Brain responses to anticipatory cues and milkshake taste in obesity, and their relationship to bariatric surgery outcome.

There is substantial variability in percent total weight loss (%TWL) following bariatric surgery. Functional brain imaging may explain more variance in post-surgical weight loss than psychological or metabolic information. Here we examined the neuronal responses during anticipatory cues and receipt of drops of milkshake in 52 pre-bariatric surgery men and women with severe obesity (OW, BMI = 35-60 kg/m2) (23 sleeve gastrectomy (SG), 24 Roux-en-Y gastric bypass (RYGB), 3 laparoscopic adjustable gastric banding (LAGB), 2 did not undergo surgery) and 21 healthy-weight (HW) controls (BMI = 19-27 kg/m2). One-year post-surgery weight loss ranged from 3.1 to 44.0 TWL%. Compared to HW, OW had a stronger response to milkshake cues (compared to water) in frontal and motor, somatosensory, occipital, and cerebellar regions. Responses to milkshake taste receipt (compared to water) differed from HW in frontal, motor, and supramarginal regions where OW showed more similar response to water. One year post-surgery, responses to high-fat milkshake cues normalized in frontal, motor, and somatosensory regions. This change in brain response was related to scores on a composite health index. We found no correlation between baseline response to milkshake cues or tastes and%TWL at 1-yr post-surgery. In RYGB participants only, a stronger response to low-fat milkshake and water cues (compared to high-fat) in supramarginal and cuneal regions respectively was associated with more weight loss. A stronger cerebellar response to high-fat vs low-fat milkshake receipt was also associated with more weight loss. We confirm differential responses to anticipatory milkshake cues in participants with severe obesity and HW in the largest adult cohort to date. Our brain wide results emphasizes the need to look beyond reward and cognitive control regions. Despite the lack of a correlation with post-surgical weight loss in the entire surgical group, participants who underwent RYGB showed predictive power in several regions and contrasts. Our findings may help in understanding the neuronal mechanisms associated with obesity.

Individualized prediction of three- and six-year outcomes of psychosis in a longitudinal multicenter study: a machine learning approach.

Schizophrenia and related disorders have heterogeneous outcomes. Individualized prediction of long-term outcomes may be helpful in improving treatment decisions. Utilizing extensive baseline data of 523 patients with a psychotic disorder and variable illness duration, we predicted symptomatic and global outcomes at 3-year and 6-year follow-ups. We classified outcomes as (1) symptomatic: in remission or not in remission, and (2) global outcome, using the Global Assessment of Functioning (GAF) scale, divided into good (GAF ≥ 65) and poor (GAF < 65). Aiming for a robust and interpretable prediction model, we employed a linear support vector machine and recursive feature elimination within a nested cross-validation design to obtain a lean set of predictors. Generalization to out-of-study samples was estimated using leave-one-site-out cross-validation. Prediction accuracies were above chance and ranged from 62.2% to 64.7% (symptomatic outcome), and 63.5-67.6% (global outcome). Leave-one-site-out cross-validation demonstrated the robustness of our models, with a minor drop in predictive accuracies of 2.3% on average. Important predictors included GAF scores, psychotic symptoms, quality of life, antipsychotics use, psychosocial needs, and depressive symptoms. These robust, albeit modestly accurate, long-term prognostic predictions based on lean predictor sets indicate the potential of machine learning models complementing clinical judgment and decision-making. Future model development may benefit from studies scoping patient's and clinicians' needs in prognostication.

Associations of cannabis use disorder with cognition, brain structure, and brain function in African Americans.

Although previous studies have highlighted associations of cannabis use with cognition and brain morphometry, critical questions remain with regard to the association between cannabis use and brain structural and functional connectivity. In a cross-sectional community sample of 205 African Americans (age 18-70) we tested for associations of cannabis use disorder (CUD, n = 57) with multi-domain cognitive measures and structural, diffusion, and resting state brain-imaging phenotypes. Post hoc model evidence was computed with Bayes factors (BF) and posterior probabilities of association (PPA) to account for multiple testing. General cognitive functioning, verbal intelligence, verbal memory, working memory, and motor speed were lower in the CUD group compared with non-users (p < .011; 1.9 < BF < 3,217). CUD was associated with altered functional connectivity in a network comprising the motor-hand region in the superior parietal gyri and the anterior insula (p < .04). These differences were not explained by alcohol, other drug use, or education. No associations with CUD were observed in cortical thickness, cortical surface area, subcortical or cerebellar volumes (0.12 < BF < 1.5), or graph-theoretical metrics of resting state connectivity (PPA < 0.01). In a large sample collected irrespective of cannabis used to minimize recruitment bias, we confirm the literature on poorer cognitive functioning in CUD, and an absence of volumetric brain differences between CUD and non-CUD. We did not find evidence for or against a disruption of structural connectivity, whereas we did find localized resting state functional dysconnectivity in CUD. There was sufficient proof, however, that organization of functional connectivity as determined via graph metrics does not differ between CUD and non-user group.

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.

Resting-state subcortical functional connectivity in HIV-infected patients on long-term cART.

Despite long-term successful treatment with cART, impairments in cognitive functioning are still being reported in HIV-infected patients. Since changes in cognitive function may be preceded by subtle changes in brain function, neuroimaging techniques, such as resting-state functional magnetic resonance imaging (rs-fMRI) have become useful tools in assessing HIV-associated abnormalities in the brain. The purpose of the current study was to examine the extent to which HIV infection in virologically suppressed patients is associated with disruptions in subcortical regions of the brain in comparison to a matched HIV-negative control group. The sample consisted of 72 patients and 39 controls included between January 2012 and January 2014. Resting state functional connectivity was determined between fourteen regions-of-interest (ROI): the left and right nucleus accumbens, amygdala, caudate nucleus, hippocampus, putamen, pallidum and thalamus. A Bayesian method was used to estimate resting-state functional connectivity, quantified in terms of partial correlations. Both groups showed the strongest partial correlations between the left and right caudate nucleus and the left and right thalamus. However, no differences between the HIV patients and controls were found between the posterior expected network densities (control network density = 0.26, SD = 0.05, patient network density = 0.26, SD = 0.04, p = 0.58). The results of the current study show that HIV does not affect subcortical connectivity in virologically controlled patients who are otherwise healthy.

Let's Not Waste Time: Using Temporal Information in Clustered Activity Estimation with Spatial Adjacency Restrictions (CAESAR) for Parcellating FMRI Data.

We have proposed a Bayesian approach for functional parcellation of whole-brain FMRI measurements which we call Clustered Activity Estimation with Spatial Adjacency Restrictions (CAESAR). We use distance-dependent Chinese restaurant processes (dd-CRPs) to define a flexible prior which partitions the voxel measurements into clusters whose number and shapes are unknown a priori. With dd-CRPs we can conveniently implement spatial constraints to ensure that our parcellations remain spatially contiguous and thereby physiologically meaningful. In the present work, we extend CAESAR by using Gaussian process (GP) priors to model the temporally smooth haemodynamic signals that give rise to the measured FMRI data. A challenge for GP inference in our setting is the cubic scaling with respect to the number of time points, which can become computationally prohibitive with FMRI measurements, potentially consisting of long time series. As a solution we describe an efficient implementation that is practically as fast as the corresponding time-independent non-GP model with typically-sized FMRI data sets. We also employ a population Monte-Carlo algorithm that can significantly speed up convergence compared to traditional single-chain methods. First we illustrate the benefits of CAESAR and the GP priors with simulated experiments. Next, we demonstrate our approach by parcellating resting state FMRI data measured from twenty participants as taken from the Human Connectome Project data repository. Results show that CAESAR affords highly robust and scalable whole-brain clustering of FMRI timecourses.

Bayesian Estimation of Conditional Independence Graphs Improves Functional Connectivity Estimates.

Functional connectivity concerns the correlated activity between neuronal populations in spatially segregated regions of the brain, which may be studied using functional magnetic resonance imaging (fMRI). This coupled activity is conveniently expressed using covariance, but this measure fails to distinguish between direct and indirect effects. A popular alternative that addresses this issue is partial correlation, which regresses out the signal of potentially confounding variables, resulting in a measure that reveals only direct connections. Importantly, provided the data are normally distributed, if two variables are conditionally independent given all other variables, their respective partial correlation is zero. In this paper, we propose a probabilistic generative model that allows us to estimate functional connectivity in terms of both partial correlations and a graph representing conditional independencies. Simulation results show that this methodology is able to outperform the graphical LASSO, which is the de facto standard for estimating partial correlations. Furthermore, we apply the model to estimate functional connectivity for twenty subjects using resting-state fMRI data. Results show that our model provides a richer representation of functional connectivity as compared to considering partial correlations alone. Finally, we demonstrate how our approach can be extended in several ways, for instance to achieve data fusion by informing the conditional independence graph with data from probabilistic tractography. As our Bayesian formulation of functional connectivity provides access to the posterior distribution instead of only to point estimates, we are able to quantify the uncertainty associated with our results. This reveals that while we are able to infer a clear backbone of connectivity in our empirical results, the data are not accurately described by simply looking at the mode of the distribution over connectivity. The implication of this is that deterministic alternatives may misjudge connectivity results by drawing conclusions from noisy and limited data.

Probabilistic clustering of the human connectome identifies communities and hubs.

A fundamental assumption in neuroscience is that brain function is constrained by its structural properties. This motivates the idea that the brain can be parcellated into functionally coherent regions based on anatomical connectivity patterns that capture how different areas are interconnected. Several studies have successfully implemented this idea in humans using diffusion weighted MRI, allowing parcellation to be conducted in vivo. Two distinct approaches to connectivity-based parcellation can be identified. The first uses the connection profiles of brain regions as a feature vector, and groups brain regions with similar connection profiles together. Alternatively, one may adopt a network perspective that aims to identify clusters of brain regions that show dense within-cluster and sparse between-cluster connectivity. In this paper, we introduce a probabilistic model for connectivity-based parcellation that unifies both approaches. Using the model we are able to obtain a parcellation of the human brain whose clusters may adhere to either interpretation. We find that parts of the connectome consistently cluster as densely connected components, while other parts consistently result in clusters with similar connections. Interestingly, the densely connected components consist predominantly of major cortical areas, while the clusters with similar connection profiles consist of regions that have previously been identified as the 'rich club'; regions known for their integrative role in connectivity. Furthermore, the probabilistic model allows quantification of the uncertainty in cluster assignments. We show that, while most clusters are clearly delineated, some regions are more difficult to assign. These results indicate that care should be taken when interpreting connectivity-based parcellations obtained using alternative deterministic procedures.

Quantifying uncertainty in brain network measures using Bayesian connectomics.

The wiring diagram of the human brain can be described in terms of graph measures that characterize structural regularities. These measures require an estimate of whole-brain structural connectivity for which one may resort to deterministic or thresholded probabilistic streamlining procedures. While these procedures have provided important insights about the characteristics of human brain networks, they ultimately rely on unwarranted assumptions such as those of noise-free data or the use of an arbitrary threshold. Therefore, resulting structural connectivity estimates as well as derived graph measures fail to fully take into account the inherent uncertainty in the structural estimate. In this paper, we illustrate an easy way of obtaining posterior distributions over graph metrics using Bayesian inference. It is shown that this posterior distribution can be used to quantify uncertainty about graph-theoretical measures at the single subject level, thereby providing a more nuanced view of the graph-theoretical properties of human brain connectivity. We refer to this model-based approach to connectivity analysis as Bayesian connectomics.

Structurally-informed Bayesian functional connectivity analysis.

Functional connectivity refers to covarying activity between spatially segregated brain regions and can be studied by measuring correlation between functional magnetic resonance imaging (fMRI) time series. These correlations can be caused either by direct communication via active axonal pathways or indirectly via the interaction with other regions. It is not possible to discriminate between these two kinds of functional interaction simply by considering the covariance matrix. However, the non-diagonal elements of its inverse, the precision matrix, can be naturally related to direct communication between brain areas and interpreted in terms of partial correlations. In this paper, we propose a Bayesian model for functional connectivity analysis which allows estimation of a posterior density over precision matrices, and, consequently, allows one to quantify the uncertainty about estimated partial correlations. In order to make model estimation feasible it is assumed that the sparseness structure of the precision matrices is given by an estimate of structural connectivity obtained using diffusion imaging data. The model was tested on simulated data as well as resting-state fMRI data and compared with a graphical lasso analysis. The presented approach provides a theoretically solid foundation for quantifying functional connectivity in the presence of uncertainty.