Search

Background: Mental disorders and individual characteristics such as intelligence and personality are complex traits sharing a largely unknown neuronal basis. Their genetic architectures are highly polygenic and overlapping, which is supported by heterogeneous phenotypic expression and substantial clinical overlap. Brain network analysis provides a noninvasive means of dissecting biological heterogeneity, yet its sensitivity, specificity, and validity in assessing individual characteristics relevant for brain function and mental health and their genetic underpinnings in clinical applications remain a challenge., Methods: In a machine learning approach, we predicted individual scores for educational attainment, fluid intelligence and dimensional measures of depression, anxiety, and neuroticism using functional magnetic resonance imaging-based static and dynamic temporal synchronization between large-scale brain network nodes in 10,343 healthy individuals from the UK Biobank. In addition to using age and sex to serve as our reference point, we also predicted individual polygenic scores for related phenotypes and 13 different neuroticism traits and schizophrenia., Results: Beyond high accuracy for age and sex, supporting the biological sensitivity of the connectome-based features, permutation tests revealed above chance-level prediction accuracy for trait-level educational attainment and fluid intelligence. Educational attainment and fluid intelligence were mainly negatively associated with static brain connectivity in frontal and default mode networks, whereas age showed positive correlations with a more widespread pattern. In contrast, prediction accuracy was at chance level for depression, anxiety, neuroticism, and polygenic scores across traits., Conclusions: These novel findings provide a benchmark for future studies linking the genetic architecture of individual and mental health traits with functional magnetic resonance imaging-based brain connectomics., (Copyright © 2019 Society of Biological Psychiatry. All rights reserved.)

Network connectivity fingerprints are among today's best choices to obtain a faithful sampling of an individual's brain and cognition. Widely available MRI scanners can provide rich information tapping into network recruitment and reconfiguration that now scales to hundreds and thousands of humans. Here, we contemplate the advantages of analysing such connectome profiles using Bayesian strategies. These analysis techniques afford full probability estimates of the studied network coupling phenomena, provide analytical machinery to separate epistemological uncertainty and biological variability in a coherent manner, usher us towards avenues to go beyond binary statements on existence versus non-existence of an effect, and afford credibility estimates around all model parameters at play which thus enable single-subject predictions with rigorous uncertainty intervals. We illustrate the brittle boundary between healthy and diseased brain circuits by autism spectrum disorder as a recurring theme where, we argue, network-based approaches in neuroscience will require careful probabilistic answers. This article is part of the theme issue 'Unifying the essential concepts of biological networks: biological insights and philosophical foundations'.

The cerebral cortex underlies our complex cognitive capabilities, yet little is known about the specific genetic loci that influence human cortical structure. To identify genetic variants that affect cortical structure, we conducted a genome-wide association meta-analysis of brain magnetic resonance imaging data from 51,665 individuals. We analyzed the surface area and average thickness of the whole cortex and 34 regions with known functional specializations. We identified 199 significant loci and found significant enrichment for loci influencing total surface area within regulatory elements that are active during prenatal cortical development, supporting the radial unit hypothesis. Loci that affect regional surface area cluster near genes in Wnt signaling pathways, which influence progenitor expansion and areal identity. Variation in cortical structure is genetically correlated with cognitive function, Parkinson's disease, insomnia, depression, neuroticism, and attention deficit hyperactivity disorder., (Copyright © 2020 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works.)

In human and nonhuman primates, sex differences typically explain much interindividual variability. Male and female behaviors may have played unique roles in the likely coevolution of increasing brain volume and more complex social dynamics. To explore possible divergence in social brain morphology between men and women living in different social environments, we applied probabilistic generative modeling to ~10,000 UK Biobank participants. We observed strong volume effects especially in the limbic system but also in regions of the sensory, intermediate, and higher association networks. Sex-specific brain volume effects in the limbic system were linked to the frequency and intensity of social contact, such as indexed by loneliness, household size, and social support. Across the processing hierarchy of neural networks, different conditions for social interplay may resonate in and be influenced by brain anatomy in sex-dependent ways., (Copyright © 2020 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution NonCommercial License 4.0 (CC BY-NC).)

Patients with major depressive disorder (MDD) show heterogeneous treatment response and highly variable clinical trajectories: while some patients experience swift recovery, others show relapsing-remitting or chronic courses. Predicting individual clinical trajectories at an early stage is a key challenge for psychiatry and might facilitate individually tailored interventions. So far, however, reliable predictors at the single-patient level are absent. Here, we evaluated the utility of a machine learning strategy - generative embedding (GE) - which combines interpretable generative models with discriminative classifiers. Specifically, we used functional magnetic resonance imaging (fMRI) data of emotional face perception in 85 MDD patients from the NEtherlands Study of Depression and Anxiety (NESDA) who had been followed up over two years and classified into three subgroups with distinct clinical trajectories. Combining a generative model of effective (directed) connectivity with support vector machines (SVMs), we could predict whether a given patient would experience chronic depression vs. fast remission with a balanced accuracy of 79%. Gradual improvement vs. fast remission could still be predicted above-chance, but less convincingly, with a balanced accuracy of 61%. Generative embedding outperformed classification based on conventional (descriptive) features, such as functional connectivity or local activation estimates, which were obtained from the same data and did not allow for above-chance classification accuracy. Furthermore, predictive performance of GE could be assigned to a specific network property: the trial-by-trial modulation of connections by emotional content. Given the limited sample size of our study, the present results are preliminary but may serve as proof-of-concept, illustrating the potential of GE for obtaining clinical predictions that are interpretable in terms of network mechanisms. Our findings suggest that abnormal dynamic changes of connections involved in emotional face processing might be associated with higher risk of developing a less favorable clinical course., Competing Interests: Declaration of Competing Interest The authors report no conflict of interest., (Copyright © 2020 The Author(s). Published by Elsevier Inc. All rights reserved.)

Background: The present paper presents a fundamentally novel approach to model individual differences of persons with the same biologically heterogeneous mental disorder. Unlike prevalent case-control analyses, that assume a clear distinction between patient and control groups and thereby introducing the concept of an 'average patient', we describe each patient's biology individually, gaining insights into the different facets that characterize persistent attention-deficit/hyperactivity disorder (ADHD)., Methods: Using a normative modeling approach, we mapped inter-individual differences in reference to normative structural brain changes across the lifespan to examine the degree to which case-control analyses disguise differences between individuals., Results: At the level of the individual, deviations from the normative model were frequent in persistent ADHD. However, the overlap of more than 2% between participants with ADHD was only observed in few brain loci. On average, participants with ADHD showed significantly reduced gray matter in the cerebellum and hippocampus compared to healthy individuals. While the case-control differences were in line with the literature on ADHD, individuals with ADHD only marginally reflected these group differences., Conclusions: Case-control comparisons, disguise inter-individual differences in brain biology in individuals with persistent ADHD. The present results show that the 'average ADHD patient' has limited informative value, providing the first evidence for the necessity to explore different biological facets of ADHD at the level of the individual and practical means to achieve this end.

Subcortical brain structures are integral to motion, consciousness, emotions and learning. We identified common genetic variation related to the volumes of the nucleus accumbens, amygdala, brainstem, caudate nucleus, globus pallidus, putamen and thalamus, using genome-wide association analyses in almost 40,000 individuals from CHARGE, ENIGMA and UK Biobank. We show that variability in subcortical volumes is heritable, and identify 48 significantly associated loci (40 novel at the time of analysis). Annotation of these loci by utilizing gene expression, methylation and neuropathological data identified 199 genes putatively implicated in neurodevelopment, synaptic signaling, axonal transport, apoptosis, inflammation/infection and susceptibility to neurological disorders. This set of genes is significantly enriched for Drosophila orthologs associated with neurodevelopmental phenotypes, suggesting evolutionarily conserved mechanisms. Our findings uncover novel biology and potential drug targets underlying brain development and disease.

Normative models are a class of emerging statistical techniques useful for understanding the heterogeneous biology underlying psychiatric disorders at the level of the individual participant. Analogous to normative growth charts used in paediatric medicine for plotting child development in terms of height or weight as a function of age, normative models chart variation in clinical cohorts in terms of mappings between quantitative biological measures and clinically relevant variables. An emerging body of literature has demonstrated that such techniques are excellent tools for parsing the heterogeneity in clinical cohorts by providing statistical inferences at the level of the individual participant with respect to the normative range. Here, we provide a unifying review of the theory and application of normative modelling for understanding the biological and clinical heterogeneity underlying mental disorders. We first provide a statistically grounded yet non-technical overview of the conceptual underpinnings of normative modelling and propose a conceptual framework to link the many different methodological approaches that have been proposed for this purpose. We survey the literature employing these techniques, focusing principally on applications of normative modelling to quantitative neuroimaging-based biomarkers in psychiatry and, finally, we provide methodological considerations and recommendations to guide future applications of these techniques. We show that normative modelling provides a means by which the importance of modelling individual differences can be brought from theory to concrete data analysis procedures for understanding heterogeneous mental disorders and ultimately a promising route towards precision medicine in psychiatry.

Pattern classification and stratification approaches have increasingly been used in research on Autism Spectrum Disorder (ASD) over the last ten years with the goal of translation towards clinical applicability. Here, we present an extensive scoping literature review on those two approaches. We screened a total of 635 studies, of which 57 pattern classification and 19 stratification studies were included. We observed large variance across pattern classification studies in terms of predictive performance from about 60% to 98% accuracy, which is among other factors likely linked to sampling bias, different validation procedures across studies, the heterogeneity of ASD and differences in data quality. Stratification studies were less prevalent with only two studies reporting replications and just a few showing external validation. While some identified strata based on cognition and intelligence reappear across studies, biology as a stratification marker is clearly underexplored. In summary, mapping biological differences at the level of the individual with ASD is a major challenge for the field now. Conceptualizing those mappings and individual trajectories that lead to the diagnosis of ASD, will become a major challenge in the near future., (Copyright © 2019 Elsevier Ltd. All rights reserved.)

Longitudinal imaging biomarkers are invaluable for understanding the course of neurodegeneration, promising the ability to track disease progression and to detect disease earlier than cross-sectional biomarkers. To properly realize their potential, biomarker trajectory models must be robust to both under-sampling and measurement errors and should be able to integrate multi-modal information to improve trajectory inference and prediction. Here we present a parametric Bayesian multi-task learning based approach to modeling univariate trajectories across subjects that addresses these criteria. Our approach learns multiple subjects' trajectories within a single model that allows for different types of information sharing, that is, coupling, across subjects. It optimizes a combination of uncoupled, fully coupled and kernel coupled models. Kernel-based coupling allows linking subjects' trajectories based on one or more biomarker measures. We demonstrate this using Alzheimer's Disease Neuroimaging Initiative (ADNI) data, where we model longitudinal trajectories of MRI-derived cortical volumes in neurodegeneration, with coupling based on APOE genotype, cerebrospinal fluid (CSF) and amyloid PET-based biomarkers. In addition to detecting established disease effects, we detect disease related changes within the insula that have not received much attention within the literature. Due to its sensitivity in detecting disease effects, its competitive predictive performance and its ability to learn the optimal parameter covariance from data rather than choosing a specific set of random and fixed effects a priori, we propose that our model can be used in place of or in addition to linear mixed effects models when modeling biomarker trajectories. A software implementation of the method is publicly available., (© 2019 The Authors. Human Brain Mapping published by Wiley Periodicals, Inc.)

Background: A diagnosis of dissociative identity disorder (DID) is controversial and prone to under- and misdiagnosis. From the moment of seeking treatment for symptoms to the time of an accurate diagnosis of DID individuals received an average of four prior other diagnoses and spent 7 years, with reports of up to 12 years, in mental health services., Aim: To investigate whether data-driven pattern recognition methodologies applied to structural brain images can provide biomarkers to aid DID diagnosis., Method: Structural brain images of 75 participants were included: 32 female individuals with DID and 43 matched healthy controls. Individuals with DID were recruited from psychiatry and psychotherapy out-patient clinics. Probabilistic pattern classifiers were trained to discriminate cohorts based on measures of brain morphology., Results: The pattern classifiers were able to accurately discriminate between individuals with DID and healthy controls with high sensitivity (72%) and specificity (74%) on the basis of brain structure. These findings provide evidence for a biological basis for distinguishing between DID-affected and healthy individuals., Conclusions: We propose a pattern of neuroimaging biomarkers that could be used to inform the identification of individuals with DID from healthy controls at the individual level. This is important and clinically relevant because the DID diagnosis is controversial and individuals with DID are often misdiagnosed. Ultimately, the application of pattern recognition methodologies could prevent unnecessary suffering of individuals with DID because of an earlier accurate diagnosis, which will facilitate faster and targeted interventions., Declaration of Interest: The authors declare no competing financial interests.

Background: The neuroanatomical basis of autism spectrum disorder (ASD) has remained elusive, mostly owing to high biological and clinical heterogeneity among diagnosed individuals. Despite considerable effort toward understanding ASD using neuroimaging biomarkers, heterogeneity remains a barrier, partly because studies mostly employ case-control approaches, which assume that the clinical group is homogeneous., Methods: Here, we used an innovative normative modeling approach to parse biological heterogeneity in ASD. We aimed to dissect the neuroanatomy of ASD by mapping the deviations from a typical pattern of neuroanatomical development at the level of the individual and to show the necessity to look beyond the case-control paradigm to understand the neurobiology of ASD. We first estimated a vertexwise normative model of cortical thickness development using Gaussian process regression, then mapped the deviation of each participant from the typical pattern. For this, we employed a heterogeneous cross-sectional sample of 206 typically developing individuals (127 males) and 321 individuals with ASD (232 males) (6-31 years of age)., Results: We found few case-control differences, but the ASD cohort showed highly individualized patterns of deviations in cortical thickness that were widespread across the brain. These deviations correlated with severity of repetitive behaviors and social communicative symptoms, although only repetitive behaviors survived corrections for multiple testing., Conclusions: Our results 1) reinforce the notion that individuals with ASD show distinct, highly individualized trajectories of brain development and 2) show that by focusing on common effects (i.e., the "average ASD participant"), the case-control approach disguises considerable interindividual variation crucial for precision medicine., (Copyright © 2019 Society of Biological Psychiatry. Published by Elsevier Inc. All rights reserved.)

Background: Psychiatric disorders are highly heterogeneous, defined based on symptoms with little connection to potential underlying biological mechanisms. A possible approach to dissect biological heterogeneity is to look for biologically meaningful subtypes. A recent study Drysdale et al. (2017) showed promising results along this line by simultaneously using resting state fMRI and clinical data and identified four distinct subtypes of depression with different clinical profiles and abnormal resting state fMRI connectivity. These subtypes were predictive of treatment response to transcranial magnetic stimulation therapy., Objective: Here, we attempted to replicate the procedure followed in the Drysdale et al. study and their findings in a different clinical population and a more heterogeneous sample of 187 participants with depression and anxiety. We aimed to answer the following questions: 1) Using the same procedure, can we find a statistically significant and reliable relationship between brain connectivity and clinical symptoms? 2) Is the observed relationship similar to the one found in the original study? 3) Can we identify distinct and reliable subtypes? 4) Do they have similar clinical profiles as the subtypes identified in the original study?, Methods: We followed the original procedure as closely as possible, including a canonical correlation analysis to find a low dimensional representation of clinically relevant resting state fMRI features, followed by hierarchical clustering to identify subtypes. We extended the original procedure using additional statistical tests, to test the statistical significance of the relationship between resting state fMRI and clinical data, and the existence of distinct subtypes. Furthermore, we examined the stability of the whole procedure using resampling., Results and Conclusion: As in the original study, we found extremely high canonical correlations between functional connectivity and clinical symptoms, and an optimal three-cluster solution. However, neither canonical correlations nor clusters were statistically significant. On the basis of our extensive evaluations of the analysis methodology used and within the limits of comparison of our sample relative to the sample used in Drysdale et al., we argue that the evidence for the existence of the distinct resting state connectivity-based subtypes of depression should be interpreted with caution., (Copyright © 2019 The Authors. Published by Elsevier Inc. All rights reserved.)

Many variables have been linked to different course trajectories of depression. These findings, however, are based on group comparisons with unknown translational value. This study evaluated the prognostic value of a wide range of clinical, psychological, and biological characteristics for predicting the course of depression and aimed to identify the best set of predictors. Eight hundred four unipolar depressed patients (major depressive disorder or dysthymia) patients were assessed on a set involving 81 demographic, clinical, psychological, and biological measures and were clinically followed-up for 2 years. Subjects were grouped according to (i) the presence of a depression diagnosis at 2-year follow-up (yes n = 397, no n = 407), and (ii) three disease course trajectory groups (rapid remission, n = 356, gradual improvement n = 273, and chronic n = 175) identified by a latent class growth analysis. A penalized logistic regression, followed by tight control over type I error, was used to predict depression course and to evaluate the prognostic value of individual variables. Based on the inventory of depressive symptomatology (IDS), we could predict a rapid remission course of depression with an AUROC of 0.69 and 62% accuracy, and the presence of an MDD diagnosis at follow-up with an AUROC of 0.66 and 66% accuracy. Other clinical, psychological, or biological variables did not significantly improve the prediction. Among the large set of variables considered, only the IDS provided predictive value for course prediction on an individual level, although this analysis represents only one possible methodological approach. However, accuracy of course prediction was moderate at best and further improvement is required for these findings to be clinically useful.

Importance: Schizophrenia and bipolar disorder are severe and complex brain disorders characterized by substantial clinical and biological heterogeneity. However, case-control studies often ignore such heterogeneity through their focus on the average patient, which may be the core reason for a lack of robust biomarkers indicative of an individual's treatment response and outcome., Objectives: To investigate the degree to which case-control analyses disguise interindividual differences in brain structure among patients with schizophrenia and bipolar disorder and to map the brain alterations linked to these disorders at the level of individual patients., Design, Setting, and Participants: This study used cross-sectional, T1-weighted magnetic resonance imaging data from participants recruited for the Thematically Organized Psychosis study from October 27, 2004, to October 17, 2012. Data were reanalyzed in 2017 and 2018. Patients were recruited from inpatient and outpatient clinics in the Oslo area of Norway, and healthy individuals from the same catchment area were drawn from the national population registry., Main Outcomes and Measures: Interindividual differences in brain structure among patients with schizophrenia and bipolar disorder. Voxel-based morphometry maps were computed, which were used for normative modeling to map the range of interindividual differences in brain structure., Results: This study included 218 patients with schizophrenia spectrum disorders (mean [SD] age, 30 [9.3] years; 126 [57.8%] male), of whom 163 had schizophrenia (mean [SD] age, 31 [8.7] years; 105 [64.4%] male) and 190 had bipolar disorder (mean [SD] age, 34 [11.3] years; 79 [41.6%] male), and 256 healthy individuals (mean [SD] age, 34 [9.5] years; 140 [54.7%] male). At the level of the individual, deviations from the normative model were frequent in both disorders but highly heterogeneous. Overlap of more than 2% among patients was observed in only a few loci, primarily in frontal, temporal, and cerebellar regions. The proportion of alterations was associated with diagnosis and cognitive and clinical characteristics within clinical groups. Patients with schizophrenia, on average, had significantly reduced gray matter in frontal regions, cerebellum, and temporal cortex. In patients with bipolar disorder, mean deviations were primarily present in cerebellar regions., Conclusions and Relevance: This study found that group-level differences disguised biological heterogeneity and interindividual differences among patients with the same diagnosis. This finding suggests that the idea of the average patient is a noninformative construct in psychiatry that falls apart when mapping abnormalities at the level of the individual patient. This study presents a workable route toward precision medicine in psychiatry.

Brain regions are often topographically connected: nearby locations within one brain area connect with nearby locations in another area. Mapping these connection topographies, or 'connectopies' in short, is crucial for understanding how information is processed in the brain. Here, we propose principled, fully data-driven methods for mapping connectopies using functional magnetic resonance imaging (fMRI) data acquired at rest by combining spectral embedding of voxel-wise connectivity 'fingerprints' with a novel approach to spatial statistical inference. We apply the approach in human primary motor and visual cortex, and show that it can trace biologically plausible, overlapping connectopies in individual subjects that follow these regions' somatotopic and retinotopic maps. As a generic mechanism to perform inference over connectopies, the new spatial statistics approach enables rigorous statistical testing of hypotheses regarding the fine-grained spatial profile of functional connectivity and whether that profile is different between subjects or between experimental conditions. The combined framework offers a fundamental alternative to existing approaches to investigating functional connectivity in the brain, from voxel- or seed-pair wise characterizations of functional association, towards a full, multivariate characterization of spatial topography., (Copyright © 2017 The Authors. Published by Elsevier Inc. All rights reserved.)

The dominant approach to neuroimaging data analysis employs the voxel as the unit of computation. While convenient, voxels lack biological meaning and their size is arbitrarily determined by the resolution of the image. Here, we propose a multivariate spatial model in which neuroimaging data are characterised as a linearly weighted combination of multiscale basis functions which map onto underlying brain nuclei or networks or nuclei. In this model, the elementary building blocks are derived to reflect the functional anatomy of the brain during the resting state. This model is estimated using a Bayesian framework which accurately quantifies uncertainty and automatically finds the most accurate and parsimonious combination of basis functions describing the data. We demonstrate the utility of this framework by predicting quantitative SPECT images of striatal dopamine function and we compare a variety of basis sets including generic isotropic functions, anatomical representations of the striatum derived from structural MRI, and two different soft functional parcellations of the striatum derived from resting-state fMRI (rfMRI). We found that a combination of ∼50 multiscale functional basis functions accurately represented the striatal dopamine activity, and that functional basis functions derived from an advanced parcellation technique known as Instantaneous Connectivity Parcellation (ICP) provided the most parsimonious models of dopamine function. Importantly, functional basis functions derived from resting fMRI were more accurate than both structural and generic basis sets in representing dopamine function in the striatum for a fixed model order. We demonstrate the translational validity of our framework by constructing classification models for discriminating parkinsonian disorders and their subtypes. Here, we show that ICP approach is the only basis set that performs well across all comparisons and performs better overall than the classical voxel-based approach. This spatial model constitutes an elegant alternative to voxel-based approaches in neuroimaging studies; not only are their atoms biologically informed, they are also adaptive to high resolutions, represent high dimensions efficiently, and capture long-range spatial dependencies, which are important and challenging objectives for neuroimaging data., (Copyright © 2017 The Authors. Published by Elsevier Inc. All rights reserved.)

Background: Attention-deficit/hyperactivity disorder (ADHD) is biologically heterogeneous, with different biological predispositions - mediated through developmental processes - converging upon a common clinical phenotype. Brain imaging studies have variably shown altered brain structure, activity and connectivity in children and adults with ADHD. Recent methodological developments allow for the integration of information across imaging modalities, potentially yielding a more coherent view regarding the biology underlying the disorder., Methods: We analyzed a sample of adults with persistent ADHD and healthy controls using an advanced multimodal linked independent component analysis approach. Diffusion and structural MRI data were fused to form imaging markers reflecting independent components that explain variation across modalities. We included these markers as predictors into logistic regression models on adult ADHD and put those into context with predictions of estimated intelligence, age and sex., Results: We included 87 adults with ADHD and 93 controls in our analysis. Participants' courses associated with all imaging markers explained 27.86% of the variance in adult ADHD. No single imaging modality dominated this result. Instead, it was explained by aggregation of relatively small effects across several modalities and markers. One of the top markers for adult ADHD was multimodal and linked to morphological and microstructural effects within anterior temporal brain regions; another was linked to cortical thickness. Several markers were also influenced by estimated intelligence, age and/or sex., Limitations: Although complex analytical approaches, such as the one applied here, provide insight into otherwise hidden mechanisms, they also increase the complexity of interpretations., Conclusion: No dominant imaging modality or marker characterizes structural brain phenotypes in adults with ADHD, but we can refine our characterization of the disorder by the integration of small effects across modalities.

The two hemispheres of the human brain differ functionally and structurally. Despite over a century of research, the extent to which brain asymmetry is influenced by sex, handedness, age, and genetic factors is still controversial. Here we present the largest ever analysis of subcortical brain asymmetries, in a harmonized multi-site study using meta-analysis methods. Volumetric asymmetry of seven subcortical structures was assessed in 15,847 MRI scans from 52 datasets worldwide. There were sex differences in the asymmetry of the globus pallidus and putamen. Heritability estimates, derived from 1170 subjects belonging to 71 extended pedigrees, revealed that additive genetic factors influenced the asymmetry of these two structures and that of the hippocampus and thalamus. Handedness had no detectable effect on subcortical asymmetries, even in this unprecedented sample size, but the asymmetry of the putamen varied with age. Genetic drivers of asymmetry in the hippocampus, thalamus and basal ganglia may affect variability in human cognition, including susceptibility to psychiatric disorders.

Anatomical tracing studies in non-human primates have suggested that corticostriatal connectivity is topographically organized: nearby locations in striatum are connected with nearby locations in cortex. The topographic organization of corticostriatal connectivity is thought to underpin many goal-directed behaviours, but these topographies have not been completely characterised in humans and their relationship to uniquely human behaviours remains to be fully determined. Instead, the dominant approach employs parcellations that cannot model the continuous nature of the topography, nor accommodate overlapping cortical projections in the striatum. Here, we employ a different approach to studying human corticostriatal circuitry: we estimate smoothly-varying and spatially overlapping 'connection topographies' from resting state fMRI. These correspond exceptionally well with and extend the topographies predicted from primate tracing studies. We show that striatal topography is preserved in regions not previously known to have topographic connections with the striatum and that many goal-directed behaviours can be mapped precisely onto individual variations in the spatial layout of striatal connectivity., Competing Interests: Competing Interests: CFB is director and shareholder in SBGNeuro Ltd. The other authors report no competing interests.

The brain's remarkable capacity for language requires bidirectional interactions between functionally specialized brain regions. We used magnetoencephalography to investigate interregional interactions in the brain network for language while 102 participants were reading sentences. Using Granger causality analysis, we identified inferior frontal cortex and anterior temporal regions to receive widespread input and middle temporal regions to send widespread output. This fits well with the notion that these regions play a central role in language processing. Characterization of the functional topology of this network, using data-driven matrix factorization, which allowed for partitioning into a set of subnetworks, revealed directed connections at distinct frequencies of interaction. Connections originating from temporal regions peaked at alpha frequency, whereas connections originating from frontal and parietal regions peaked at beta frequency. These findings indicate that the information flow between language-relevant brain areas, which is required for linguistic processing, may depend on the contributions of distinct brain rhythms., Competing Interests: The authors declare no conflict of interest.

There is evidence that the human cerebellum is involved not only in motor control but also in other cognitive functions. Several studies have shown that language-related activation is lateralized toward the right cerebellar hemisphere in most people, in accordance with leftward cerebral cortical lateralization for language and a general contralaterality of cerebral-cerebellar activations. In terms of behavior, hand use elicits asymmetrical activation in the cerebellum, while hand preference is weakly associated with language lateralization. However, it is not known how, or whether, these functional relations are reflected in anatomy. We investigated volumetric gray matter asymmetries of cerebellar lobules in an MRI data set comprising 2226 subjects. We tested these cerebellar asymmetries for associations with handedness, and for correlations with cerebral cortical anatomical asymmetries of regions important for language or hand motor control, as defined by two different automated image analysis methods and brain atlases, and supplemented with extensive visual quality control. No significant associations of cerebellar asymmetries to handedness were found. Some significant associations of cerebellar lobular asymmetries to cerebral cortical asymmetries were found, but none of these correlations were greater than 0.14, and they were mostly method-/atlas-dependent. On the basis of this large and highly powered study, we conclude that there is no overt structural manifestation of cerebellar functional lateralization and connectivity, in respect of hand motor control or language laterality.

Importance: Autism spectrum disorder (ASD) is 2 to 5 times more common in male individuals than in female individuals. While the male preponderant prevalence of ASD might partially be explained by sex differences in clinical symptoms, etiological models suggest that the biological male phenotype carries a higher intrinsic risk for ASD than the female phenotype. To our knowledge, this hypothesis has never been tested directly, and the neurobiological mechanisms that modulate ASD risk in male individuals and female individuals remain elusive., Objectives: To examine the probability of ASD as a function of normative sex-related phenotypic diversity in brain structure and to identify the patterns of sex-related neuroanatomical variability associated with low or high probability of ASD., Design, Setting, and Participants: This study examined a cross-sectional sample of 98 right-handed, high-functioning adults with ASD and 98 matched neurotypical control individuals aged 18 to 42 years. A multivariate probabilistic classification approach was used to develop a predictive model of biological sex based on cortical thickness measures assessed via magnetic resonance imaging in neurotypical controls. This normative model was subsequently applied to individuals with ASD. The study dates were June 2005 to October 2009, and this analysis was conducted between June 2015 and July 2016., Main Outcomes and Measures: Sample and population ASD probability estimates as a function of normative sex-related diversity in brain structure, as well as neuroanatomical patterns associated with low or high ASD probability in male individuals and female individuals., Results: Among the 98 individuals with ASD, 49 were male and 49 female, with a mean (SD) age of 26.88 (7.18) years. Among the 98 controls, 51 were male and 47 female, with a mean (SD) age of 27.39 (6.44) years. The sample probability of ASD increased significantly with predictive probabilities for the male neuroanatomical brain phenotype. For example, biological female individuals with a more male-typic pattern of brain anatomy were significantly (ie, 3 times) more likely to have ASD than biological female individuals with a characteristically female brain phenotype (P = .72 vs .24, respectively; χ21 = 20.26; P < .001; difference in P values, 0.48; 95% CI, 0.29-0.68). This finding translates to an estimated variability in population prevalence from 0.2% to 1.3%, respectively. Moreover, the patterns of neuroanatomical variability carrying low or high ASD probability were sex specific (eg, in inferior temporal regions, where ASD has different neurobiological underpinnings in male individuals and female individuals)., Conclusions and Relevance: These findings highlight the need for considering normative sex-related phenotypic diversity when determining an individual's risk for ASD and provide important novel insights into the neurobiological mechanisms mediating sex differences in ASD prevalence.

The hippocampal formation is a brain structure integrally involved in episodic memory, spatial navigation, cognition and stress responsiveness. Structural abnormalities in hippocampal volume and shape are found in several common neuropsychiatric disorders. To identify the genetic underpinnings of hippocampal structure here we perform a genome-wide association study (GWAS) of 33,536 individuals and discover six independent loci significantly associated with hippocampal volume, four of them novel. Of the novel loci, three lie within genes (ASTN2, DPP4 and MAST4) and one is found 200 kb upstream of SHH. A hippocampal subfield analysis shows that a locus within the MSRB3 gene shows evidence of a localized effect along the dentate gyrus, subiculum, CA1 and fissure. Further, we show that genetic variants associated with decreased hippocampal volume are also associated with increased risk for Alzheimer's disease (r g =-0.155). Our findings suggest novel biological pathways through which human genetic variation influences hippocampal volume and risk for neuropsychiatric illness.

Longitudinal designs are widely used in medical studies as a means of observing within-subject changes over time in groups of subjects, thereby aiming to improve sensitivity for detecting disease effects. Paralleling an increased use of such studies in neuroimaging has been the adoption of pattern recognition algorithms for making individualized predictions of disease. However, at present few pattern recognition methods exist to make full use of neuroimaging data that have been collected longitudinally, with most methods relying instead on cross-sectional style analysis. This article presents a principal component analysis-based feature construction method that uses longitudinal high-dimensional data to improve predictive performance of pattern recognition algorithms. The method can be applied to data from a wide range of longitudinal study designs and permits an arbitrary number of time-points per subject. We apply the method to two longitudinal datasets, one containing subjects with mild cognitive impairment along with healthy controls, the other with early dementia subjects and healthy controls. Across both datasets, we show improvements in predictive accuracy relative to cross-sectional classifiers for discriminating disease subjects from healthy controls on the basis of whole-brain structural magnetic resonance image-based voxels. In addition, we can transfer longitudinal information from one set of subjects to make disease predictions in another set of subjects. The proposed method is simple and, as a feature construction method, flexible with respect to the choice of classifier and image registration algorithm. Hum Brain Mapp 37:4385-4404, 2016. © 2016 Wiley Periodicals, Inc., (© 2016 The Authors Human Brain Mapping Published by Wiley Periodicals, Inc.)

Objectives: Recent studies have indicated that pattern recognition techniques of functional magnetic resonance imaging (fMRI) data for individual classification may be valuable for distinguishing between major depressive disorder (MDD) and bipolar disorder (BD). Importantly, medication may have affected previous classification results as subjects with MDD and BD use different classes of medication. Furthermore, almost all studies have investigated only depressed subjects. Therefore, we focused on medication-free subjects. We additionally investigated whether classification would be mood state independent by including depressed and remitted subjects alike., Methods: We applied Gaussian process classifiers to investigate the discriminatory power of structural MRI (gray matter volumes of emotion regulation areas) and resting-state fMRI (resting-state networks implicated in mood disorders: default mode network [DMN], salience network [SN], and lateralized frontoparietal networks [FPNs]) in depressed (n=42) and remitted (n=49) medication-free subjects with MDD and BD., Results: Depressed subjects with MDD and BD could be classified based on the gray matter volumes of emotion regulation areas as well as DMN functional connectivity with 69.1% prediction accuracy. Prediction accuracy using the FPNs and SN did not exceed chance level. It was not possible to discriminate between remitted subjects with MDD and BD., Conclusions: For the first time, we showed that medication-free subjects with MDD and BD can be differentiated based on structural MRI as well as resting-state functional connectivity. Importantly, the results indicated that research concerning diagnostic neuroimaging tools distinguishing between MDD and BD should consider mood state as only depressed subjects with MDD and BD could be correctly classified. Future studies, in larger samples are needed to investigate whether the results can be generalized to medication-naïve or first-episode subjects., (© 2016 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.)

Background: Despite many successes, the case-control approach is problematic in biomedical science. It introduces an artificial symmetry whereby all clinical groups (e.g., patients and control subjects) are assumed to be well defined, when biologically they are often highly heterogeneous. By definition, it also precludes inference over the validity of the diagnostic labels. In response, the National Institute of Mental Health Research Domain Criteria proposes to map relationships between symptom dimensions and broad behavioral and biological domains, cutting across diagnostic categories. However, to date, Research Domain Criteria have prompted few methods to meaningfully stratify clinical cohorts., Methods: We introduce normative modeling for parsing heterogeneity in clinical cohorts, while allowing predictions at an individual subject level. This approach aims to map variation within the cohort and is distinct from, and complementary to, existing approaches that address heterogeneity by employing clustering techniques to fractionate cohorts. To demonstrate this approach, we mapped the relationship between trait impulsivity and reward-related brain activity in a large healthy cohort (N = 491)., Results: We identify participants who are outliers within this distribution and show that the degree of deviation (outlier magnitude) relates to specific attention-deficit/hyperactivity disorder symptoms (hyperactivity, but not inattention) on the basis of individualized patterns of abnormality., Conclusions: Normative modeling provides a natural framework to study disorders at the individual participant level without dichotomizing the cohort. Instead, disease can be considered as an extreme of the normal range or as-possibly idiosyncratic-deviation from normal functioning. It also enables inferences over the degree to which behavioral variables, including diagnostic labels, map onto biology., (Copyright © 2016 Society of Biological Psychiatry. Published by Elsevier Inc. All rights reserved.)

Heterogeneity is a key feature of all psychiatric disorders that manifests on many levels, including symptoms, disease course, and biological underpinnings. These form a substantial barrier to understanding disease mechanisms and developing effective, personalized treatments. In response, many studies have aimed to stratify psychiatric disorders, aiming to find more consistent subgroups on the basis of many types of data. Such approaches have received renewed interest after recent research initiatives, such as the National Institute of Mental Health Research Domain Criteria and the European Roadmap for Mental Health Research, both of which emphasize finding stratifications that are based on biological systems and that cut across current classifications. We first introduce the basic concepts for stratifying psychiatric disorders and then provide a methodologically oriented and critical review of the existing literature. This shows that the predominant clustering approach that aims to subdivide clinical populations into more coherent subgroups has made a useful contribution but is heavily dependent on the type of data used; it has produced many different ways to subgroup the disorders we review, but for most disorders it has not converged on a consistent set of subgroups. We highlight problems with current approaches that are not widely recognized and discuss the importance of validation to ensure that the derived subgroups index clinically relevant variation. Finally, we review emerging techniques-such as those that estimate normative models for mappings between biology and behavior-that provide new ways to parse the heterogeneity underlying psychiatric disorders and evaluate all methods to meeting the objectives of such as the National Institute of Mental Health Research Domain Criteria and Roadmap for Mental Health Research.

Attention-deficit/hyperactivity disorder (ADHD) is one of the most prevalent and heritable psychiatric disorders. While previous studies have focussed on mapping focal or connectivity differences at the group level, the present study employed pattern recognition to quantify group separation between unaffected siblings, participants with ADHD, and healthy controls on the basis of spatially distributed brain activations. This was achieved using an fMRI-adapted version of the Stop-Signal Task in a sample of 103 unaffected siblings, 184 participants with ADHD, and 128 healthy controls. We used activation maps derived from three task regressors as features in our analyses employing a Gaussian process classifier. We showed that unaffected siblings could be distinguished from participants with ADHD (area under the receiver operating characteristic curve (AUC) = 0.65, p = 0.002, 95% Modified Wald CI: 0.59-0.71 AUC) and healthy controls (AUC = 0.59, p = 0.030, 95% Modified Wald CI: 0.52-0.66 AUC), although the latter did not survive correction for multiple comparisons. Further, participants with ADHD could be distinguished from healthy controls (AUC = 0.64, p = 0.001, 95% Modified Wald CI: 0.58-0.70 AUC). Altogether the present results characterise a pattern of frontolateral, superior temporal and inferior parietal expansion that is associated with risk for ADHD. Unaffected siblings show differences primarily in frontolateral regions. This provides evidence for a neural profile shared between participants with ADHD and their healthy siblings.

The identification of individuals at high risk of developing psychosis is entirely based on clinical assessment, associated with limited predictive potential. There is, therefore, increasing interest in the development of biological markers that could be used in clinical practice for this purpose. We studied 25 individuals with an at-risk mental state for psychosis and 25 healthy controls using structural MRI, and functional MRI in conjunction with a verbal memory task. Data were analyzed using a standard univariate analysis, and with support vector machine (SVM), a multivariate pattern recognition technique that enables statistical inferences to be made at the level of the individual, yielding results with high translational potential. The application of SVM to structural MRI data permitted the identification of individuals at high risk of psychosis with a sensitivity of 68% and a specificity of 76%, resulting in an accuracy of 72% (p < 0.001). Univariate volumetric between-group differences did not reach statistical significance. By contrast, the univariate fMRI analysis identified between-group differences (p < 0.05 corrected), while the application of SVM to the same data did not. Since SVM is well suited at identifying the pattern of abnormality that distinguishes two groups, whereas univariate methods are more likely to identify regions that individually are most different between two groups, our results suggest the presence of focal functional abnormalities in the context of a diffuse pattern of structural abnormalities in individuals at high clinical risk of psychosis.

An increasing number of neuroimaging studies are based on either combining more than one data modality (inter-modal) or combining more than one measurement from the same modality (intra-modal). To date, most intra-modal studies using multivariate statistics have focused on differences between datasets, for instance relying on classifiers to differentiate between effects in the data. However, to fully characterize these effects, multivariate methods able to measure similarities between datasets are needed. One classical technique for estimating the relationship between two datasets is canonical correlation analysis (CCA). However, in the context of high-dimensional data the application of CCA is extremely challenging. A recent extension of CCA, sparse CCA (SCCA), overcomes this limitation, by regularizing the model parameters while yielding a sparse solution. In this work, we modify SCCA with the aim of facilitating its application to high-dimensional neuroimaging data and finding meaningful multivariate image-to-image correspondences in intra-modal studies. In particular, we show how the optimal subset of variables can be estimated independently and we look at the information encoded in more than one set of SCCA transformations. We illustrate our framework using Arterial Spin Labeling data to investigate multivariate similarities between the effects of two antipsychotic drugs on cerebral blood flow.

Psychiatric disorders are increasingly being recognised as having a biological basis, but their diagnosis is made exclusively behaviourally. A promising approach for 'biomarker' discovery has been based on pattern recognition methods applied to neuroimaging data, which could yield clinical utility in future. In this review we survey the literature on pattern recognition for making diagnostic predictions in psychiatric disorders, and evaluate progress made in translating such findings towards clinical application. We evaluate studies on many criteria, including data modalities used, the types of features extracted and algorithm applied. We identify problems common to many studies, such as a relatively small sample size and a primary focus on estimating generalisability within a single study. Furthermore, we highlight challenges that are not widely acknowledged in the field including the importance of accommodating disease prevalence, the necessity of more extensive validation using large carefully acquired samples, the need for methodological innovations to improve accuracy and to discriminate between multiple disorders simultaneously. Finally, we identify specific clinical contexts in which pattern recognition can add value in the short to medium term., (Copyright © 2015 The Authors. Published by Elsevier Ltd.. All rights reserved.)

Background: A chronic course of major depressive disorder (MDD) is associated with profound alterations in brain volumes and emotional and cognitive processing. However, no neurobiological markers have been identified that prospectively predict MDD course trajectories. This study evaluated the prognostic value of different neuroimaging modalities, clinical characteristics, and their combination to classify MDD course trajectories., Methods: One hundred eighteen MDD patients underwent structural and functional magnetic resonance imaging (MRI) (emotional facial expressions and executive functioning) and were clinically followed-up at 2 years. Three MDD trajectories (chronic n = 23, gradual improving n = 36, and fast remission n = 59) were identified based on Life Chart Interview measuring the presence of symptoms each month. Gaussian process classifiers were employed to evaluate prognostic value of neuroimaging data and clinical characteristics (including baseline severity, duration, and comorbidity)., Results: Chronic patients could be discriminated from patients with more favorable trajectories from neural responses to various emotional faces (up to 73% accuracy) but not from structural MRI and functional MRI related to executive functioning. Chronic patients could also be discriminated from remitted patients based on clinical characteristics (accuracy 69%) but not when age differences between the groups were taken into account. Combining different task contrasts or data sources increased prediction accuracies in some but not all cases., Conclusions: Our findings provide evidence that the prediction of naturalistic course of depression over 2 years is improved by considering neuroimaging data especially derived from neural responses to emotional facial expressions. Neural responses to emotional salient faces more accurately predicted outcome than clinical data., (Copyright © 2015 Society of Biological Psychiatry. Published by Elsevier Inc. All rights reserved.)

Cognitive behavior therapy (CBT) is an effective treatment for social anxiety disorder (SAD), but many patients do not respond sufficiently and a substantial proportion relapse after treatment has ended. Predicting an individual's long-term clinical response therefore remains an important challenge. This study aimed at assessing neural predictors of long-term treatment outcome in participants with SAD 1 year after completion of Internet-delivered CBT (iCBT). Twenty-six participants diagnosed with SAD underwent iCBT including attention bias modification for a total of 13 weeks. Support vector machines (SVMs), a supervised pattern recognition method allowing predictions at the individual level, were trained to separate long-term treatment responders from nonresponders based on blood oxygen level-dependent (BOLD) responses to self-referential criticism. The Clinical Global Impression-Improvement scale was the main instrument to determine treatment response at the 1-year follow-up. Results showed that the proportion of long-term responders was 52% (12/23). From multivariate BOLD responses in the dorsal anterior cingulate cortex (dACC) together with the amygdala, we were able to predict long-term response rate of iCBT with an accuracy of 92% (confidence interval 95% 73.2-97.6). This activation pattern was, however, not predictive of improvement in the continuous Liebowitz Social Anxiety Scale-Self-report version. Follow-up psychophysiological interaction analyses revealed that lower dACC-amygdala coupling was associated with better long-term treatment response. Thus, BOLD response patterns in the fear-expressing dACC-amygdala regions were highly predictive of long-term treatment outcome of iCBT, and the initial coupling between these regions differentiated long-term responders from nonresponders. The SVM-neuroimaging approach could be of particular clinical value as it allows for accurate prediction of treatment outcome at the level of the individual.

We propose a novel approach to predicting disease progression in Alzheimer's disease (AD)--multivariate ordinal regression--which inherently models the ordered nature of brain atrophy spanning normal aging (CTL) to mild cognitive impairment (MCI) to AD. Ordinal regression provides probabilistic class predictions as well as a continuous index of disease progression--the ORCHID (Ordinal Regression Characteristic Index of Dementia) score. We applied ordinal regression to 1023 baseline structural MRI scans from two studies: the US-based Alzheimer's Disease Neuroimaging Initiative (ADNI) and the European based AddNeuroMed program. Here, the acquired AddNeuroMed dataset was used as a completely independent test set for the ordinal regression model trained on the ADNI cohort providing an optimal assessment of model generalizability. Distinguishing CTL-like (CTL and stable MCI) from AD-like (MCI converters and AD) resulted in balanced accuracies of 82% (cross-validation) for ADNI and 79% (independent test set) for AddNeuroMed. For prediction of conversion from MCI to AD, balanced accuracies of 70% (AUC of 0.75) and 75% (AUC of 0.81) were achieved. The ORCHID score was computed for all subjects. We showed that this measure significantly correlated with MMSE at 12 months (ρ =  -0.64, ADNI and ρ =  -0.59, AddNeuroMed). Additionally, the ORCHID score can help fractionate subjects with unstable diagnoses (e.g. reverters and healthy controls who later progressed to MCI), moderately late converters (12-24 months) and late converters (24-36 months). A comparison with results in the literature and direct comparison with a binary classifier suggests that the performance of this framework is highly competitive.

In the pursuit of clinical utility, neuroimaging researchers of psychiatric and neurological illness are increasingly using analyses, such as support vector machine, that allow inference at the single-subject level. Recent studies employing single-modality data, however, suggest that classification accuracies must be improved for such utility to be realized. One possible solution is to integrate different data types to provide a single combined output classification; either by generating a single decision function based on an integrated kernel matrix, or, by creating an ensemble of multiple single modality classifiers and integrating their predictions. Here, we describe four integrative approaches: (1) an un-weighted sum of kernels, (2) multi-kernel learning, (3) prediction averaging, and (4) majority voting, and compare their ability to enhance classification accuracy relative to the best single-modality classification accuracy. We achieve this by integrating structural, functional, and diffusion tensor magnetic resonance imaging data, in order to compare ultra-high risk (n = 19), first episode psychosis (n = 19) and healthy control subjects (n = 23). Our results show that (i) whilst integration can enhance classification accuracy by up to 13%, the frequency of such instances may be limited, (ii) where classification can be enhanced, simple methods may yield greater increases relative to more computationally complex alternatives, and, (iii) the potential for classification enhancement is highly influenced by the specific diagnostic comparison under consideration. In conclusion, our findings suggest that for moderately sized clinical neuroimaging datasets, combining different imaging modalities in a data-driven manner is no "magic bullet" for increasing classification accuracy. However, it remains possible that this conclusion is dependent on the use of neuroimaging modalities that had little, or no, complementary information to offer one another, and that the integration of more diverse types of data would have produced greater classification enhancement. We suggest that future studies ideally examine a greater variety of data types (e.g., genetic, cognitive, and neuroimaging) in order to identify the data types and combinations optimally suited to the classification of early stage psychosis.

The diagnosis of Attention Deficit Hyperactivity Disorder (ADHD) is based on subjective measures despite evidence for multisystemic structural and functional deficits. ADHD patients have consistent neurofunctional deficits in motor response inhibition. The aim of this study was to apply pattern classification to task-based functional magnetic resonance imaging (fMRI) of inhibition, to accurately predict the diagnostic status of ADHD. Thirty adolescent ADHD and thirty age-matched healthy boys underwent fMRI while performing a Stop task. fMRI data were analyzed with Gaussian process classifiers (GPC), a machine learning approach, to predict individual ADHD diagnosis based on task-based activation patterns. Traditional univariate case-control analyses were also performed to replicate previous findings in a relatively large dataset. The pattern of brain activation correctly classified up to 90% of patients and 63% of controls, achieving an overall classification accuracy of 77%. The regions of the discriminative network most predictive of controls included later developing lateral prefrontal, striatal, and temporo-parietal areas that mediate inhibition, while regions most predictive of ADHD were in earlier developing ventromedial fronto-limbic regions, which furthermore correlated with symptom severity. Univariate analysis showed reduced activation in ADHD in bilateral ventrolateral prefrontal, striatal, and temporo-parietal regions that overlapped with areas predictive of controls, suggesting the latter are dysfunctional areas in ADHD. We show that significant individual classification of ADHD patients of 77% can be achieved using whole brain pattern analysis of task-based fMRI inhibition data, suggesting that multivariate pattern recognition analyses of inhibition networks can provide objective diagnostic neuroimaging biomarkers of ADHD., (Copyright © 2013 The Authors. Human Brain Mapping published by Wiley Periodicals, Inc.)

Decoding models based on pattern recognition (PR) are becoming increasingly important tools for neuroimaging data analysis. In contrast to alternative (mass-univariate) encoding approaches that use hierarchical models to capture inter-subject variability, inter-subject differences are not typically handled efficiently in PR. In this work, we propose to overcome this problem by recasting the decoding problem in a multi-task learning (MTL) framework. In MTL, a single PR model is used to learn different but related "tasks" simultaneously. The primary advantage of MTL is that it makes more efficient use of the data available and leads to more accurate models by making use of the relationships between tasks. In this work, we construct MTL models where each subject is modelled by a separate task. We use a flexible covariance structure to model the relationships between tasks and induce coupling between them using Gaussian process priors. We present an MTL method for classification problems and demonstrate a novel mapping method suitable for PR models. We apply these MTL approaches to classifying many different contrasts in a publicly available fMRI dataset and show that the proposed MTL methods produce higher decoding accuracy and more consistent discriminative activity patterns than currently used techniques. Our results demonstrate that MTL provides a promising method for multi-subject decoding studies by focusing on the commonalities between a group of subjects rather than the idiosyncratic properties of different subjects., (Copyright © 2014 The Authors. Published by Elsevier Inc. All rights reserved.)

Objective: Attention-deficit/hyperactivity disorder (ADHD) is currently diagnosed on the basis of subjective measures, despite evidence for multi-systemic structural and neurofunctional deficits. A consistently observed neurofunctional deficit is in fine-temporal discrimination (TD). The aim of this proof-of-concept study was to examine the feasibility of distinguishing patients with ADHD from controls using multivariate pattern recognition analyses of functional magnetic resonance imaging (fMRI) data of TD., Method: A total of 20 medication-naive adolescent male patients with ADHD and 20 age-matched healthy controls underwent fMRI while performing a TD task. The fMRI data were analyzed with Gaussian process classifiers to predict individual ADHD diagnosis based on brain activation patterns., Results: The pattern of brain activation correctly classified up to 80% of patients and 70% of controls, achieving an overall classification accuracy of 75%. The distributed activation networks with the highest delineation between patients and controls corresponded to a distributed network of brain regions involved in TD and typically compromised in ADHD, including inferior and dorsolateral prefrontal, insula, and parietal cortices, and the basal ganglia, anterior cingulate, and cerebellum. These regions overlapped with areas of reduced activation in patients with ADHD relative to controls in a univariate analysis, suggesting that these are dysfunctional regions., Conclusions: We show evidence that pattern recognition analyses combined with fMRI using a disorder-sensitive task such as timing have potential in providing objective diagnostic neuroimaging biomarkers of ADHD., (Copyright © 2014 American Academy of Child and Adolescent Psychiatry. Published by Elsevier Inc. All rights reserved.)

Functional neuroimaging of social anxiety disorder (SAD) support altered neural activation to threat-provoking stimuli focally in the fear network, while structural differences are distributed over the temporal and frontal cortices as well as limbic structures. Previous neuroimaging studies have investigated the brain at the voxel level using mass-univariate methods which do not enable detection of more complex patterns of activity and structural alterations that may separate SAD from healthy individuals. Support vector machine (SVM) is a supervised machine learning method that capitalizes on brain activation and structural patterns to classify individuals. The aim of this study was to investigate if it is possible to discriminate SAD patients (n=14) from healthy controls (n=12) using SVM based on (1) functional magnetic resonance imaging during fearful face processing and (2) regional gray matter volume. Whole brain and region of interest (fear network) SVM analyses were performed for both modalities. For functional scans, significant classifications were obtained both at whole brain level and when restricting the analysis to the fear network while gray matter SVM analyses correctly classified participants only when using the whole brain search volume. These results support that SAD is characterized by aberrant neural activation to affective stimuli in the fear network, while disorder-related alterations in regional gray matter volume are more diffusely distributed over the whole brain. SVM may thus be useful for identifying imaging biomarkers of SAD., (Copyright © 2013 The Authors. Published by Elsevier B.V. All rights reserved.)

Background: Bipolar disorder (BD) is one of the leading causes of disability worldwide. Patients are further disadvantaged by delays in accurate diagnosis ranging between 5 and 10 years. We applied Gaussian process classifiers (GPCs) to structural magnetic resonance imaging (sMRI) data to evaluate the feasibility of using pattern recognition techniques for the diagnostic classification of patients with BD., Method: GPCs were applied to gray (GM) and white matter (WM) sMRI data derived from two independent samples of patients with BD (cohort 1: n = 26; cohort 2: n = 14). Within each cohort patients were matched on age, sex and IQ to an equal number of healthy controls., Results: The diagnostic accuracy of the GPC for GM was 73% in cohort 1 and 72% in cohort 2; the sensitivity and specificity of the GM classification were respectively 69% and 77% in cohort 1 and 64% and 99% in cohort 2. The diagnostic accuracy of the GPC for WM was 69% in cohort 1 and 78% in cohort 2; the sensitivity and specificity of the WM classification were both 69% in cohort 1 and 71% and 86% respectively in cohort 2. In both samples, GM and WM clusters discriminating between patients and controls were localized within cortical and subcortical structures implicated in BD., Conclusions: Our results demonstrate the predictive value of neuroanatomical data in discriminating patients with BD from healthy individuals. The overlap between discriminative networks and regions implicated in the pathophysiology of BD supports the biological plausibility of the classifiers.

Feature selection (FS) methods play two important roles in the context of neuroimaging based classification: potentially increase classification accuracy by eliminating irrelevant features from the model and facilitate interpretation by identifying sets of meaningful features that best discriminate the classes. Although the development of FS techniques specifically tuned for neuroimaging data is an active area of research, up to date most of the studies have focused on finding a subset of features that maximizes accuracy. However, maximizing accuracy does not guarantee reliable interpretation as similar accuracies can be obtained from distinct sets of features. In the current paper we propose a new approach for selecting features: SCoRS (survival count on random subsamples) based on a recently proposed Stability Selection theory. SCoRS relies on the idea of choosing relevant features that are stable under data perturbation. Data are perturbed by iteratively sub-sampling both features (subspaces) and examples. We demonstrate the potential of the proposed method in a clinical application to classify depressed patients versus healthy individuals based on functional magnetic resonance imaging data acquired during visualization of happy faces.

Background: At present there are no objective, biological markers that can be used to reliably identify individuals with post-traumatic stress disorder (PTSD). This study assessed the diagnostic potential of structural magnetic resonance imaging (sMRI) for identifying trauma-exposed individuals with and without PTSD., Method: sMRI scans were acquired from 50 survivors of the Sichuan earthquake of 2008 who had developed PTSD, 50 survivors who had not developed PTSD and 40 healthy controls who had not been exposed to the earthquake. Support vector machine (SVM), a multivariate pattern recognition technique, was used to develop an algorithm that distinguished between the three groups at an individual level. The accuracy of the algorithm and its statistical significance were estimated using leave-one-out cross-validation and permutation testing., Results: When survivors with PTSD were compared against healthy controls, both grey and white matter allowed discrimination with an accuracy of 91% (p < 0.001). When survivors without PTSD were compared against healthy controls, the two groups could be discriminated with accuracies of 76% (p < 0.001) and 85% (p < 0.001) based on grey and white matter, respectively. Finally, when survivors with and without PTSD were compared directly, grey matter allowed discrimination with an accuracy of 67% (p < 0.001); in contrast the two groups could not be distinguished based on white matter., Conclusions: These results reveal patterns of neuroanatomical alterations that could be used to inform the identification of trauma survivors with and without PTSD at the individual level, and provide preliminary support to the development of SVM as a clinically useful diagnostic aid.

Background: Group-level results suggest that relative to healthy controls (HCs), ultra-high-risk (UHR) and first-episode psychosis (FEP) subjects show alterations in neuroanatomy, neurofunction and cognition that may be mediated genetically. It is unclear, however, whether these groups can be differentiated at single-subject level, for instance using the machine learning analysis support vector machine (SVM). Here, we used a multimodal approach to examine the ability of structural magnetic resonance imaging (sMRI), functional MRI (fMRI), diffusion tensor neuroimaging (DTI), genetic and cognitive data to differentiate between UHR, FEP and HC subjects at the single-subject level using SVM., Method: Three age- and gender-matched SVM paired comparison groups were created comprising 19, 19 and 15 subject pairs for FEP versus HC, UHR versus HC and FEP versus UHR, respectively. Genetic, sMRI, DTI, fMRI and cognitive data were obtained for each participant and the ability of each to discriminate subjects at the individual level in conjunction with SVM was tested., Results: Successful classification accuracies (p < 0.05) comprised FEP versus HC (genotype, 67.86%; DTI, 65.79%; fMRI, 65.79% and 68.42%; cognitive data, 73.69%), UHR versus HC (sMRI, 68.42%; DTI, 65.79%), and FEP versus UHR (sMRI, 76.67%; fMRI, 73.33%; cognitive data, 66.67%)., Conclusions: The results suggest that FEP subjects are identifiable at the individual level using a range of biological and cognitive measures. Comparatively, only sMRI and DTI allowed discrimination of UHR from HC subjects. For the first time FEP and UHR subjects have been shown to be directly differentiable at the single-subject level using cognitive, sMRI and fMRI data. Preliminarily, the results support clinical development of SVM to help inform identification of FEP and UHR subjects, though future work is needed to provide enhanced levels of accuracy.

Neuroimaging data are increasingly being used to predict potential outcomes or groupings, such as clinical severity, drug dose response, and transitional illness states. In these examples, the variable (target) we want to predict is ordinal in nature. Conventional classification schemes assume that the targets are nominal and hence ignore their ranked nature, whereas parametric and/or non-parametric regression models enforce a metric notion of distance between classes. Here, we propose a novel, alternative multivariate approach that overcomes these limitations - whole brain probabilistic ordinal regression using a Gaussian process framework. We applied this technique to two data sets of pharmacological neuroimaging data from healthy volunteers. The first study was designed to investigate the effect of ketamine on brain activity and its subsequent modulation with two compounds - lamotrigine and risperidone. The second study investigates the effect of scopolamine on cerebral blood flow and its modulation using donepezil. We compared ordinal regression to multi-class classification schemes and metric regression. Considering the modulation of ketamine with lamotrigine, we found that ordinal regression significantly outperformed multi-class classification and metric regression in terms of accuracy and mean absolute error. However, for risperidone ordinal regression significantly outperformed metric regression but performed similarly to multi-class classification both in terms of accuracy and mean absolute error. For the scopolamine data set, ordinal regression was found to outperform both multi-class and metric regression techniques considering the regional cerebral blood flow in the anterior cingulate cortex. Ordinal regression was thus the only method that performed well in all cases. Our results indicate the potential of an ordinal regression approach for neuroimaging data while providing a fully probabilistic framework with elegant approaches for model selection., (Copyright © 2013. Published by Elsevier Inc.)

Progressive supranuclear palsy (PSP), multiple system atrophy (MSA) and idiopathic Parkinson's disease (IPD) can be clinically indistinguishable, especially in the early stages, despite distinct patterns of molecular pathology. Structural neuroimaging holds promise for providing objective biomarkers for discriminating these diseases at the single subject level but all studies to date have reported incomplete separation of disease groups. In this study, we employed multi-class pattern recognition to assess the value of anatomical patterns derived from a widely available structural neuroimaging sequence for automated classification of these disorders. To achieve this, 17 patients with PSP, 14 with IPD and 19 with MSA were scanned using structural MRI along with 19 healthy controls (HCs). An advanced probabilistic pattern recognition approach was employed to evaluate the diagnostic value of several pre-defined anatomical patterns for discriminating the disorders, including: (i) a subcortical motor network; (ii) each of its component regions and (iii) the whole brain. All disease groups could be discriminated simultaneously with high accuracy using the subcortical motor network. The region providing the most accurate predictions overall was the midbrain/brainstem, which discriminated all disease groups from one another and from HCs. The subcortical network also produced more accurate predictions than the whole brain and all of its constituent regions. PSP was accurately predicted from the midbrain/brainstem, cerebellum and all basal ganglia compartments; MSA from the midbrain/brainstem and cerebellum and IPD from the midbrain/brainstem only. This study demonstrates that automated analysis of structural MRI can accurately predict diagnosis in individual patients with Parkinsonian disorders, and identifies distinct patterns of regional atrophy particularly useful for this process.

In the past years, mass univariate statistical analyses of neuroimaging data have been complemented by the use of multivariate pattern analyses, especially based on machine learning models. While these allow an increased sensitivity for the detection of spatially distributed effects compared to univariate techniques, they lack an established and accessible software framework. The goal of this work was to build a toolbox comprising all the necessary functionalities for multivariate analyses of neuroimaging data, based on machine learning models. The "Pattern Recognition for Neuroimaging Toolbox" (PRoNTo) is open-source, cross-platform, MATLAB-based and SPM compatible, therefore being suitable for both cognitive and clinical neuroscience research. In addition, it is designed to facilitate novel contributions from developers, aiming to improve the interaction between the neuroimaging and machine learning communities. Here, we introduce PRoNTo by presenting examples of possible research questions that can be addressed with the machine learning framework implemented in PRoNTo, and cannot be easily investigated with mass univariate statistical analysis.

Pattern recognition approaches to the analysis of neuroimaging data have brought new applications such as the classification of patients and healthy controls within reach. In our view, the reliance on expensive neuroimaging techniques which are not well tolerated by many patient groups and the inability of most current biomarker algorithms to accommodate information about prior class frequencies (such as a disorder's prevalence in the general population) are key factors limiting practical application. To overcome both limitations, we propose a probabilistic pattern recognition approach based on cheap and easy-to-use multi-channel near-infrared spectroscopy (fNIRS) measurements. We show the validity of our method by applying it to data from healthy controls (n = 14) enabling differentiation between the conditions of a visual checkerboard task. Second, we show that high-accuracy single subject classification of patients with schizophrenia (n = 40) and healthy controls (n = 40) is possible based on temporal patterns of fNIRS data measured during a working memory task. For classification, we integrate spatial and temporal information at each channel to estimate overall classification accuracy. This yields an overall accuracy of 76% which is comparable to the highest ever achieved in biomarker-based classification of patients with schizophrenia. In summary, the proposed algorithm in combination with fNIRS measurements enables the analysis of sub-second, multivariate temporal patterns of BOLD responses and high-accuracy predictions based on low-cost, easy-to-use fNIRS patterns. In addition, our approach can easily compensate for variable class priors, which is highly advantageous in making predictions in a wide range of clinical neuroimaging applications., (Copyright © 2012 Wiley Periodicals, Inc.)

Suggestions of limb paralysis in highly hypnotically suggestible subjects have been employed to successfully model conversion disorders, revealing similar patterns of brain activation associated with attempted movement of the affected limb. However, previous studies differ with regard to the executive regions involved during involuntary inhibition of the affected limb. This difference may have arisen as previous studies did not control for differences in hypnosis depth between conditions and/or include subjective measures to explore the experience of suggested paralysis. In the current study we employed functional magnetic resonance imaging (fMRI) to examine the functional anatomy of left and right upper limb movements in eight healthy subjects selected for high hypnotic suggestibility during (i) hypnosis (NORMAL) and (ii) attempted movement following additional left upper limb paralysis suggestions (PARALYSIS). Contrast of left upper limb motor function during NORMAL relative to PARALYSIS conditions revealed greater activation of contralateral M1/S1 and ipsilateral cerebellum, consistent with the engagement of these regions in the completion of movements. By contrast, two significant observations were noted in PARALYSIS relative to NORMAL conditions. In conjunction with reports of attempts to move the paralysed limb, greater supplementary motor area (SMA) activation was observed, a finding consistent with the role of SMA in motor intention and planning. The anterior cingulate cortex (ACC, BA 24) was also significantly more active in PARALYSIS relative to NORMAL conditions - suggesting that ACC (BA 24) may be implicated in involuntary, as well as voluntary inhibition of prepotent motor responses., (Copyright © 2012 Elsevier Ltd. All rights reserved.)