Voxel-wise multivariate analysis of brain-psychosocial associations in adolescents reveals six latent dimensions of cognition and psychopathology.

BACKGROUND: Adolescence heralds the onset of much psychopathology, which may be conceptualized as an emergence of altered covariation between symptoms and brain measures. Multivariate methods can detect such modes of covariation or latent dimensions, but none specifically relating to psychopathology have yet been found using population-level structural brain data. Using voxel-wise (instead of parcellated) brain data may strengthen latent dimensions' brain-psychosocial relationships, but this creates computational challenges. METHODS: We obtained voxel-wise grey matter density and psychosocial variables from the baseline (aged 9-10 years) Adolescent Brain and Cognitive Development cohort (n=11288), and employed a state-of-the-art segmentation method, sparse partial least squares, and a rigorous machine learning framework to prevent overfitting. RESULTS: We found six latent dimensions, four pertaining specifically to mental health. The mental health dimensions related to overeating, anorexia/internalizing, oppositional symptoms (all p<0.002) and ADHD symptoms (p=0.03). ADHD related to increased and internalizing related to decreased grey matter density in dopaminergic and serotonergic midbrain areas, whereas oppositional symptoms related to increased grey matter in a noradrenergic nucleus. Internalizing related to increased and oppositional symptoms to reduced grey matter density in insula, cingulate and auditory cortices. Striatal regions featured strongly, with reduced caudate nucleus grey matter in ADHD, and reduced putamen grey matter in oppositional/conduct problems. Voxel-wise grey matter density generated stronger brain-psychosocial correlations than brain parcellations. CONCLUSIONS: Voxel-wise brain data strengthen latent dimensions of brain-psychosocial covariation and sparse multivariate methods increase their psychopathological specificity. Internalizing and externalizing are associated with opposite grey matter changes in similar cortical and subcortical areas.

Spectral density-based clustering algorithms for complex networks.

Introduction: Clustering is usually the first exploratory analysis step in empirical data. When the data set comprises graphs, the most common approaches focus on clustering its vertices. In this work, we are interested in grouping networks with similar connectivity structures together instead of grouping vertices of the graph. We could apply this approach to functional brain networks (FBNs) for identifying subgroups of people presenting similar functional connectivity, such as studying a mental disorder. The main problem is that real-world networks present natural fluctuations, which we should consider. Methods: In this context, spectral density is an exciting feature because graphs generated by different models present distinct spectral densities, thus presenting different connectivity structures. We introduce two clustering methods: k-means for graphs of the same size and gCEM, a model-based approach for graphs of different sizes. We evaluated their performance in toy models. Finally, we applied them to FBNs of monkeys under anesthesia and a dataset of chemical compounds. Results: We show that our methods work well in both toy models and real-world data. They present good results for clustering graphs presenting different connectivity structures even when they present the same number of edges, vertices, and degree of centrality. Discussion: We recommend using k-means-based clustering for graphs when graphs present the same number of vertices and the gCEM method when graphs present a different number of vertices.

A cross-cohort replicable and heritable latent dimension linking behaviour to multi-featured brain structure.

Identifying associations between interindividual variability in brain structure and behaviour requires large cohorts, multivariate methods, out-of-sample validation and, ideally, out-of-cohort replication. Moreover, the influence of nature vs nurture on brain-behaviour associations should be analysed. We analysed associations between brain structure (grey matter volume, cortical thickness, and surface area) and behaviour (spanning cognition, emotion, and alertness) using regularized canonical correlation analysis and a machine learning framework that tests the generalisability and stability of such associations. The replicability of brain-behaviour associations was assessed in two large, independent cohorts. The load of genetic factors on these associations was analysed with heritability and genetic correlation. We found one heritable and replicable latent dimension linking cognitive-control/executive-functions and positive affect to brain structural variability in areas typically associated with higher cognitive functions, and with areas typically associated with sensorimotor functions. These results revealed a major axis of interindividual behavioural variability linking to a whole-brain structural pattern.

Canonical Correlation Analysis and Partial Least Squares for Identifying Brain-Behavior Associations: A Tutorial and a Comparative Study.

Canonical correlation analysis (CCA) and partial least squares (PLS) are powerful multivariate methods for capturing associations across 2 modalities of data (e.g., brain and behavior). However, when the sample size is similar to or smaller than the number of variables in the data, standard CCA and PLS models may overfit, i.e., find spurious associations that generalize poorly to new data. Dimensionality reduction and regularized extensions of CCA and PLS have been proposed to address this problem, yet most studies using these approaches have some limitations. This work gives a theoretical and practical introduction into the most common CCA/PLS models and their regularized variants. We examine the limitations of standard CCA and PLS when the sample size is similar to or smaller than the number of variables. We discuss how dimensionality reduction and regularization techniques address this problem and explain their main advantages and disadvantages. We highlight crucial aspects of the CCA/PLS analysis framework, including optimizing the hyperparameters of the model and testing the identified associations for statistical significance. We apply the described CCA/PLS models to simulated data and real data from the Human Connectome Project and Alzheimer's Disease Neuroimaging Initiative (both of n > 500). We use both low- and high-dimensionality versions of these data (i.e., ratios between sample size and variables in the range of ∼1-10 and ∼0.1-0.01, respectively) to demonstrate the impact of data dimensionality on the models. Finally, we summarize the key lessons of the tutorial.

A hierarchical Bayesian model to find brain-behaviour associations in incomplete data sets.

Canonical Correlation Analysis (CCA) and its regularised versions have been widely used in the neuroimaging community to uncover multivariate associations between two data modalities (e.g., brain imaging and behaviour). However, these methods have inherent limitations: (1) statistical inferences about the associations are often not robust; (2) the associations within each data modality are not modelled; (3) missing values need to be imputed or removed. Group Factor Analysis (GFA) is a hierarchical model that addresses the first two limitations by providing Bayesian inference and modelling modality-specific associations. Here, we propose an extension of GFA that handles missing data, and highlight that GFA can be used as a predictive model. We applied GFA to synthetic and real data consisting of brain connectivity and non-imaging measures from the Human Connectome Project (HCP). In synthetic data, GFA uncovered the underlying shared and specific factors and predicted correctly the non-observed data modalities in complete and incomplete data sets. In the HCP data, we identified four relevant shared factors, capturing associations between mood, alcohol and drug use, cognition, demographics and psychopathological measures and the default mode, frontoparietal control, dorsal and ventral networks and insula, as well as two factors describing associations within brain connectivity. In addition, GFA predicted a set of non-imaging measures from brain connectivity. These findings were consistent in complete and incomplete data sets, and replicated previous findings in the literature. GFA is a promising tool that can be used to uncover associations between and within multiple data modalities in benchmark datasets (such as, HCP), and easily extended to more complex models to solve more challenging tasks.

Will artificial intelligence eventually replace psychiatrists?

SUMMARY: The dystopian scenario of an 'artificial intelligence takeover' imagines artificial intelligence (AI) becoming the dominant form of intelligence on Earth, rendering humans redundant. As a society we have become increasingly familiar with AI and robots replacing humans in many tasks, certain jobs and even some areas of medicine, but surely this is not the fate of psychiatry?Here a computational neuroscientist (Janaina Mourão-Miranda) and psychiatrist (Justin Taylor Baker) suggest that psychiatry as a profession is relatively safe, whereas psychiatrists Christian Brown and Giles William Story predict that robots will be taking over the asylum.

Correction to: How do you perceive threat? It's all in your pattern of brain activity.

The author found a mistake in their published article. They observed that Fig. 2 presented some mistakes as follow.

Finding the needle in a high-dimensional haystack: Canonical correlation analysis for neuroscientists.

The 21st century marks the emergence of "big data" with a rapid increase in the availability of datasets with multiple measurements. In neuroscience, brain-imaging datasets are more commonly accompanied by dozens or hundreds of phenotypic subject descriptors on the behavioral, neural, and genomic level. The complexity of such "big data" repositories offer new opportunities and pose new challenges for systems neuroscience. Canonical correlation analysis (CCA) is a prototypical family of methods that is useful in identifying the links between variable sets from different modalities. Importantly, CCA is well suited to describing relationships across multiple sets of data, such as in recently available big biomedical datasets. Our primer discusses the rationale, promises, and pitfalls of CCA.

Fast temporal dynamics and causal relevance of face processing in the human temporal cortex.

We measured the fast temporal dynamics of face processing simultaneously across the human temporal cortex (TC) using intracranial recordings in eight participants. We found sites with selective responses to faces clustered in the ventral TC, which responded increasingly strongly to marine animal, bird, mammal, and human faces. Both face-selective and face-active but non-selective sites showed a posterior to anterior gradient in response time and selectivity. A sparse model focusing on information from the human face-selective sites performed as well as, or better than, anatomically distributed models when discriminating faces from non-faces stimuli. Additionally, we identified the posterior fusiform site (pFUS) as causally the most relevant node for inducing distortion of conscious face processing by direct electrical stimulation. These findings support anatomically discrete but temporally distributed response profiles in the human brain and provide a new common ground for unifying the seemingly contradictory modular and distributed modes of face processing.

Multiple Holdouts With Stability: Improving the Generalizability of Machine Learning Analyses of Brain-Behavior Relationships.

BACKGROUND: In 2009, the National Institute of Mental Health launched the Research Domain Criteria, an attempt to move beyond diagnostic categories and ground psychiatry within neurobiological constructs that combine different levels of measures (e.g., brain imaging and behavior). Statistical methods that can integrate such multimodal data, however, are often vulnerable to overfitting, poor generalization, and difficulties in interpreting the results. METHODS: We propose an innovative machine learning framework combining multiple holdouts and a stability criterion with regularized multivariate techniques, such as sparse partial least squares and kernel canonical correlation analysis, for identifying hidden dimensions of cross-modality relationships. To illustrate the approach, we investigated structural brain-behavior associations in an extensively phenotyped developmental sample of 345 participants (312 healthy and 33 with clinical depression). The brain data consisted of whole-brain voxel-based gray matter volumes, and the behavioral data included item-level self-report questionnaires and IQ and demographic measures. RESULTS: Both sparse partial least squares and kernel canonical correlation analysis captured two hidden dimensions of brain-behavior relationships: one related to age and drinking and the other one related to depression. The applied machine learning framework indicates that these results are stable and generalize well to new data. Indeed, the identified brain-behavior associations are in agreement with previous findings in the literature concerning age, alcohol use, and depression-related changes in brain volume. CONCLUSIONS: Multivariate techniques (such as sparse partial least squares and kernel canonical correlation analysis) embedded in our novel framework are promising tools to link behavior and/or symptoms to neurobiology and thus have great potential to contribute to a biologically grounded definition of psychiatric disorders.

How do you perceive threat? It's all in your pattern of brain activity.

Whether subtle differences in the emotional context during threat perception can be detected by multi-voxel pattern analysis (MVPA) remains a topic of debate. To investigate this question, we compared the ability of pattern recognition analysis to discriminate between patterns of brain activity to a threatening versus a physically paired neutral stimulus in two different emotional contexts (the stimulus being directed towards or away from the viewer). The directionality of the stimuli is known to be an important factor in activating different defensive responses. Using multiple kernel learning (MKL) classification models, we accurately discriminated patterns of brain activation to threat versus neutral stimuli in the directed towards context but not during the directed away context. Furthermore, we investigated whether it was possible to decode an individual's subjective threat perception from patterns of whole-brain activity to threatening stimuli in the different emotional contexts using MKL regression models. Interestingly, we were able to accurately predict the subjective threat perception index from the pattern of brain activation to threat only during the directed away context. These results show that subtle differences in the emotional context during threat perception can be detected by MVPA. In the directed towards context, the threat perception was more intense, potentially producing more homogeneous patterns of brain activation across individuals. In the directed away context, the threat perception was relatively less intense and more variable across individuals, enabling the regression model to successfully capture the individual differences and predict the subjective threat perception.

Brain-behaviour modes of covariation in healthy and clinically depressed young people.

Understanding how variations in dimensions of psychometrics, IQ and demographics relate to changes in brain connectivity during the critical developmental period of adolescence and early adulthood is a major challenge. This has particular relevance for mental health disorders where a failure to understand these links might hinder the development of better diagnostic approaches and therapeutics. Here, we investigated this question in 306 adolescents and young adults (14-24 y, 25 clinically depressed) using a multivariate statistical framework, based on canonical correlation analysis (CCA). By linking individual functional brain connectivity profiles to self-report questionnaires, IQ and demographic data we identified two distinct modes of covariation. The first mode mapped onto an externalization/internalization axis and showed a strong association with sex. The second mode mapped onto a well-being/distress axis independent of sex. Interestingly, both modes showed an association with age. Crucially, the changes in functional brain connectivity associated with changes in these phenotypes showed marked developmental effects. The findings point to a role for the default mode, frontoparietal and limbic networks in psychopathology and depression.

Predicting Bipolar Disorder Risk Factors in Distressed Young Adults From Patterns of Brain Activation to Reward: A Machine Learning Approach.

BACKGROUND: The aim of this study was to apply multivariate pattern recognition to predict the severity of behavioral traits and symptoms associated with risk for bipolar spectrum disorder from patterns of whole-brain activation during reward expectancy to facilitate the identification of individual-level neural biomarkers of bipolar disorder risk. METHODS: We acquired functional neuroimaging data from two independent samples of transdiagnostically recruited adults (18-25 years of age; n = 56, mean age 21.9 ± 2.2 years, 42 women; n = 36, mean age 21.2 ± 2.2 years, 24 women) during reward expectancy task performance. Pattern recognition model performance in each sample was measured using correlation and mean squared error between actual and whole-brain activation-predicted scores on behavioral traits and symptoms. RESULTS: In the first sample, the model significantly predicted severity of a specific hypo/mania-related symptom, heightened energy, measured by the energy manic subdomain of the Mood Spectrum Structured Interviews (r = .42, p = .001; mean squared error = 9.93, p = .001). The region with the highest contribution to the model was the left ventrolateral prefrontal cortex. Results were confirmed in the second sample (r = .33, p = .01; mean squared error = 8.61, p = .01), in which the severity of this symptom was predicted using a bilateral ventrolateral prefrontal cortical mask (r = .33, p = .009, mean squared error = 9.37, p = .04). CONCLUSIONS: The severity of a specific hypo/mania-related symptom was predicted from patterns of whole-brain activation in two independent samples. Given that emerging manic symptoms predispose to bipolar disorders, these findings could provide neural biomarkers to aid early identification of individual-level bipolar disorder risk in young adults.

Predicting anxiety from wholebrain activity patterns to emotional faces in young adults: a machine learning approach.

BACKGROUND: It is becoming increasingly clear that pathophysiological processes underlying psychiatric disorders categories are heterogeneous on many levels, including symptoms, disease course, comorbidity and biological underpinnings. This heterogeneity poses challenges for identifying biological markers associated with dimensions of symptoms and behaviour that could provide targets to guide treatment choice and novel treatment. In response, the research domain criteria (RDoC) (Insel et al., 2010) was developed to advocate a dimensional approach which omits any disease definitions, disorder thresholds, or cut-points for various levels of psychopathology to understanding the pathophysiological processes underlying psychiatry disorders. In the present study we aimed to apply pattern regression analysis to identify brain signatures during dynamic emotional face processing that are predictive of anxiety and depression symptoms in a continuum that ranges from normal to pathological levels, cutting across categorically-defined diagnoses. METHODS: The sample was composed of one-hundred and fifty-four young adults (mean age=21.6 and s.d.=2.0, 103 females) consisting of eighty-two young adults seeking treatment for psychological distress that cut across categorically-defined diagnoses and 72 matched healthy young adults. Participants performed a dynamic face task involving fearful, angry and happy faces (and geometric shapes) while undergoing functional Magnetic Resonance Imaging (fMRI). Pattern regression analyses consisted of Gaussian Process Regression (GPR) implemented in the Pattern Recognition for Neuroimaging toolbox (PRoNTo). Predicted and actual clinical scores were compared using Pearson's correlation coefficient (r) and normalized mean squared error (MSE) to evaluate the models' performance. Permutation test was applied to estimate significance levels. RESULTS: GPR identified patterns of neural activity to dynamic emotional face processing predictive of self-report anxiety in the whole sample, which covered a continuum that ranged from healthy to different levels of distress, including subthreshold to fully-syndromal psychiatric diagnoses. Results were significant using two different cross validation strategies (two-fold: r=0.28 (p-value=0.001), MSE=4.47 (p-value=0.001) and five fold r=0.28 (p-value=0.002), MSE=4.62 (p-value=0.003). The contributions of individual regions to the predictive model were very small, demonstrating that predictions were based on the overall pattern rather than on a small combination of regions. CONCLUSIONS: These findings represent early evidence that neuroimaging techniques may inform clinical assessment of young adults irrespective of diagnoses by allowing accurate and objective quantitative estimation of psychopathology.

Combining heterogeneous data sources for neuroimaging based diagnosis: re-weighting and selecting what is important.

Combining neuroimaging and clinical information for diagnosis, as for example behavioral tasks and genetics characteristics, is potentially beneficial but presents challenges in terms of finding the best data representation for the different sources of information. Their simple combination usually does not provide an improvement if compared with using the best source alone. In this paper, we proposed a framework based on a recent multiple kernel learning algorithm called EasyMKL and we investigated the benefits of this approach for diagnosing two different mental health diseases. The well known Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset tackling the Alzheimer Disease (AD) patients versus healthy controls classification task, and a second dataset tackling the task of classifying an heterogeneous group of depressed patients versus healthy controls. We used EasyMKL to combine a huge amount of basic kernels alongside a feature selection methodology, pursuing an optimal and sparse solution to facilitate interpretability. Our results show that the proposed approach, called EasyMKLFS, outperforms baselines (e.g. SVM and SimpleMKL), state-of-the-art random forests (RF) and feature selection (FS) methods.

Making Individual Prognoses in Psychiatry Using Neuroimaging and Machine Learning.

Psychiatric prognosis is a difficult problem. Making a prognosis requires looking far into the future, as opposed to making a diagnosis, which is concerned with the current state. During the follow-up period, many factors will influence the course of the disease. Combined with the usually scarcer longitudinal data and the variability in the definition of outcomes/transition, this makes prognostic predictions a challenging endeavor. Employing neuroimaging data in this endeavor introduces the additional hurdle of high dimensionality. Machine learning techniques are especially suited to tackle this challenging problem. This review starts with a brief introduction to machine learning in the context of its application to clinical neuroimaging data. We highlight a few issues that are especially relevant for prediction of outcome and transition using neuroimaging. We then review the literature that discusses the application of machine learning for this purpose. Critical examination of the studies and their results with respect to the relevant issues revealed the following: 1) there is growing evidence for the prognostic capability of machine learning-based models using neuroimaging; and 2) reported accuracies may be too optimistic owing to small sample sizes and the lack of independent test samples. Finally, we discuss options to improve the reliability of (prognostic) prediction models. These include new methodologies and multimodal modeling. Paramount, however, is our conclusion that future work will need to provide properly (cross-)validated accuracy estimates of models trained on sufficiently large datasets. Nevertheless, with the technological advances enabling acquisition of large databases of patients and healthy subjects, machine learning represents a powerful tool in the search for psychiatric biomarkers.

Sparsity Is Better with Stability: Combining Accuracy and Stability for Model Selection in Brain Decoding.

Structured sparse methods have received significant attention in neuroimaging. These methods allow the incorporation of domain knowledge through additional spatial and temporal constraints in the predictive model and carry the promise of being more interpretable than non-structured sparse methods, such as LASSO or Elastic Net methods. However, although sparsity has often been advocated as leading to more interpretable models it can also lead to unstable models under subsampling or slight changes of the experimental conditions. In the present work we investigate the impact of using stability/reproducibility as an additional model selection criterion on several different sparse (and structured sparse) methods that have been recently applied for fMRI brain decoding. We compare three different model selection criteria: (i) classification accuracy alone; (ii) classification accuracy and overlap between the solutions; (iii) classification accuracy and correlation between the solutions. The methods we consider include LASSO, Elastic Net, Total Variation, sparse Total Variation, Laplacian and Graph Laplacian Elastic Net (GraphNET). Our results show that explicitly accounting for stability/reproducibility during the model optimization can mitigate some of the instability inherent in sparse methods. In particular, using accuracy and overlap between the solutions as a joint optimization criterion can lead to solutions that are more similar in terms of accuracy, sparsity levels and coefficient maps even when different sparsity methods are considered.

Predictive modelling using neuroimaging data in the presence of confounds.

When training predictive models from neuroimaging data, we typically have available non-imaging variables such as age and gender that affect the imaging data but which we may be uninterested in from a clinical perspective. Such variables are commonly referred to as 'confounds'. In this work, we firstly give a working definition for confound in the context of training predictive models from samples of neuroimaging data. We define a confound as a variable which affects the imaging data and has an association with the target variable in the sample that differs from that in the population-of-interest, i.e., the population over which we intend to apply the estimated predictive model. The focus of this paper is the scenario in which the confound and target variable are independent in the population-of-interest, but the training sample is biased due to a sample association between the target and confound. We then discuss standard approaches for dealing with confounds in predictive modelling such as image adjustment and including the confound as a predictor, before deriving and motivating an Instance Weighting scheme that attempts to account for confounds by focusing model training so that it is optimal for the population-of-interest. We evaluate the standard approaches and Instance Weighting in two regression problems with neuroimaging data in which we train models in the presence of confounding, and predict samples that are representative of the population-of-interest. For comparison, these models are also evaluated when there is no confounding present. In the first experiment we predict the MMSE score using structural MRI from the ADNI database with gender as the confound, while in the second we predict age using structural MRI from the IXI database with acquisition site as the confound. Considered over both datasets we find that none of the methods for dealing with confounding gives more accurate predictions than a baseline model which ignores confounding, although including the confound as a predictor gives models that are less accurate than the baseline model. We do find, however, that different methods appear to focus their predictions on specific subsets of the population-of-interest, and that predictive accuracy is greater when there is no confounding present. We conclude with a discussion comparing the advantages and disadvantages of each approach, and the implications of our evaluation for building predictive models that can be used in clinical practice.