Consistent Functional Connectivity Alterations in Schizophrenia Spectrum Disorder: A Multisite Study

Graph theoretical analysis and independent component analysis of diabetic optic neuropathy: A resting-state functional magnetic resonance imaging study

AIMS

This study aimed to investigate the resting-state functional connectivity and topologic characteristics of brain networks in patients with diabetic optic neuropathy (DON).

METHODS

Resting-state functional magnetic resonance imaging scans were performed on 23 patients and 41 healthy control (HC) subjects. We used independent component analysis and graph theoretical analysis to determine the topologic characteristics of the brain and as well as functional network connectivity (FNC) and topologic properties of brain networks.

RESULTS

Compared with HCs, patients with DON showed altered global characteristics. At the nodal level, the DON group had fewer nodal degrees in the thalamus and insula, and a greater number in the right rolandic operculum, right postcentral gyrus, and right superior temporal gyrus. In the internetwork comparison, DON patients showed significantly increased FNC between the left frontoparietal network (FPN-L) and ventral attention network (VAN). Additionally, in the intranetwork comparison, connectivity between the left medial superior frontal gyrus (MSFG) of the default network (DMN) and left putamen of auditory network was decreased in the DON group.

CONCLUSION

DON patients altered node properties and connectivity in the DMN, auditory network, FPN-L, and VAN. These results provide evidence of the involvement of specific brain networks in the pathophysiology of DON.

Functional magnetic resonance imaging in schizophrenia: current evidence, methodological advances, limitations and future directions

Functional neuroimaging emerged with great promise and has provided fundamental insights into the neurobiology of schizophrenia. However, it has faced challenges and criticisms, most notably a lack of clinical translation. This paper provides a comprehensive review and critical summary of the literature on functional neuroimaging, in particular functional magnetic resonance imaging (fMRI), in schizophrenia. We begin by reviewing research on fMRI biomarkers in schizophrenia and the clinical high risk phase through a historical lens, moving from case-control regional brain activation to global connectivity and advanced analytical approaches, and more recent machine learning algorithms to identify predictive neuroimaging features. Findings from fMRI studies of negative symptoms as well as of neurocognitive and social cognitive deficits are then reviewed. Functional neural markers of these symptoms and deficits may represent promising treatment targets in schizophrenia. Next, we summarize fMRI research related to antipsychotic medication, psychotherapy and psychosocial interventions, and neurostimulation, including treatment response and resistance, therapeutic mechanisms, and treatment targeting. We also review the utility of fMRI and data-driven approaches to dissect the heterogeneity of schizophrenia, moving beyond case-control comparisons, as well as methodological considerations and advances, including consortia and precision fMRI. Lastly, limitations and future directions of research in the field are discussed. Our comprehensive review suggests that, in order for fMRI to be clinically useful in the care of patients with schizophrenia, research should address potentially actionable clinical decisions that are routine in schizophrenia treatment, such as which antipsychotic should be prescribed or whether a given patient is likely to have persistent functional impairment. The potential clinical utility of fMRI is influenced by and must be weighed against cost and accessibility factors. Future evaluations of the utility of fMRI in prognostic and treatment response studies may consider including a health economics analysis.

Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium

BACKGROUND

Recent advances in data-driven computational approaches have been helpful in devising tools to objectively diagnose psychiatric disorders. However, current machine learning studies limited to small homogeneous samples, different methodologies, and different imaging collection protocols, limit the ability to directly compare and generalize their results. Here we aimed to classify individuals with PTSD versus controls and assess the generalizability using a large heterogeneous brain datasets from the ENIGMA-PGC PTSD Working group.

METHODS

We analyzed brain MRI data from 3,477 structural-MRI; 2,495 resting state-fMRI; and 1,952 diffusion-MRI. First, we identified the brain features that best distinguish individuals with PTSD from controls using traditional machine learning methods. Second, we assessed the utility of the denoising variational autoencoder (DVAE) and evaluated its classification performance. Third, we assessed the generalizability and reproducibility of both models using leave-one-site-out cross-validation procedure for each modality.

RESULTS

We found lower performance in classifying PTSD vs. controls with data from over 20 sites (60 % test AUC for s-MRI, 59 % for rs-fMRI and 56 % for d-MRI), as compared to other studies run on single-site data. The performance increased when classifying PTSD from HC without trauma history in each modality (75 % AUC). The classification performance remained intact when applying the DVAE framework, which reduced the number of features. Finally, we found that the DVAE framework achieved better generalization to unseen datasets compared with the traditional machine learning frameworks, albeit performance was slightly above chance.

CONCLUSION

These results have the potential to provide a baseline classification performance for PTSD when using large scale neuroimaging datasets. Our findings show that the control group used can heavily affect classification performance. The DVAE framework provided better generalizability for the multi-site data. This may be more significant in clinical practice since the neuroimaging-based diagnostic DVAE classification models are much less site-specific, rendering them more generalizable.

A meta-analysis and systematic review of single vs. multimodal neuroimaging techniques in the classification of psychosis

BACKGROUND

Psychotic disorders are characterized by structural and functional abnormalities in brain networks. Neuroimaging techniques map and characterize such abnormalities using unique features (e.g., structural integrity, coactivation). However, it is unclear if a specific method, or a combination of modalities, is particularly effective in identifying differences in brain networks of someone with a psychotic disorder.

METHODS

A systematic meta-analysis evaluated machine learning classification of schizophrenia spectrum disorders in comparison to healthy control participants using various neuroimaging modalities (i.e., T1-weighted imaging (T1), diffusion tensor imaging (DTI), resting state functional connectivity (rs-FC), or some combination (multimodal)). Criteria for manuscript inclusion included whole-brain analyses and cross-validation to provide a complete picture regarding the predictive ability of large-scale brain systems in psychosis. For this meta-analysis, we searched Ovid MEDLINE, PubMed, PsychInfo, Google Scholar, and Web of Science published between inception and March 13th 2023. Prediction results were averaged for studies using the same dataset, but parallel analyses were run that included studies with pooled sample across many datasets. We assessed bias through funnel plot asymmetry. A bivariate regression model determined whether differences in imaging modality, demographics, and preprocessing methods moderated classification. Separate models were run for studies with internal prediction (via cross-validation) and external prediction.

RESULTS

93 studies were identified for quantitative review (30 T1, 9 DTI, 40 rs-FC, and 14 multimodal). As a whole, all modalities reliably differentiated those with schizophrenia spectrum disorders from controls (OR = 2.64 (95%CI = 2.33 to 2.95)). However, classification was relatively similar across modalities: no differences were seen across modalities in the classification of independent internal data, and a small advantage was seen for rs-FC studies relative to T1 studies in classification in external datasets. We found large amounts of heterogeneity across results resulting in significant signs of bias in funnel plots and Egger's tests. Results remained similar, however, when studies were restricted to those with less heterogeneity, with continued small advantages for rs-FC relative to structural measures. Notably, in all cases, no significant differences were seen between multimodal and unimodal approaches, with rs-FC and unimodal studies reporting largely overlapping classification performance. Differences in demographics and analysis or denoising were not associated with changes in classification scores.

CONCLUSIONS

The results of this study suggest that neuroimaging approaches have promise in the classification of psychosis. Interestingly, at present most modalities perform similarly in the classification of psychosis, with slight advantages for rs-FC relative to structural modalities in some specific cases. Notably, results differed substantially across studies, with suggestions of biased effect sizes, particularly highlighting the need for more studies using external prediction and large sample sizes. Adopting more rigorous and systematized standards will add significant value toward understanding and treating this critical population.

Alterations in grey matter structure linked to frequency-specific cortico-subcortical connectivity in schizophrenia via multimodal data fusion

Schizophrenia (SZ) is a complex psychiatric disorder that is currently defined by symptomatic and behavioral, rather than biological, criteria. Neuroimaging is an appealing avenue for SZ biomarker development, as several neuroimaging-based studies comparing individuals with SZ to healthy controls (HC) have shown measurable group differences in brain structure, as well as functional brain alterations in both static and dynamic functional network connectivity (sFNC and dFNC, respectively). The recently proposed filter-banked connectivity (FBC) method extends the standard dFNC sliding-window approach to estimate FNC within an arbitrary number of distinct frequency bands. The initial implementation used a set of filters spanning the full connectivity spectral range, providing a unified approach to examine both sFNC and dFNC in a single analysis. Initial FBC results found that individuals with SZ spend more time in a less structured, more disconnected low-frequency (i.e., static) FNC state than HC, as well as preferential SZ occupancy in high-frequency connectivity states, suggesting a frequency-specific component underpinning the functional dysconnectivity observed in SZ. Building on these findings, we sought to link such frequency-specific patterns of FNC to covarying data-driven structural brain networks in the context of SZ. Specifically, we employ a multi-set canonical correlation analysis + joint independent components analysis (mCCA + jICA) data fusion framework to study the connection between grey matter volume (GMV) maps and FBC states across the full connectivity frequency spectrum. Our multimodal analysis identified two joint sources that captured co-varying patterns of frequency-specific functional connectivity and alterations in GMV with significant group differences in loading parameters between the SZ group and HC. The first joint source linked frequency-modulated connections between the subcortical and sensorimotor networks and GMV alterations in the frontal and temporal lobes, while the second joint source identified a relationship between low-frequency cerebellar-sensorimotor connectivity and structural changes in both the cerebellum and motor cortex. Together, these results show a strong connection between cortico-subcortical functional connectivity at both high and low frequencies and alterations in cortical GMV that may be relevant to the pathogenesis and pathophysiology of SZ.

Methodological and Quality Flaws in the Use of Artificial Intelligence in Mental Health Research: Systematic Review

BACKGROUND

Artificial intelligence (AI) is giving rise to a revolution in medicine and health care. Mental health conditions are highly prevalent in many countries, and the COVID-19 pandemic has increased the risk of further erosion of the mental well-being in the population. Therefore, it is relevant to assess the current status of the application of AI toward mental health research to inform about trends, gaps, opportunities, and challenges.

OBJECTIVE

This study aims to perform a systematic overview of AI applications in mental health in terms of methodologies, data, outcomes, performance, and quality.

METHODS

A systematic search in PubMed, Scopus, IEEE Xplore, and Cochrane databases was conducted to collect records of use cases of AI for mental health disorder studies from January 2016 to November 2021. Records were screened for eligibility if they were a practical implementation of AI in clinical trials involving mental health conditions. Records of AI study cases were evaluated and categorized by the International Classification of Diseases 11th Revision (ICD-11). Data related to trial settings, collection methodology, features, outcomes, and model development and evaluation were extracted following the CHARMS (Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies) guideline. Further, evaluation of risk of bias is provided.

RESULTS

A total of 429 nonduplicated records were retrieved from the databases and 129 were included for a full assessment-18 of which were manually added. The distribution of AI applications in mental health was found unbalanced between ICD-11 mental health categories. Predominant categories were Depressive disorders (n=70) and Schizophrenia or other primary psychotic disorders (n=26). Most interventions were based on randomized controlled trials (n=62), followed by prospective cohorts (n=24) among observational studies. AI was typically applied to evaluate quality of treatments (n=44) or stratify patients into subgroups and clusters (n=31). Models usually applied a combination of questionnaires and scales to assess symptom severity using electronic health records (n=49) as well as medical images (n=33). Quality assessment revealed important flaws in the process of AI application and data preprocessing pipelines. One-third of the studies (n=56) did not report any preprocessing or data preparation. One-fifth of the models were developed by comparing several methods (n=35) without assessing their suitability in advance and a small proportion reported external validation (n=21). Only 1 paper reported a second assessment of a previous AI model. Risk of bias and transparent reporting yielded low scores due to a poor reporting of the strategy for adjusting hyperparameters, coefficients, and the explainability of the models. International collaboration was anecdotal (n=17) and data and developed models mostly remained private (n=126).

CONCLUSIONS

These significant shortcomings, alongside the lack of information to ensure reproducibility and transparency, are indicative of the challenges that AI in mental health needs to face before contributing to a solid base for knowledge generation and for being a support tool in mental health management.

Compressed sensorimotor-to-transmodal hierarchical organization in schizophrenia

BACKGROUND

Schizophrenia has been primarily conceptualized as a disorder of high-order cognitive functions with deficits in executive brain regions. Yet due to the increasing reports of early sensory processing deficit, recent models focus more on the developmental effects of impaired sensory process on high-order functions. The present study examined whether this pathological interaction relates to an overarching system-level imbalance, specifically a disruption in macroscale hierarchy affecting integration and segregation of unimodal and transmodal networks.

METHODS

We applied a novel combination of connectome gradient and stepwise connectivity analysis to resting-state fMRI to characterize the sensorimotor-to-transmodal cortical hierarchy organization (96 patients v. 122 controls).

RESULTS

We demonstrated compression of the cortical hierarchy organization in schizophrenia, with a prominent compression from the sensorimotor region and a less prominent compression from the frontal-parietal region, resulting in a diminished separation between sensory and fronto-parietal cognitive systems. Further analyses suggested reduced differentiation related to atypical functional connectome transition from unimodal to transmodal brain areas. Specifically, we found hypo-connectivity within unimodal regions and hyper-connectivity between unimodal regions and fronto-parietal and ventral attention regions along the classical sensation-to-cognition continuum (voxel-level corrected, p < 0.05).

CONCLUSIONS

The compression of cortical hierarchy organization represents a novel and integrative system-level substrate underlying the pathological interaction of early sensory and cognitive function in schizophrenia. This abnormal cortical hierarchy organization suggests cascading impairments from the disruption of the somatosensory-motor system and inefficient integration of bottom-up sensory information with attentional demands and executive control processes partially account for high-level cognitive deficits characteristic of schizophrenia.

Default mode network dynamic functional network connectivity predicts psychotic symptom severity

Neuropsychiatric disorders affect millions of people worldwide every year. Recent studies showed that the symptomatic overlaps across neuropsychiatric disorders mislead schizophrenia and bipolar disorder diagnosis. Additionally, recent studies claimed that schizoaffective disorder as a condition overlapped with both schizophrenia and bipolar disorder. Since symptomatic overlap among these disorders causes misdiagnosis, a need for neuroimaging biomarkers differentiating these disorders for a more accurate diagnosis is crucial. This study investigates dynamics functional network connectivity (dFNC) in the default mode network (DMN) of schizophrenia, bipolar, and schizoaffective disorder patients and compares them with their relative and healthy control. Additionally, it explored whether DMN dFNC features can predict the symptom severity of these neuropsychiatric disorders. Here, we found that dFNC features can differentiate schizophrenia from bipolar disorder. At the same time, we did not see a significant difference between schizoaffective with other conditions. Additionally, we found dFNC features can predict symptom severity of these three conditions.

Multimodal data fusion of cortical-subcortical morphology and functional network connectivity in psychotic spectrum disorder

•

Overlap has been noted disorders which fall on the psychotic spectrum.

•

Univariate studies may miss joint brain features across diagnostic categories.

•

mCCA with jICA is paired with features across the psychotic spectrum to produce joint components.

•

One joint component displayed a significant relationship with cognitive scores.

•

The replicate trends of cortical-subcortical irregularity in psychotic spectrum disorders.

Multiple authors have noted overlapping symptoms and alterations across clinical, anatomical, and functional brain features in schizophrenia (SZ), schizoaffective disorder (SZA), and bipolar disorder (BPI). However, regarding brain features, few studies have approached this line of inquiry using analytical techniques optimally designed to extract the shared features across anatomical and functional information in a simultaneous manner. Univariate studies of anatomical or functional alterations across these disorders can be limited and run the risk of omitting small but potentially crucial overlapping or joint neuroanatomical (e.g., structural images) and functional features (e.g., fMRI-based features) which may serve as informative clinical indicators of across multiple diagnostic categories. To address this limitation, we paired an unsupervised multimodal canonical correlation analysis (mCCA) together with joint independent component analysis (jICA) to identify linked spatial gray matter (GM), resting-state functional network connectivity (FNC), and white matter fractional anisotropy (FA) features across these diagnostic categories. We then calculated associations between the identified linked features and trans-diagnostic behavioral measures (MATRICs Consensus Cognitive Battery, MCCB).

Component number 4 of the 13 identified displayed a statistically significant relationship with overall MCCB scores across GM, resting-state FNC, and FA. These linked modalities of component 4 consisted primarily of positive correlations within subcortical structures including the caudate and putamen in the GM maps with overall MCCB, sparse negative correlations within subcortical and cortical connection tracts (e.g., corticospinal tract, superior longitudinal fasciculus) in the FA maps with overall MCCB, and negative relationships with MCCB values and loading parameters with FNC matrices displaying increased FNC in subcortical-cortical regions with auditory, somatomotor, and visual regions.

An attention-based hybrid deep learning framework integrating brain connectivity and activity of resting-state functional MRI data

Functional magnetic resonance imaging (fMRI) as a promising tool to investigate psychotic disorders can be decomposed into useful imaging features such as time courses (TCs) of independent components (ICs) and functional network connectivity (FNC) calculated by TC cross-correlation. TCs reflect the temporal dynamics of brain activity and the FNC characterizes temporal coherence across intrinsic brain networks. Both features have been used as input to deep learning approaches with decent results. However, few studies have tried to leverage their complementary information to learn optimal representations at multiple facets. Motivated by this, we proposed a Hybrid Deep Learning Framework integrating brain Connectivity and Activity (HDLFCA) together by combining convolutional recurrent neural network (C-RNN) and deep neural network (DNN), aiming to improve classification accuracy and interpretability simultaneously. Specifically, C-RNNAM was proposed to extract temporal dynamic dependencies with an attention module (AM) to automatically learn discriminative knowledge from TC nodes, while DNN was applied to identify the most group-discriminative FNC patterns with layer-wise relevance propagation (LRP). Then, both prediction outputs were concatenated to build a new feature matrix, generating the final decision by logistic regression. The effectiveness of HDLFCA was validated on both multi-site schizophrenia (SZ, n ∼ 1100) and public autism datasets (ABIDE, n ∼ 1522) by outperforming 12 alternative models at 2.8-8.9% accuracy, including 8 models using either static FNC or TCs and 4 models using dynamic FNC. Appreciable classification accuracy was achieved for HC vs. SZ (85.3%) and HC vs. Autism (72.4%) respectively. More importantly, the most group-discriminative brain regions can be easily attributed and visualized, providing meaningful biological interpretability and highlighting the great potential of the proposed HDLFCA model in the identification of valid neuroimaging biomarkers.

Path Analysis: A Method to Estimate Altered Pathways in Time-varying Graphs of Neuroimaging Data

Graph-theoretical methods have been widely used to study human brain networks in psychiatric disorders. However, the focus has primarily been on global graphic metrics with little attention to the information contained in paths connecting brain regions. Details of disruption of these paths may be highly informative for understanding disease mechanisms. To detect the absence or addition of multistep paths in the patient group, we provide an algorithm estimating edges that contribute to these paths with reference to the control group. We next examine where pairs of nodes were connected through paths in both groups by using a covariance decomposition method. We apply our method to study resting-state fMRI data in schizophrenia versus controls. Results show several disconnectors in schizophrenia within and between functional domains, particularly within the default mode and cognitive control networks. Additionally, we identify new edges generating additional paths. Moreover, although paths exist in both groups, these paths take unique trajectories and have a significant contribution to the decomposition. The proposed path analysis provides a way to characterize individuals by evaluating changes in paths, rather than just focusing on the pairwise relationships. Our results show promise for identifying path-based metrics in neuroimaging data.

Functional cortical associations and their intraclass correlations and heritability as revealed by the fMRI Human Connectome Project

We report on the functional connectivity (FC), its intraclass correlation (ICC), and heritability among 70 areas of the human cerebral cortex. FC was estimated as the Pearson correlation between averaged prewhitened Blood Oxygenation Level-Dependent time series of cortical areas in 988 young adult participants in the Human Connectome Project. Pairs of areas were assigned to three groups, namely homotopic (same area in the two hemispheres), ipsilateral (both areas in the same hemisphere), and heterotopic (nonhomotopic areas in different hemispheres). ICC for each pair of areas was computed for six genetic groups, namely monozygotic (MZ) twins, dizygotic (DZ) twins, singleton siblings of MZ twins (MZsb), singleton siblings of DZ twins (DZsb), non-twin siblings (SB), and unrelated individuals (UNR). With respect to FC, we found the following. (a) Homotopic FC was stronger than ipsilateral and heterotopic FC; (b) average FCs of left and right cortical areas were highly and positively correlated; and (c) FC varied in a systematic fashion along the anterior-posterior and inferior-superior dimensions, such that it increased from anterior to posterior and from inferior to superior. With respect to ICC, we found the following. (a) Homotopic ICC was significantly higher than ipsilateral and heterotopic ICC, but the latter two did not differ significantly from each other; (b) ICC was highest for MZ twins; (c) ICC of DZ twins was significantly lower than that of the MZ twins and higher than that of the three sibling groups (MZsb, DZsb, SB); and (d) ICC was close to zero for UNR. Finally, with respect to heritability, it was highest for homotopic areas, followed by ipsilateral, and heterotopic; however, it did not differ statistically significantly from each other.

Discriminative Analysis of Schizophrenia Patients Using Topological Properties of Structural and Functional Brain Networks: A Multimodal Magnetic Resonance Imaging Study

Interest in the application of machine learning (ML) techniques to multimodal magnetic resonance imaging (MRI) data for the diagnosis of schizophrenia (SZ) at the individual level is growing. However, a few studies have applied the features of structural and functional brain networks derived from multimodal MRI data to the discriminative analysis of SZ patients at different clinical stages. In this study, 205 normal controls (NCs), 61 first-episode drug-naive SZ (FESZ) patients, and 79 chronic SZ (CSZ) patients were recruited. We acquired their structural MRI, diffusion tensor imaging, and resting-state functional MRI data and constructed brain networks for each participant, including the gray matter network (GMN), white matter network (WMN), and functional brain network (FBN). We then calculated 3 nodal properties for each brain network, including degree centrality, nodal efficiency, and betweenness centrality. Two classifications (SZ vs. NC and FESZ vs. CSZ) were performed using five ML algorithms. We found that the SVM classifier with the input features of the combination of nodal properties of both the GMN and FBN achieved the best performance to discriminate SZ patients from NCs [accuracy, 81.2%; area under the receiver operating characteristic curve (AUC), 85.2%; p &lt; 0.05]. Moreover, the SVM classifier with the input features of the combination of the nodal properties of both the GMN and WMN achieved the best performance to discriminate FESZ from CSZ patients (accuracy, 86.2%; AUC, 92.3%; p &lt; 0.05). Furthermore, the brain areas in the subcortical/cerebellum network and the frontoparietal network showed significant importance in both classifications. Together, our findings provide new insights to understand the neuropathology of SZ and further highlight the potential advantages of multimodal network properties for identifying SZ patients at different clinical stages.

Searching for Imaging Biomarkers of Psychotic Dysconnectivity

BACKGROUND

Progress in precision psychiatry is predicated on identifying reliable individual-level diagnostic biomarkers. For psychosis, measures of structural and functional connectivity could be promising biomarkers given consistent reports of dysconnectivity across psychotic disorders using magnetic resonance imaging.

METHODS

We leveraged data from four independent cohorts of patients with psychosis and control subjects with observations from approximately 800 individuals. We used group-level analyses and two supervised machine learning algorithms (support vector machines and ridge regression) to test within-, between-, and across-sample classification performance of white matter and resting-state connectivity metrics.

RESULTS

Although we replicated group-level differences in brain connectivity, individual-level classification was suboptimal. Classification performance within samples was variable across folds (highest area under the curve [AUC] range = 0.30) and across datasets (average support vector machine AUC range = 0.50; average ridge regression AUC range = 0.18). Classification performance between samples was similarly variable or resulted in AUC values of approximately 0.65, indicating a lack of model generalizability. Furthermore, collapsing across samples (resting-state functional magnetic resonance imaging, N = 888; diffusion tensor imaging, N = 860) did not improve model performance (maximal AUC = 0.67). Ridge regression models generally outperformed support vector machine models, although classification performance was still suboptimal in terms of clinical relevance. Adjusting for demographic covariates did not greatly affect results.

CONCLUSIONS

Connectivity measures were not suitable as diagnostic biomarkers for psychosis as assessed in this study. Our results do not negate that other approaches may be more successful, although it is clear that a systematic approach to individual-level classification with large independent validation samples is necessary to properly vet neuroimaging features as diagnostic biomarkers.

Reduced intrinsic neural timescales in schizophrenia along posterior parietal and occipital areas

We computed intrinsic neural timescales (INT) based on resting-state functional magnetic resonance imaging (rsfMRI) data of healthy controls (HC) and patients with schizophrenia spectrum disorder (SZ) from three independently collected samples. Five clusters showed decreased INT in SZ compared to HC in all three samples: right occipital fusiform gyrus (rOFG), left superior occipital gyrus (lSOG), right superior occipital gyrus (rSOG), left lateral occipital cortex (lLOC) and right postcentral gyrus (rPG). In other words, it appears that sensory information in visual and posterior parietal areas is stored for reduced lengths of time in SZ compared to HC. Finally, we found that symptom severity appears to modulate INT of these areas in SZ.

Aberrant default mode connectivity in adolescents with early-onset psychosis: A resting state fMRI study

Abnormal default mode network (DMN) connectivity has been found in schizophrenia and other psychotic disorders. However, there are limited studies on early onset psychosis (EOP), and their results show lack of agreement. Here, we investigated within-network DMN connectivity in EOP compared to healthy controls (HC), and its relationship to clinical characteristics. A sample of 68 adolescent patients with EOP (mean age 16.53 ± 1.12 [SD] years, females 66%) and 95 HC (mean age 16.24 ± 1.50 [SD], females 60%) from two Scandinavian cohorts underwent resting state functional magnetic resonance imaging (rsfMRI). A group independent component analysis (ICA) was performed to identify the DMN across all participants. Dual regression was used to estimate spatial maps reflecting each participant's DMN network, which were compared between EOP and HC using voxel-wise general linear models and permutation-based analyses. Subgroup analyses were performed within the patient group, to explore associations between diagnostic subcategories and current use of psychotropic medication in relation to connectivity strength. The analysis revealed significantly reduced DMN connectivity in EOP compared to HC in the posterior cingulate cortex, precuneus, fusiform cortex, putamen, pallidum, amygdala, and insula. The subgroup analysis in the EOP group showed strongest deviations for affective psychosis, followed by other psychotic disorders and schizophrenia. There was no association between DMN connectivity strength and the current use of psychotropic medication. In conclusion, the findings demonstrate weaker DMN connectivity in adolescent patients with EOP compared to healthy peers, and differential effects across diagnostic subcategories, which may inform our understanding of underlying disease mechanisms in EOP.

The foundations of the working alliance in assertive community treatment teams

BACKGROUND

In this study, we aimed to identify and define the fundamental components of the working alliance in multidisciplinary (Flexible) Assertive Community Treatment teams with shared caseloads, in order to support their daily practice and further research.

METHODS

After reviewing the literature, concept mapping with professionals and clients was used to define the working alliance in (F) ACT teams. The resulting concept maps formed the basis for the working alliance assessment instrument, which was pilot tested with professionals and clients through cognitive interviews with a think-aloud procedure.

RESULTS

The study led to the development of a twenty five-item assessment instrument to evaluate working alliances in multidisciplinary teams (WAM) that was comprised of three subscales: bond, task/goal and team. Two different versions were developed for clients and professionals.

CONCLUSIONS

The WAM instrument was developed to determine the quality of the working alliance in (F) ACT teams. Future research will focus on testing its psychometric properties and predictive value.

Computing schizophrenia: ethical challenges for machine learning in psychiatry

Recent advances in machine learning (ML) promise far-reaching improvements across medical care, not least within psychiatry. While to date no psychiatric application of ML constitutes standard clinical practice, it seems crucial to get ahead of these developments and address their ethical challenges early on. Following a short general introduction concerning ML in psychiatry, we do so by focusing on schizophrenia as a paradigmatic case. Based on recent research employing ML to further the diagnosis, treatment, and prediction of schizophrenia, we discuss three hypothetical case studies of ML applications with view to their ethical dimensions. Throughout this discussion, we follow the principlist framework by Tom Beauchamp and James Childress to analyse potential problems in detail. In particular, we structure our analysis around their principles of beneficence, non-maleficence, respect for autonomy, and justice. We conclude with a call for cautious optimism concerning the implementation of ML in psychiatry if close attention is paid to the particular intricacies of psychiatric disorders and its success evaluated based on tangible clinical benefit for patients.

Thalamus Radiomics-Based Disease Identification and Prediction of Early Treatment Response for Schizophrenia

Background

Emerging evidence suggests structural and functional disruptions of the thalamus in schizophrenia, but whether thalamus abnormalities are able to be used for disease identification and prediction of early treatment response in schizophrenia remains to be determined. This study aims at developing and validating a method of disease identification and prediction of treatment response by multi-dimensional thalamic features derived from magnetic resonance imaging in schizophrenia patients using radiomics approaches.

Methods

A total of 390 subjects, including patients with schizophrenia and healthy controls, participated in this study, among which 109 out of 191 patients had clinical characteristics of early outcome (61 responders and 48 non-responders). Thalamus-based radiomics features were extracted and selected. The diagnostic and predictive capacity of multi-dimensional thalamic features was evaluated using radiomics approach.

Results

Using radiomics features, the classifier accurately discriminated patients from healthy controls, with an accuracy of 68%. The features were further confirmed in prediction and random forest of treatment response, with an accuracy of 75%.

Conclusion

Our study demonstrates a radiomics approach by multiple thalamic features to identify schizophrenia and predict early treatment response. Thalamus-based classification could be promising to apply in schizophrenia definition and treatment selection.

Machine Learning of Schizophrenia Detection with Structural and Functional Neuroimaging

Schizophrenia (SZ) is a severe psychiatric illness, and it affects around 1% of the general population; however, its reliable diagnosis is challenging. Functional MRI (fMRI) and structural MRI (sMRI) are useful techniques for investigating the functional and structural abnormalities of the human brain, and a growing number of studies have reported that multimodal brain data can improve diagnostic accuracy. Machine learning (ML) is widely used in the diagnosis of neuroscience and neuropsychiatry diseases, and it can obtain high accuracy. However, the conventional ML which concatenated the features into a longer feature vector could not be sufficiently effective to combine different features from different modalities. There are considerable controversies over the use of global signal regression (GSR), and few studies have explored the role of GSR in ML in diagnosing neurological diseases. The current study utilized fMRI and sMRI data to implement a new method named multimodal imaging and multilevel characterization with multiclassifier (M3) to classify SZs and healthy controls (HCs) and investigate the influence of GSR in SZ classification. We found that when we used Brainnetome 246 atlas and without performed GSR, our method obtained a classification accuracy of 83.49%, with a sensitivity of 68.69%, a specificity of 93.75%, and an AUC of 0.8491, respectively. We also got great classification performances with different processing methods (with/without GSR and different brain parcellation schemes). We found that the accuracy and specificity of the models without GSR were higher than that of the models with GSR. Our findings indicate that the M3 method is an effective tool to distinguish SZs from HCs, and it can identify discriminative regions to detect SZ to explore the neural mechanisms underlying SZ. The global signal may contain important neuronal information; it can improve the accuracy and specificity of SZ detection.

Schizophrenia: A Survey of Artificial Intelligence Techniques Applied to Detection and Classification

Artificial Intelligence in healthcare employs machine learning algorithms to emulate human cognition in the analysis of complicated or large sets of data. Specifically, artificial intelligence taps on the ability of computer algorithms and software with allowable thresholds to make deterministic approximate conclusions. In comparison to traditional technologies in healthcare, artificial intelligence enhances the process of data analysis without the need for human input, producing nearly equally reliable, well defined output. Schizophrenia is a chronic mental health condition that affects millions worldwide, with impairment in thinking and behaviour that may be significantly disabling to daily living. Multiple artificial intelligence and machine learning algorithms have been utilized to analyze the different components of schizophrenia, such as in prediction of disease, and assessment of current prevention methods. These are carried out in hope of assisting with diagnosis and provision of viable options for individuals affected. In this paper, we review the progress of the use of artificial intelligence in schizophrenia.

Aberrant Dynamic Functional Connectivity of Default Mode Network in Schizophrenia and Links to Symptom Severity

Background: Schizophrenia affects around 1% of the global population. Functional connectivity extracted from resting-state functional magnetic resonance imaging (rs-fMRI) has previously been used to study schizophrenia and has great potential to provide novel insights into the disorder. Some studies have shown abnormal functional connectivity in the default mode network (DMN) of individuals with schizophrenia, and more recent studies have shown abnormal dynamic functional connectivity (dFC) in individuals with schizophrenia. However, DMN dFC and the link between abnormal DMN dFC and symptom severity have not been well-characterized. Method: Resting-state fMRI data from subjects with schizophrenia (SZ) and healthy controls (HC) across two datasets were analyzed independently. We captured seven maximally independent subnodes in the DMN by applying group independent component analysis and estimated dFC between subnode time courses using a sliding window approach. A clustering method separated the dFCs into five reoccurring brain states. A feature selection method modeled the difference between SZs and HCs using the state-specific FC features. Finally, we used the transition probability of a hidden Markov model to characterize the link between symptom severity and dFC in SZ subjects. Results: We found decreases in the connectivity of the anterior cingulate cortex (ACC) and increases in the connectivity between the precuneus (PCu) and the posterior cingulate cortex (PCC) (i.e., PCu/PCC) of SZ subjects. In SZ, the transition probability from a state with weaker PCu/PCC and stronger ACC connectivity to a state with stronger PCu/PCC and weaker ACC connectivity increased with symptom severity. Conclusions: To our knowledge, this was the first study to investigate DMN dFC and its link to schizophrenia symptom severity. We identified reproducible neural states in a data-driven manner and demonstrated that the strength of connectivity within those states differed between SZs and HCs. Additionally, we identified a relationship between SZ symptom severity and the dynamics of DMN functional connectivity. We validated our results across two datasets. These results support the potential of dFC for use as a biomarker of schizophrenia and shed new light upon the relationship between schizophrenia and DMN dynamics.

Sparse deep neural networks on imaging genetics for schizophrenia case-control classification

Deep learning methods hold strong promise for identifying biomarkers for clinical application. However, current approaches for psychiatric classification or prediction do not allow direct interpretation of original features. In the present study, we introduce a sparse deep neural network (DNN) approach to identify sparse and interpretable features for schizophrenia (SZ) case–control classification. An L₀‐norm regularization is implemented on the input layer of the network for sparse feature selection, which can later be interpreted based on importance weights. We applied the proposed approach on a large multi‐study cohort with gray matter volume (GMV) and single nucleotide polymorphism (SNP) data for SZ classification. A total of 634 individuals served as training samples, and the classification model was evaluated for generalizability on three independent datasets of different scanning protocols (N = 394, 255, and 160, respectively). We examined the classification power of pure GMV features, as well as combined GMV and SNP features. Empirical experiments demonstrated that sparse DNN slightly outperformed independent component analysis + support vector machine (ICA + SVM) framework, and more effectively fused GMV and SNP features for SZ discrimination, with an average error rate of 28.98% on external data. The importance weights suggested that the DNN model prioritized to select frontal and superior temporal gyrus for SZ classification with high sparsity, with parietal regions further included with lower sparsity, echoing previous literature. The results validate the application of the proposed approach to SZ classification, and promise extended utility on other data modalities and traits which ultimately may result in clinically useful tools.

Temporoparietal Connectivity Within Default Mode Network Associates With Clinical Improvements in Schizophrenia Following Modified Electroconvulsive Therapy

Although modified electroconvulsive therapy (ECT) has been reported to be effective for the treatment of schizophrenia (SCZ), its action mechanism is unclear. To elucidate the underlying ECT mechanisms of SCZ, this study used a longitudinal cohort including 21 SCZ patients receiving only antipsychotics (DSZ group) and 21 SCZ patients receiving a regular course of ECT combining with antipsychotics (MSZ group) for 4 weeks. All patients underwent magnetic resonance imaging (MRI) scans at baseline (t1) and follow-up (t2) time points. A matched healthy control (HC) group included 23 individuals who were only scanned at baseline. Functional connectivity (FC) within the default mode network (DMN) was evaluated before and after ECT. Significant interaction of the group over time was found in FC between angular gyrus (AG) and middle temporal gyrus (MTG). Post-hoc analysis showed a significantly enhanced FC of left AG(AG.L) and right MTG (MTG.R) in the MSZ group relative to the DSZ group. In addition, the right AG (AG.R) showed significantly enhanced FC between MTG.R and left MTG (MTG.L) after ECT in the MSZ group, but no in the DSZ group. In particular, the FCs change in AG.L-MTG.R and AG.R-MTG.R were positively correlated with the Positive and Negative Syndrome Scale (PANSS) negative score reduction. Furthermore, the FC change in AG.L-MTG.R was also positively correlated with the PANSS general psychopathology score reduction. These findings confirmed a potential relationship between ECT inducing hyperconnectivity within DMN and improvements in symptomatology of SCZ, suggesting that ECT controls mental symptoms by regulating the temporoparietal connectivity within DMN.

Cost-effectiveness of neuroimaging technologies in management of psychiatric and insomnia disorders: A meta-analysis and prospective cost analysis

BACKGROUND

The optimal diagnostic strategy for patients with psychiatric and insomnia disorders has not been established yet.

PURPOSE

The purpose of this study was to perform cost-effectiveness analysis of six neuroimaging technologies in diagnosis of patients with psychiatric and insomnia disorders.

METHODS

An economic evaluation study was conducted in three parts, including a systematic review for determining diagnostic accuracy, a descriptive cross-sectional study with Activity-Based Costing (ABC) technique for tracing resource consumption, and a cost-effectiveness analysis using a short-term decision-analytic model.

RESULTS

In the first phase, 93 diagnostic accuracy studies were included in the systematic review. The accumulated results (meta-analysis) showed that the highest diagnostic accuracy for psychiatric and insomnia disorders was attributed to PET (sensitivity of 90% and specificity of 80%) and MRI (sensitivity of 76% and specificity of 78%) respectively. In the second phase of the study, we calculated the cost of each technology. The results showed that MRI has the lowest cost. Based on the results in the model of cost-effectiveness sMRI ($ 50.08 per accurate diagnosis) and MRI ($ 58.54 per accurate diagnosis) were more cost-effective neuroimaging technologies.

CONCLUSION

In psychiatric disorders, no single strategy was characterized by both low cost and high accuracy. However, MRI and PET scan had lower cost and higher accuracy for psychiatric disorders, respectively. MRI was the least costly with the highest diagnostic accuracy in insomnia disorders. Based on our model, sMRI in psychiatric disorders and MRI in insomnia disorders were the most cost-effective technologies.

Disrupted Intersubject Variability Architecture in Functional Connectomes in Schizophrenia

Schizophrenia (SCZ) is a highly heterogeneous disorder with remarkable intersubject variability in clinical presentations. Previous neuroimaging studies in SCZ have primarily focused on identifying group-averaged differences in the brain connectome between patients and healthy controls (HCs), largely neglecting the intersubject differences among patients. We acquired whole-brain resting-state functional MRI data from 121 SCZ patients and 183 HCs and examined the intersubject variability of the functional connectome (IVFC) in SCZ patients and HCs. Between-group differences were determined using permutation analysis. Then, we evaluated the relationship between IVFC and clinical variables in SCZ. Finally, we used datasets of patients with bipolar disorder (BD) and major depressive disorder (MDD) to assess the specificity of IVFC alteration in SCZ. The whole-brain IVFC pattern in the SCZ group was generally similar to that in HCs. Compared with the HC group, the SCZ group exhibited higher IVFC in the bilateral sensorimotor, visual, auditory, and subcortical regions. Moreover, altered IVFC was negatively correlated with age of onset, illness duration, and Brief Psychiatric Rating Scale scores and positively correlated with clinical heterogeneity. Although the SCZ shared altered IVFC in the visual cortex with BD and MDD, the alterations of IVFC in the sensorimotor, auditory, and subcortical cortices were specific to SCZ. The alterations of whole-brain IVFC in SCZ have potential implications for the understanding of the high clinical heterogeneity of SCZ and the future individualized clinical diagnosis and treatment of this disease.

A Deep Network Model on Dynamic Functional Connectivity With Applications to Gender Classification and Intelligence Prediction

Increasing evidence has suggested that the dynamic properties of functional brain networks are related to individual behaviors and cognition traits. However, current fMRI-based approaches mostly focus on statistical characteristics of the windowed correlation time course, potentially overlooking subtle time-varying patterns in dynamic functional connectivity (dFC). Here, we proposed the use of an end-to-end deep learning model that combines the convolutional neural network (CNN) and long short-term memory (LSTM) network to capture temporal and spatial features of functional connectivity sequences simultaneously. The results on a large cohort (Human Connectome Project, n = 1,050) demonstrated that our model could achieve a high classification accuracy of about 93% in a gender classification task and prediction accuracies of 0.31 and 0.49 (Pearson's correlation coefficient) in fluid and crystallized intelligence prediction tasks, significantly outperforming previously reported models. Furthermore, we demonstrated that our model could effectively learn spatiotemporal dynamics underlying dFC with high statistical significance based on the null hypothesis estimated using surrogate data. Overall, this study suggests the advantages of a deep learning model in making full use of dynamic information in resting-state functional connectivity, and highlights the potential of time-varying connectivity patterns in improving the prediction of individualized characterization of demographics and cognition traits.

Grab-AD: Generalizability and reproducibility of altered brain activity and diagnostic classification in Alzheimer's Disease

Alzheimer's disease (AD) is associated with disruptions in brain activity and networks. However, there is substantial inconsistency among studies that have investigated functional brain alterations in AD; such contradictions have hindered efforts to elucidate the core disease mechanisms. In this study, we aim to comprehensively characterize AD-associated functional brain alterations using one of the world's largest resting-state functional MRI (fMRI) biobank for the disorder. The biobank includes fMRI data from six neuroimaging centers, with a total of 252 AD patients, 221 mild cognitive impairment (MCI) patients and 215 healthy comparison individuals. Meta-analytic techniques were used to unveil reliable differences in brain function among the three groups. Relative to the healthy comparison group, AD was associated with significantly reduced functional connectivity and local activity in the default-mode network, basal ganglia and cingulate gyrus, along with increased connectivity or local activity in the prefrontal lobe and hippocampus (p < .05, Bonferroni corrected). Moreover, these functional alterations were significantly correlated with the degree of cognitive impairment (AD and MCI groups) and amyloid-β burden. Machine learning models were trained to recognize key fMRI features to predict individual diagnostic status and clinical score. Leave-one-site-out cross-validation established that diagnostic status (mean area under the receiver operating characteristic curve: 0.85) and clinical score (mean correlation coefficient between predicted and actual Mini-Mental State Examination scores: 0.56, p < .0001) could be predicted with high accuracy. Collectively, our findings highlight the potential for a reproducible and generalizable functional brain imaging biomarker to aid the early diagnosis of AD and track its progression.

Detecting schizophrenia at the level of the individual: relative diagnostic value of whole-brain images, connectome-wide functional connectivity and graph-based metrics

BACKGROUND

Previous studies using resting-state functional neuroimaging have revealed alterations in whole-brain images, connectome-wide functional connectivity and graph-based metrics in groups of patients with schizophrenia relative to groups of healthy controls. However, it is unclear which of these measures best captures the neural correlates of this disorder at the level of the individual patient.

METHODS

Here we investigated the relative diagnostic value of these measures. A total of 295 patients with schizophrenia and 452 healthy controls were investigated using resting-state functional Magnetic Resonance Imaging at five research centres. Connectome-wide functional networks were constructed by thresholding correlation matrices of 90 brain regions, and their topological properties were analyzed using graph theory-based methods. Single-subject classification was performed using three machine learning (ML) approaches associated with varying degrees of complexity and abstraction, namely logistic regression, support vector machine and deep learning technology.

RESULTS

Connectome-wide functional connectivity allowed single-subject classification of patients and controls with higher accuracy (average: 81%) than both whole-brain images (average: 53%) and graph-based metrics (average: 69%). Classification based on connectome-wide functional connectivity was driven by a distributed bilateral network including the thalamus and temporal regions.

CONCLUSION

These results were replicated across the three employed ML approaches. Connectome-wide functional connectivity permits differentiation of patients with schizophrenia from healthy controls at single-subject level with greater accuracy; this pattern of results is consistent with the 'dysconnectivity hypothesis' of schizophrenia, which states that the neural basis of the disorder is best understood in terms of system-level functional connectivity alterations.

Resting state auditory-language cortex connectivity is associated with hallucinations in clinical and biological subtypes of psychotic disorders

•

Transdiagnostic evidence for neural disruption in psychotic hallucinations.

•

Hallucinations associated increased connectivity in auditory association cortex.

•

Brain regions for auditory-verbal language comprehension linked to hallucinations.

•

Interhemispheric connectivity alterations related to subgroup-specific findings.

•

Hallucinations link to auditory rs-connectivity tested in 243 psychosis patients.

Background

Auditory hallucinations are prevalent across the major psychotic disorders, but their underlying mechanism is poorly understood. Limited prior work supports a hypothesis of altered auditory/language brain systems. To more definitively assess this, we examined whether alterations in resting state connectivity of auditory and language cortices are associated with hallucination severity in a large sample of individuals in the schizo-bipolar spectrum.

Methods

Whole brain resting state connectivity of auditory and language cortex (primary auditory cortex, unimodal auditory association cortex, Wernicke’s area [speech and heteromodal association cortex] and Broca’s area [speech production motor]) was evaluated for 243 subjects with schizophrenia, schizoaffective, or bipolar disorder with psychosis and 186 healthy controls from the Bipolar Schizophrenia Network on Intermediate Phenotypes (B-SNIP) study. Regression analyses were conducted to evaluate whether resting state connectivity of auditory and language cortex was a significant predictor of current overall hallucination severity (information about specific modality of hallucinations experienced was not available).

Results

Increased connectivity between lower and higher order regions of left temporal-parietal auditory/language processing cortex was associated with worse hallucination severity for all psychosis patients. Additionally, within bipolar subjects, increased interhemispheric connectivity between higher order temporal-parietal auditory/language regions was related to greater hallucination severity. When patients were categorized by B-SNIP biomarker-based Biotype groups, interhemispheric connectivity between left auditory association cortex and right core auditory cortex was related to greater hallucination severity for Biotype 1 patients. Exploratory analyses resulted in different patterns of connectivity of auditory/language cortex in patients and controls, unrelated to current hallucination severity.

Conclusions

Although the findings cannot be precisely attributed to auditory hallucination severity or possible differences in such experiences between groups, increased connectivity among the left hemisphere auditory and receptive language cortex may represent a significant factor contributing to hallucination severity across psychotic disorders, and additional subgroup specific connectivity alterations may also be present.

Transdiagnostic Dysfunctions in Brain Modules Across Patients with Schizophrenia, Bipolar Disorder, and Major Depressive Disorder: A Connectome-Based Study

Psychiatric disorders, including schizophrenia (SCZ), bipolar disorder (BD), and major depressive disorder (MDD), share clinical and neurobiological features. Because previous investigations of functional dysconnectivity have mainly focused on single disorders, the transdiagnostic alterations in the functional connectome architecture of the brain remain poorly understood. We collected resting-state functional magnetic resonance imaging data from 512 participants, including 121 with SCZ, 100 with BD, 108 with MDD, and 183 healthy controls. Individual functional brain connectomes were constructed in a voxelwise manner, and the modular architectures were examined at different scales, including (1) global modularity, (2) module-specific segregation and intra- and intermodular connections, and (3) nodal participation coefficients. The correlation of these modular measures with clinical scores was also examined. We reliably identify common alterations in modular organization in patients compared to controls, including (1) lower global modularity; (2) lower modular segregation in the frontoparietal, subcortical, visual, and sensorimotor modules driven by more intermodular connections; and (3) higher participation coefficients in several network connectors (the dorsolateral prefrontal cortex and angular gyrus) and the thalamus. Furthermore, the alterations in the SCZ group are more widespread than those of the BD and MDD groups and involve more intermodular connections, lower modular segregation and higher connector integrity. These alterations in modular organization significantly correlate with clinical scores in patients. This study demonstrates common hyper-integrated modular architectures of functional brain networks among patients with SCZ, BD, and MDD. These findings reveal a transdiagnostic mechanism of network dysfunction across psychiatric disorders from a connectomic perspective.

State-Dependent Functional Dysconnectivity in Youth With Psychosis Spectrum Symptoms

Psychosis spectrum disorders are conceptualized as neurodevelopmental disorders accompanied by disruption of large-scale functional brain networks. Dynamic functional dysconnectivity has been described in patients with schizophrenia and in help-seeking individuals at clinical high risk for psychosis. Less is known, about developmental aspects of dynamic functional network connectivity (dFNC) associated with psychotic symptoms (PS) in the general population. Here, we investigate resting state functional magnetic resonance imaging data using established dFNC methods in the Philadelphia Neurodevelopmental Cohort (ages 8-22 years), including 129 participants experiencing PS and 452 participants without PS (non-PS). Functional networks were identified using group spatial independent component analysis. A sliding window approach and k-means clustering were applied to covariance matrices of all functional networks to identify recurring whole-brain connectivity states. PS-associated dysconnectivity of default mode, salience, and executive networks occurred only in a few states, whereas dysconnectivity in the sensorimotor and visual systems in PS youth was more pervasive, observed across multiple states. This study provides new evidence that disruptions of dFNC are present even at the less severe end of the psychosis continuum in youth, complementing previous work on help-seeking and clinically diagnosed cohorts that represent the more severe end of this spectrum.

Generalizability of machine learning for classification of schizophrenia based on resting-state functional MRI data

Machine learning has increasingly been applied to classification of schizophrenia in neuroimaging research. However, direct replication studies and studies seeking to investigate generalizability are scarce. To address these issues, we assessed within-site and between-site generalizability of a machine learning classification framework which achieved excellent performance in a previous study using two independent resting-state functional magnetic resonance imaging data sets collected from different sites and scanners. We established within-site generalizability of the classification framework in the main data set using cross-validation. Then, we trained a model in the main data set and investigated between-site generalization in the validated data set using external validation. Finally, recognizing the poor between-site generalization performance, we updated the unsupervised algorithm to investigate if transfer learning using additional unlabeled data were able to improve between-site classification performance. Cross-validation showed that the published classification procedure achieved an accuracy of 0.73 using majority voting across all selected components. External validation found a classification accuracy of 0.55 (not significant) and 0.70 (significant) using the direct and transfer learning procedures, respectively. The failure of direct generalization from one site to another demonstrates the limitation of within-site cross-validation and points toward the need to incorporate efforts to facilitate application of machine learning across multiple data sets. The improvement in performance with transfer learning highlights the importance of taking into account the properties of data when constructing predictive models across samples and sites. Our findings suggest that machine learning classification result based on a single study should be interpreted cautiously.

Clinical Strategies and Technical Challenges in Psychoradiology

Psychoradiology is an emerging discipline at the intersection between radiology and psychiatry. It holds promise for playing a role in clinical diagnosis, evaluation of treatment response and prognosis, and illness risk prediction for patients with psychiatric disorders. Addressing complex issues, such as the biological heterogeneity of psychiatric syndromes and unclear neurobiological mechanisms underpinning radiological abnormalities, is a challenge that needs to be resolved. With the advance of multimodal imaging and more efforts in standardization of image acquisition and analysis, psychoradiology is becoming a promising tool for the future of clinical care for patients with psychiatric disorders.

Multivariate consistency of resting-state fMRI connectivity maps acquired on a single individual over 2.5 years, 13 sites and 3 vendors

Studies using resting-state functional magnetic resonance imaging (rsfMRI) are increasingly collecting data at multiple sites in order to speed up recruitment or increase sample size. The main objective of this study was to assess the long-term consistency of rsfMRI connectivity maps derived at multiple sites and vendors using the Canadian Dementia Imaging Protocol (CDIP, www.cdip-pcid.ca). Nine to 10 min of functional BOLD images were acquired from an adult cognitively healthy volunteer scanned repeatedly at 13 Canadian sites on three scanner makes (General Electric, Philips and Siemens) over the course of 2.5 years. The consistency (spatial Pearson's correlation) of rsfMRI connectivity maps for seven canonical networks ranged from 0.3 to 0.8, with a negligible effect of time, but significant site and vendor effects. We noted systematic differences in data quality (i.e. head motion, number of useable time frames, temporal signal-to-noise ratio) across vendors, which may also confound some of these results, and could not be disentangled in this sample. We also pooled the long-term longitudinal data with a single-site, short-term (1 month) data sample acquired on 26 subjects (10 scans per subject), called HNU1. Using randomly selected pairs of scans from each subject, we quantified the ability of a data-driven unsupervised cluster analysis to match two scans of the same subjects. In this "fingerprinting" experiment, we found that scans from the Canadian subject (Csub) could be matched with high accuracy intra-site (>95% for some networks), but that the accuracy decreased substantially for scans drawn from different sites and vendors, even falling outside of the range of accuracies observed in HNU1. Overall, our results demonstrate good multivariate stability of rsfMRI measures over several years, but substantial impact of scanning site and vendors. How detrimental these effects are will depend on the application, yet our results demonstrate that new methods for harmonizing multisite analysis represent an important area for future work.

N-Acetyl-Cysteine Supplementation Improves Functional Connectivity Within the Cingulate Cortex in Early Psychosis: A Pilot Study

BACKGROUND

There is increasing evidence that redox dysregulation, which can lead to oxidative stress and eventually to impairment of oligodendrocytes and parvalbumin interneurons, may underlie brain connectivity alterations in schizophrenia. Accordingly, we previously reported that levels of brain antioxidant glutathione in the medial prefrontal cortex were positively correlated with increased functional connectivity along the cingulum bundle in healthy controls but not in early psychosis patients. In a recent randomized controlled trial, we observed that 6-month supplementation with a glutathione precursor, N-acetyl-cysteine, increased brain glutathione levels and improved symptomatic expression and processing speed.

METHODS

We investigated the effect of N-acetyl-cysteine supplementation on the functional connectivity between regions of the cingulate cortex, which have been linked to positive symptoms and processing speed decline. In this pilot study, we compared structural connectivity and resting-state functional connectivity between early psychosis patients treated with 6-month N-acetyl-cysteine (n = 9) or placebo (n = 11) supplementation with sex- and age-matched healthy control subjects (n = 74).

RESULTS

We observed that 6-month N-acetyl-cysteine supplementation increases functional connectivity along the cingulum and more precisely between the caudal anterior part and the isthmus of the cingulate cortex. These functional changes can be partially explained by an increase of centrality of these regions in the functional brain network.

CONCLUSIONS

N-acetyl-cysteine supplementation has a positive effect on functional connectivity within the cingulate cortex in early psychosis patients. To our knowledge, this is the first study suggesting that increased brain glutathione levels via N-acetyl-cysteine supplementation may improve brain functional connectivity.

Group ICA for identifying biomarkers in schizophrenia: 'Adaptive' networks via spatially constrained ICA show more sensitivity to group differences than spatio-temporal regression

Brain functional networks identified from fMRI data can provide potential biomarkers for brain disorders. Group independent component analysis (GICA) is popular for extracting brain functional networks from multiple subjects. In GICA, different strategies exist for reconstructing subject-specific networks from the group-level networks. However, it is unknown whether these strategies have different sensitivities to group differences and abilities in distinguishing patients. Among GICA, spatio-temporal regression (STR) and spatially constrained ICA approaches such as group information guided ICA (GIG-ICA) can be used to propagate components (indicating networks) to a new subject that is not included in the original subjects. In this study, based on the same a priori network maps, we reconstructed subject-specific networks using these two methods separately from resting-state fMRI data of 151 schizophrenia patients (SZs) and 163 healthy controls (HCs). We investigated group differences in the estimated functional networks and the functional network connectivity (FNC) obtained by each method. The networks were also used as features in a cross-validated support vector machine (SVM) for classifying SZs and HCs. We selected features using different strategies to provide a comprehensive comparison between the two methods. GIG-ICA generally showed greater sensitivity in statistical analysis and better classification performance (accuracy 76.45 ± 8.9%, sensitivity 0.74 ± 0.11, specificity 0.79 ± 0.11) than STR (accuracy 67.45 ± 8.13%, sensitivity 0.65 ± 0.11, specificity 0.71 ± 0.11). Importantly, results were also consistent when applied to an independent dataset including 82 HCs and 82 SZs. Our work suggests that the functional networks estimated by GIG-ICA are more sensitive to group differences, and GIG-ICA is promising for identifying image-derived biomarkers of brain disease.

•

We investigate which group ICA method is more sensitive to group differences in networks and FNC.

•

We evaluate which group ICA method can result in better classification performance.

•

We compare the spatio-temporal regression (STR) and GIG-ICA using different feature selection and model building strategies and independent samples.

•

We use different feature selection and model building strategies and classification using independent samples.

•

Using fMRI data including schizophrenia patients, GIG-ICA shows better performance than the traditional STR method.

Reproducible grey matter patterns index a multivariate, global alteration of brain structure in schizophrenia and bipolar disorder

Schizophrenia is a severe mental disorder characterized by numerous subtle changes in brain structure and function. Machine learning allows exploring the utility of combining structural and functional brain magnetic resonance imaging (MRI) measures for diagnostic application, but this approach has been hampered by sample size limitations and lack of differential diagnostic data. Here, we performed a multi-site machine learning analysis to explore brain structural patterns of T1 MRI data in 2668 individuals with schizophrenia, bipolar disorder or attention-deficit/ hyperactivity disorder, and healthy controls. We found reproducible changes of structural parameters in schizophrenia that yielded a classification accuracy of up to 76% and provided discrimination from ADHD, through it lacked specificity against bipolar disorder. The observed changes largely indexed distributed grey matter alterations that could be represented through a combination of several global brain-structural parameters. This multi-site machine learning study identified a brain-structural signature that could reproducibly differentiate schizophrenia patients from controls, but lacked specificity against bipolar disorder. While this currently limits the clinical utility of the identified signature, the present study highlights that the underlying alterations index substantial global grey matter changes in psychotic disorders, reflecting the biological similarity of these conditions, and provide a roadmap for future exploration of brain structural alterations in psychiatric patients.

Development of Neuroimaging-Based Biomarkers in Psychiatry

This chapter presents an overview of accumulating neuroimaging data with emphasis on translational potential. The subject will be described in the context of three disease states, i.e., schizophrenia, bipolar disorder, and major depressive disorder, and for three clinical goals, i.e., disease risk assessment, subtyping, and treatment decision.

Within-Network Connectivity in the Salience Network After Attention Bias Modification Training in Residual Depression: Report From a Preregistered Clinical Trial

Alterations in resting state networks (RSNs) are associated with emotional- and attentional control difficulties in depressed individuals. Attentional bias modification (ABM) training may lead to more adaptive emotional processing in depression, but little is known about the neural underpinnings associated with ABM. In the current study a sample of 134 previously depressed individuals were randomized into 14 days of computerized ABM- or a closely matched placebo training regime followed by a resting state magnetic resonance imaging (MRI) scan. Using independent component analysis (ICA) we examined within-network connectivity in three major RSN's, the default mode network (DMN), the salience network (SN) and the central executive network (CEN) after 2 weeks of ABM training. We found a significant difference between the training groups within the SN, but no difference within the DMN or CEN. Moreover, a significant symptom improvement was observed in the ABM group after training. Clinical Trial Registration: www.ClinicalTrials.gov, identifier NCT02931487.

Classification and Prediction of Brain Disorders Using Functional Connectivity: Promising but Challenging

Brain functional imaging data, especially functional magnetic resonance imaging (fMRI) data, have been employed to reflect functional integration of the brain. Alteration in brain functional connectivity (FC) is expected to provide potential biomarkers for classifying or predicting brain disorders. In this paper, we present a comprehensive review in order to provide guidance about the available brain FC measures and typical classification strategies. We survey the state-of-the-art FC analysis methods including widely used static functional connectivity (SFC) and more recently proposed dynamic functional connectivity (DFC). Temporal correlations among regions of interest (ROIs), data-driven spatial network and functional network connectivity (FNC) are often computed to reflect SFC from different angles. SFC can be extended to DFC using a sliding-window framework, and intrinsic connectivity states along the time-varying connectivity patterns are typically extracted using clustering or decomposition approaches. We also briefly summarize window-less DFC approaches. Subsequently, we highlight various strategies for feature selection including the filter, wrapper and embedded methods. In terms of model building, we include traditional classifiers as well as more recently applied deep learning methods. Moreover, we review representative applications with remarkable classification accuracy for psychosis and mood disorders, neurodevelopmental disorder, and neurological disorders using fMRI data. Schizophrenia, bipolar disorder, autism spectrum disorder (ASD), attention deficit hyperactivity disorder (ADHD), Alzheimer's disease and mild cognitive impairment (MCI) are discussed. Finally, challenges in the field are pointed out with respect to the inaccurate diagnosis labeling, the abundant number of possible features and the difficulty in validation. Some suggestions for future work are also provided.

Disease Definition for Schizophrenia by Functional Connectivity Using Radiomics Strategy

Specific biomarker reflecting neurobiological substrates of schizophrenia (SZ) is required for its diagnosis and treatment selection of SZ. Evidence from neuroimaging has implicated disrupted functional connectivity in the pathophysiology. We aimed to develop and validate a method of disease definition for SZ by resting-state functional connectivity using radiomics strategy. This study included 2 data sets collected with different scanners. A total of 108 first-episode SZ patients and 121 healthy controls (HCs) participated in the current study, among which 80% patients and HCs (n = 183) and 20% (n = 46) were selected for training and testing in intra-data set validation and 1 of the 2 data sets was selected for training and the other for testing in inter-data set validation, respectively. Functional connectivity was calculated for both groups, features were selected by Least Absolute Shrinkage and Selection Operator (LASSO) method, and the clinical utility of its features and the generalizability of effects across samples were assessed using machine learning by training and validating multivariate classifiers in the independent samples. We found that the accuracy of intra-data set training was 87.09% for diagnosing SZ patients by applying functional connectivity features, with a validation in the independent replication data set (accuracy = 82.61%). The inter-data set validation further confirmed the disease definition by functional connectivity features (accuracy = 83.15% for training and 80.07% for testing). Our findings demonstrate a valid radiomics approach by functional connectivity to diagnose SZ, which is helpful to facilitate objective SZ individualized diagnosis using quantitative and specific functional connectivity biomarker.

Increased resting-state global functional connectivity density of default mode network in schizophrenia subjects treated with electroconvulsive therapy

Modified electroconvulsive therapy (MECT) has been widely applied to help treat schizophrenia patients who are treatment-resistant to pharmaceutical therapy. Although the technique is increasingly prevalent, the underlying neural mechanisms have not been well clarified. We conducted a longitudinal study to investigate the alteration of global functional connectivity density (gFCD) in schizophrenia patients undergoing MECT using resting state fMRI (functional magnetic resonance imaging). Two groups of schizophrenia inpatients were recruited. One group received a four-week MECT together with antipsychotic drugs (ECT+Drug, n=21); the other group only received antipsychotic drugs (Drug, n=21). Both groups were compared to a sample of healthy controls (HC, n=23). fMRI scans were obtained from the schizophrenia patients twice at baseline (t₁) and after 4-week treatment (t₂), and from healthy controls at baseline. gFCD was computed using resting state fMRI. Repeated ANCOVA showed a significant interaction effect of group×time in the schizophrenia patients in left precuneus (Pcu), ventral medial prefrontal cortex (vMPFC), and dorsal medial prefrontal cortex (dMPFC) (GRF-corrected P<0.05), which are mainly located within the default mode network (DMN). Post-hoc analysis revealed that compared with baseline (t₁), an increased gFCD was found in the ECT+Drug group in the dMPFC (t=3.87, p=0.00095), vMPFC (t=3.95, p=0.00079) and left Pcu (t=3.33, p=0.0034), but no significant effect was identified in the Drug group. The results suggested that increased global functional connectivity density within the DMN might be one important neural mechanism of MECT in schizophrenia.

Identifying first-episode drug naïve patients with schizophrenia with or without auditory verbal hallucinations using whole-brain functional connectivity: A pattern analysis study

Many studies have focused on patients with schizophrenia with or without auditory verbal hallucinations (AVHs), but due to the complexity of schizophrenia, biologically based diagnosis of patients with schizophrenia remains unsolved. The objectives of this study are to classify between first-episode drug-naïve patients with schizophrenia and healthy controls, and to classify between patients with and without AVHs. Resting state fMRI data from 41 patients with schizophrenia (22 with and 19 without AVHs) and 23 normal controls (NC) were included to compute functional connectivity between brain regions. Classifiers based on support vector machine (SVM) were developed to classify patients with schizophrenia from NC, as well as between the two subgroups of patients. The classification accuracy was evaluated with a leave-one-out cross-validation (LOOCV) strategy. The accuracy in discriminating both subgroups of patients from NC was 81.3%, with 92.0% (sensitivity) and 65.2% (specificity) for the patients and NC, respectively. The classification accuracy in discriminating patients with and without AVHs was 75.6%, with 77.3% (sensitivity) and 73.9% (specificity) for patients with and without AVHs, respectively. The results suggest that functional connectivity provided good discriminative power not only for identifying patients with schizophrenia among NC, but also in discriminating patients with schizophrenia with and without AVHs.

Multi-Site Diagnostic Classification of Schizophrenia Using Discriminant Deep Learning with Functional Connectivity MRI

BACKGROUND

A lack of a sufficiently large sample at single sites causes poor generalizability in automatic diagnosis classification of heterogeneous psychiatric disorders such as schizophrenia based on brain imaging scans. Advanced deep learning methods may be capable of learning subtle hidden patterns from high dimensional imaging data, overcome potential site-related variation, and achieve reproducible cross-site classification. However, deep learning-based cross-site transfer classification, despite less imaging site-specificity and more generalizability of diagnostic models, has not been investigated in schizophrenia.

METHODS

A large multi-site functional MRI sample (n = 734, including 357 schizophrenic patients from seven imaging resources) was collected, and a deep discriminant autoencoder network, aimed at learning imaging site-shared functional connectivity features, was developed to discriminate schizophrenic individuals from healthy controls.

FINDINGS

Accuracies of approximately 85·0% and 81·0% were obtained in multi-site pooling classification and leave-site-out transfer classification, respectively. The learned functional connectivity features revealed dysregulation of the cortical-striatal-cerebellar circuit in schizophrenia, and the most discriminating functional connections were primarily located within and across the default, salience, and control networks.

INTERPRETATION

The findings imply that dysfunctional integration of the cortical-striatal-cerebellar circuit across the default, salience, and control networks may play an important role in the "disconnectivity" model underlying the pathophysiology of schizophrenia. The proposed discriminant deep learning method may be capable of learning reliable connectome patterns and help in understanding the pathophysiology and achieving accurate prediction of schizophrenia across multiple independent imaging sites.

Translational Significance of Selective Estrogen Receptor Modulators in Psychiatric Disorders

Accumulating data from various clinical trial studies suggests that adjuvant therapy with ovarian hormones (estrogens) could be effective in reducing cognitive deficit and psychopathological symptoms in women with psychiatric disorders. However, estrogen therapy poses serious limitations and health issues including feminization in men and increased risks of thromboembolism, hot flashes, breast hyperplasia, and endometrium hyperplasia when used for longer duration in older women (aged ≥ 60 years) or in women who have genetic predispositions. On the other hand, selective estrogen receptor modulators (SERMs), which may (or may not) carry some risks of hot flashes, thromboembolism, breast hyperplasia, and endometrial hyperplasia, are generally devoid of feminization effect. In clinical trial studies, adjuvant therapy with tamoxifen, a triphenylethylene class of SERM, has been found to reduce the frequency of manic episodes in patients with bipolar disorder, whereas addition of raloxifene, a benzothiophene class of SERM, to regular doses of antipsychotic drugs has been found to reduce cognitive deficit and psychological symptoms in men and women with schizophrenia, including women with treatment refractory psychosis. These outcomes together with potent neurocognitive, neuroprotective, and cardiometabolic properties suggest that SERMs could be the potential targets for designing effective and safer therapies for psychiatric disorders.

Brain hubs in lesion models: Predicting functional network topology with lesion patterns in patients

Various important topological properties of healthy brain connectome have recently been identified. However, the manner in which brain lesion changes the functional network topology is unknown. We examined how critical specific brain areas are in the maintenance of network topology using multivariate support vector regression analysis on brain structural and resting-state functional imaging data in 96 patients with brain damages. Patients’ cortical lesion distribution patterns could significantly predict the functional network topology and a set of regions with significant weights in the prediction models were identified as “lesion hubs”. Intriguingly, we found two different types of lesion hubs, whose lesions associated with changes of network topology towards relatively different directions, being either more integrated (global) or more segregated (local), and correspond to hubs identified in healthy functional network in complex manners. Our results pose further important questions about the potential dynamics of the functional brain network after brain damage.