Accommodating site variation in neuroimaging data using normative and hierarchical Bayesian models.

The potential of normative modeling to make individualized predictions from neuroimaging data has enabled inferences that go beyond the case-control approach. However, site effects are often confounded with variables of interest in a complex manner and can bias estimates of normative models, which has impeded the application of normative models to large multi-site neuroimaging data sets. In this study, we suggest accommodating for these site effects by including them as random effects in a hierarchical Bayesian model. We compared the performance of a linear and a non-linear hierarchical Bayesian model in modeling the effect of age on cortical thickness. We used data of 570 healthy individuals from the ABIDE (autism brain imaging data exchange) data set in our experiments. In addition, we used data from individuals with autism to test whether our models are able to retain clinically useful information while removing site effects. We compared the proposed single stage hierarchical Bayesian method to several harmonization techniques commonly used to deal with additive and multiplicative site effects using a two stage regression, including regressing out site and harmonizing for site with ComBat, both with and without explicitly preserving variance caused by age and sex as biological variation of interest, and with a non-linear version of ComBat. In addition, we made predictions from raw data, in which site has not been accommodated for. The proposed hierarchical Bayesian method showed the best predictive performance according to multiple metrics. Beyond that, the resulting z-scores showed little to no residual site effects, yet still retained clinically useful information. In contrast, performance was particularly poor for the regression model and the ComBat model in which age and sex were not explicitly modeled. In all two stage harmonization models, predictions were poorly scaled, suffering from a loss of more than 90% of the original variance. Our results show the value of hierarchical Bayesian regression methods for accommodating site variation in neuroimaging data, which provides an alternative to harmonization techniques. While the approach we propose may have broad utility, our approach is particularly well suited to normative modeling where the primary interest is in accurate modeling of inter-subject variation and statistical quantification of deviations from a reference model.

Predicting individual improvement in schizophrenia symptom severity at 1-year follow-up: Comparison of connectomic, structural, and clinical predictors.

In a machine learning setting, this study aims to compare the prognostic utility of connectomic, brain structural, and clinical/demographic predictors of individual change in symptom severity in individuals with schizophrenia. Symptom severity at baseline and 1-year follow-up was assessed in 30 individuals with a schizophrenia-spectrum disorder using the Brief Psychiatric Rating Scale. Structural and functional neuroimaging was acquired in all individuals at baseline. Machine learning classifiers were trained to predict whether individuals improved or worsened with respect to positive, negative, and overall symptom severity. Classifiers were trained using various combinations of predictors, including regional cortical thickness and gray matter volume, static and dynamic resting-state connectivity, and/or baseline clinical and demographic variables. Relative change in overall symptom severity between baseline and 1-year follow-up varied markedly among individuals (interquartile range: 55%). Dynamic resting-state connectivity measured within the default-mode network was the most accurate single predictor of change in positive (accuracy: 87%), negative (83%), and overall symptom severity (77%) at follow-up. Incorporating predictors based on regional cortical thickness, gray matter volume, and baseline clinical variables did not markedly improve prediction accuracy and the prognostic utility of these predictors in isolation was moderate (<70%). Worsening negative symptoms at 1-year follow-up were predicted by hyper-connectivity and hypo-dynamism within the default-mode network at baseline assessment, while hypo-connectivity and hyper-dynamism predicted worsening positive symptoms. Given the modest sample size investigated, we recommend giving precedence to the relative ranking of the predictors investigated in this study, rather than the prediction accuracy estimates.

Brain network dynamics in schizophrenia: Reduced dynamism of the default mode network.

Complex human behavior emerges from dynamic patterns of neural activity that transiently synchronize between distributed brain networks. This study aims to model the dynamics of neural activity in individuals with schizophrenia and to investigate whether the attributes of these dynamics associate with the disorder's behavioral and cognitive deficits. A hidden Markov model (HMM) was inferred from resting-state functional magnetic resonance imaging (fMRI) data that was temporally concatenated across individuals with schizophrenia (n = 41) and healthy comparison individuals (n = 41). Under the HMM, fluctuations in fMRI activity within 14 canonical resting-state networks were described using a repertoire of 12 brain states. The proportion of time spent in each state and the mean length of visits to each state were compared between groups, and canonical correlation analysis was used to test for associations between these state descriptors and symptom severity. Individuals with schizophrenia activated default mode and executive networks for a significantly shorter proportion of the 8-min acquisition than healthy comparison individuals. While the default mode was activated less frequently in schizophrenia, the duration of each activation was on average 4-5 s longer than the comparison group. Severity of positive symptoms was associated with a longer proportion of time spent in states characterized by inactive default mode and executive networks, together with heightened activity in sensory networks. Furthermore, classifiers trained on the state descriptors predicted individual diagnostic status with an accuracy of 76-85%.

Spatio-temporal dynamics of resting-state brain networks improve single-subject prediction of schizophrenia diagnosis.

Correlation in functional MRI activity between spatially separated brain regions can fluctuate dynamically when an individual is at rest. These dynamics are typically characterized temporally by measuring fluctuations in functional connectivity between brain regions that remain fixed in space over time. Here, dynamics in functional connectivity were characterized in both time and space. Temporal dynamics were mapped with sliding-window correlation, while spatial dynamics were characterized by enabling network regions to vary in size (shrink/grow) over time according to the functional connectivity profile of their constituent voxels. These temporal and spatial dynamics were evaluated as biomarkers to distinguish schizophrenia patients from controls, and compared to current biomarkers based on static measures of resting-state functional connectivity. Support vector machine classifiers were trained using: (a) static, (b) dynamic in time, (c) dynamic in space, and (d) dynamic in time and space characterizations of functional connectivity within canonical resting-state brain networks. Classifiers trained on functional connectivity dynamics mapped over both space and time predicted diagnostic status with accuracy exceeding 91%, whereas utilizing only spatial or temporal dynamics alone yielded lower classification accuracies. Static measures of functional connectivity yielded the lowest accuracy (79.5%). Compared to healthy comparison individuals, schizophrenia patients generally exhibited functional connectivity that was reduced in strength and more variable. Robustness was established with replication in an independent dataset. The utility of biomarkers based on temporal and spatial functional connectivity dynamics suggests that resting-state dynamics are not trivially attributable to sampling variability and head motion.

Risk Factors for Suicide Attempt During Outpatient Care in Adolescents With Severe and Complex Depression.

Background: Young people receiving tertiary mental health care are at elevated risk for suicidal behavior, and understanding which individuals are at increased risk during care is important for treatment and suicide prevention. Aim: We aimed to retrospectively identify risk factors for attempted suicide during outpatient care and predict which young people did or did not attempt during care. Method: Penalized logistic regression analysis was performed in a small high-risk sample of 84 young people receiving care at Orygen's Youth Mood Clinic (age: 14-25 years, 51% female) to predict suicide attempt during care (N = 16). Results: Prediction of suicide attempt during care was only moderately accurate (Area Under the Receiver Operating Curve range 0.71; sensitivity 0.57) using a combination of sociodemographic, psychosocial, and clinical variables. The features that best discriminated both groups included suicidal ideation during care, history of suicide attempt prior to care, changes in appetite reported on the PHQ-9, history of parental separation, and parental mental illness. Limitation: Replication of findings in an independent validation sample is needed. Conclusion: While prediction of suicide attempt during care was only moderately successful, we were able to identify individual risk factors for suicidal behavior during care in a high-risk sample.

Daily Cannabidiol Administration for 10 Weeks Modulates Hippocampal and Amygdalar Resting-State Functional Connectivity in Cannabis Users: A Functional Magnetic Resonance Imaging Open-Label Clinical Trial.

Introduction: Cannabis use is associated with brain functional changes in regions implicated in prominent neuroscientific theories of addiction. Emerging evidence suggests that cannabidiol (CBD) is neuroprotective and may reverse structural brain changes associated with prolonged heavy cannabis use. In this study, we examine how an ∼10-week exposure of CBD in cannabis users affected resting-state functional connectivity in brain regions functionally altered by cannabis use. Materials and Methods: Eighteen people who use cannabis took part in a ∼10 weeks open-label pragmatic trial of self-administered daily 200 mg CBD in capsules. They were not required to change their cannabis exposure patterns. Participants were assessed at baseline and post-CBD exposure with structural magnetic resonance imaging (MRI) and a functional MRI resting-state task (eyes closed). Seed-based connectivity analyses were run to examine changes in the functional connectivity of a priori regions-the hippocampus and the amygdala. We explored if connectivity changes were associated with cannabinoid exposure (i.e., cumulative cannabis dosage over trial, and plasma CBD concentrations and Δ9-tetrahydrocannabinol (THC) plasma metabolites postexposure), and mental health (i.e., severity of anxiety, depression, and positive psychotic symptom scores), accounting for cigarette exposure in the past month, alcohol standard drinks in the past month and cumulative CBD dose during the trial. Results: Functional connectivity significantly decreased pre-to-post the CBD trial between the anterior hippocampus and precentral gyrus, with a strong effect size (d=1.73). Functional connectivity increased between the amygdala and the lingual gyrus pre-to-post the CBD trial, with a strong effect size (d=1.19). There were no correlations with cannabinoids or mental health symptom scores. Discussion: Prolonged CBD exposure may restore/reduce functional connectivity differences reported in cannabis users. These new findings warrant replication in a larger sample, using robust methodologies-double-blind and placebo-controlled-and in the most vulnerable people who use cannabis, including those with more severe forms of Cannabis Use Disorder and experiencing worse mental health outcomes (e.g., psychosis, depression).

Predicting Depression Onset in Young People Based on Clinical, Cognitive, Environmental, and Neurobiological Data.

BACKGROUND: Adolescent onset of depression is associated with long-lasting negative consequences. Identifying adolescents at risk for developing depression would enable the monitoring of risk factors and the development of early intervention strategies. Using machine learning to combine several risk factors from multiple modalities might allow prediction of depression onset at the individual level. METHODS: A subsample of a multisite longitudinal study in adolescents, the IMAGEN study, was used to predict future (subthreshold) major depressive disorder onset in healthy adolescents. Based on 2-year and 5-year follow-up data, participants were grouped into the following: 1) those developing a diagnosis of major depressive disorder or subthreshold major depressive disorder and 2) healthy control subjects. Baseline measurements of 145 variables from different modalities (clinical, cognitive, environmental, and structural magnetic resonance imaging) at age 14 years were used as input to penalized logistic regression (with different levels of penalization) to predict depression onset in a training dataset (n = 407). The features contributing the highest to the prediction were validated in an independent hold-out sample (three independent IMAGEN sites; n = 137). RESULTS: The area under the receiver operating characteristic curve for predicting depression onset ranged between 0.70 and 0.72 in the training dataset. Baseline severity of depressive symptoms, female sex, neuroticism, stressful life events, and surface area of the supramarginal gyrus contributed most to the predictive model and predicted onset of depression, with an area under the receiver operating characteristic curve between 0.68 and 0.72 in the independent validation sample. CONCLUSIONS: This study showed that depression onset in adolescents can be predicted based on a combination multimodal data of clinical characteristics, life events, personality traits, and brain structure variables.