Based Predictive Modeling in Autism

Autism is a heterogeneous neurodevelopmental condition, and functional magnetic resonance imaging-based studies have helped advance our understanding of its effects on brain network activity. We review how predictive modeling, using measures of functional connectivity and symptoms, has helped reveal key insights into this condition. We discuss how different prediction frameworks can further our understanding of the brain-based features that underlie complex autism symptomatology and consider how predictive models may be used in clinical settings. Throughout, we highlight aspects of study interpretation, such as data decay and sampling biases, that require consideration within the context of this condition. We close by suggesting exciting future directions for predictive modeling in autism.

Edge-centric analysis of time-varying functional brain networks with applications in autism spectrum disorder

The interaction between brain regions changes over time, which can be characterized using time-varying functional connectivity (tvFC). The common approach to estimate tvFC uses sliding windows and offers limited temporal resolution. An alternative method is to use the recently proposed edge-centric approach, which enables the tracking of moment-to-moment changes in co-fluctuation patterns between pairs of brain regions. Here, we first examined the dynamic features of edge time series and compared them to those in the sliding window tvFC (sw-tvFC). Then, we used edge time series to compare subjects with autism spectrum disorder (ASD) and healthy controls (CN). Our results indicate that relative to sw-tvFC, edge time series captured rapid and bursty network-level fluctuations that synchronize across subjects during movie-watching. The results from the second part of the study suggested that the magnitude of peak amplitude in the collective co-fluctuations of brain regions (estimated as root sum square (RSS) of edge time series) is similar in CN and ASD. However, the trough-to-trough duration in RSS signal is greater in ASD, compared to CN. Furthermore, an edge-wise comparison of high-amplitude co-fluctuations showed that the within-network edges exhibited greater magnitude fluctuations in CN. Our findings suggest that high-amplitude co-fluctuations captured by edge time series provide details about the disruption of functional brain dynamics that could potentially be used in developing new biomarkers of mental disorders.

Combination of structural and functional connectivity explains unique variation in specific domains of cognitive function

The relationship between structural and functional brain networks has been characterised as complex: the two networks mirror each other and show mutual influence but they also diverge in their organisation. This work explored whether a combination of structural and functional connectivity can improve the fit of regression models of cognitive performance. Principal Component Analysis (PCA) was first applied to cognitive data from the Human Connectome Project to identify latent cognitive components: Executive Function, Self-regulation, Language, Encoding and Sequence Processing. A Principal Component Regression approach with embedded Step-Wise Regression (SWR-PCR) was then used to fit regression models of each cognitive domain based on structural (SC), functional (FC) or combined structural-functional (CC) connectivity. Executive Function was best explained by the CC model. Self-regulation was equally well explained by SC and FC. Language was equally well explained by CC and FC models. Encoding and Sequence Processing were best explained by SC. Evaluation of out-of-sample models' skill via cross-validation showed that SC, FC and CC produced generalisable models of Language performance. SC models performed most effectively at predicting Language performance in unseen sample. Executive Function was most effectively predicted by SC models, followed only by CC models. Self-regulation was only effectively predicted by CC models and Sequence Processing was only effectively predicted by FC models. The present study demonstrates that integrating structural and functional connectivity can help explaining cognitive performance, but that the added explanatory value (in sample) may be domain-specific and can come at the expense of reduced generalisation performance (out-of-sample).

Video-evoked fMRI BOLD responses are highly consistent across different data acquisition sites

Naturalistic imaging paradigms, in which participants view complex videos in the scanner, are increasingly used in human cognitive neuroscience. Videos evoke temporally synchronized brain responses that are similar across subjects as well as within subjects, but the reproducibility of these brain responses across different data acquisition sites has not yet been quantified. Here, we characterize the consistency of brain responses across independent samples of participants viewing the same videos in functional magnetic resonance imaging (fMRI) scanners at different sites (Indiana University and Caltech). We compared brain responses collected at these different sites for two carefully matched datasets with identical scanner models, acquisition, and preprocessing details, along with a third unmatched dataset in which these details varied. Our overall conclusion is that for matched and unmatched datasets alike, video-evoked brain responses have high consistency across these different sites, both when compared across groups and across pairs of individuals. As one might expect, differences between sites were larger for unmatched datasets than matched datasets. Residual differences between datasets could in part reflect participant-level variability rather than scanner- or data- related effects. Altogether our results indicate promise for the development and, critically, generalization of video fMRI studies of individual differences in healthy and clinical populations alike.

Brain connectivity fingerprinting and behavioural prediction rest on distinct functional systems of the human connectome

The prediction of inter-individual behavioural differences from neuroimaging data is a rapidly evolving field of research focusing on individualised methods to describe human brain organisation on the single-subject level. One method that harnesses such individual signatures is functional connectome fingerprinting, which can reliably identify individuals from large study populations. However, the precise relationship between functional signatures underlying fingerprinting and behavioural prediction remains unclear. Expanding on previous reports, here we systematically investigate the link between discrimination and prediction on different levels of brain network organisation (individual connections, network interactions, topographical organisation, and connection variability). Our analysis revealed a substantial divergence between discriminatory and predictive connectivity signatures on all levels of network organisation. Across different brain parcellations, thresholds, and prediction algorithms, we find discriminatory connections in higher-order multimodal association cortices, while neural correlates of behaviour display more variable distributions. Furthermore, we find the standard deviation of connections between participants to be significantly higher in fingerprinting than in prediction, making inter-individual connection variability a possible separating marker. These results demonstrate that participant identification and behavioural prediction involve highly distinct functional systems of the human connectome. The present study thus calls into question the direct functional relevance of connectome fingerprints.

Mantwill et al. analysed the relationship between functional connectivity markers that are specific to individuals (i.e. brain fingerprints) and those predictive of behaviour. They reveal that these markers are unrelated and suggest an alternative perspective on the basis of individual signatures.

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.

High-amplitude cofluctuations in cortical activity drive functional connectivity

Resting-state functional connectivity is used throughout neuroscience to study brain organization and to generate biomarkers of development, disease, and cognition. The processes that give rise to correlated activity are, however, poorly understood. Here we decompose resting-state functional connectivity using a temporal unwrapping procedure to assess the contributions of moment-to-moment activity cofluctuations to the overall connectivity pattern. This approach temporally resolves functional connectivity at a timescale of single frames, which enables us to make direct comparisons of cofluctuations of network organization with fluctuations in the blood oxygen level-dependent (BOLD) time series. We show that surprisingly, only a small fraction of frames exhibiting the strongest cofluctuation amplitude are required to explain a significant fraction of variance in the overall pattern of connection weights as well as the network's modular structure. These frames coincide with frames of high BOLD activity amplitude, corresponding to activity patterns that are remarkably consistent across individuals and identify fluctuations in default mode and control network activity as the primary driver of resting-state functional connectivity. Finally, we demonstrate that cofluctuation amplitude synchronizes across subjects during movie watching and that high-amplitude frames carry detailed information about individual subjects (whereas low-amplitude frames carry little). Our approach reveals fine-scale temporal structure of resting-state functional connectivity and discloses that frame-wise contributions vary across time. These observations illuminate the relation of brain activity to functional connectivity and open a number of directions for future research.

Accurate prediction of individual subject identity and task, but not autism diagnosis, from functional connectomes

Despite enthusiasm about the potential for using fMRI-based functional connectomes in the development of biomarkers for autism spectrum disorder (ASD), the literature is full of negative findings-failures to distinguish ASD functional connectomes from those of typically developing controls (TD)-and positive findings that are inconsistent across studies. Here, we report on a new study designed to either better differentiate ASD from TD functional connectomes-or, alternatively, to refine our understanding of the factors underlying the current state of affairs. We scanned individuals with ASD and controls both at rest and while watching videos with social content. Using multiband fMRI across repeat sessions, we improved both data quantity and scanning duration by collecting up to 2 hr of data per individual. This is about 50 times the typical number of temporal samples per individual in ASD fcMRI studies. We obtained functional connectomes that were discriminable, allowing for near-perfect individual identification regardless of diagnosis, and equally reliable in both groups. However, contrary to what one might expect, we did not consistently or robustly observe in the ASD group either reductions in similarity to TD functional connectivity (FC) patterns or shared atypical FC patterns. Accordingly, FC-based predictions of diagnosis group achieved accuracy levels around chance. However, using the same approaches to predict scan type (rest vs. video) achieved near-perfect accuracy. Our findings suggest that neither the limitations of resting state as a "task," data resolution, data quantity, or scan duration can be considered solely responsible for failures to differentiate ASD from TD functional connectomes.