Using genetic, cognitive and multi-modal neuroimaging data to identify ultra-high-risk and first-episode psychosis at the individual level

Magnetic resonance imaging-based machine learning classification of schizophrenia spectrum disorders: a meta-analysis

BACKGROUND

Recent advances in multivariate pattern recognition have fostered the search for reliable neuroimaging-based biomarkers in psychiatric conditions, including schizophrenia. These approaches consider the complex pattern of alterations in brain function and structure, overcoming the limitations of traditional univariate methods. To assess the reliability of neuroimaging-based biomarkers and the contribution of study characteristics in distinguishing individuals with schizophrenia spectrum disorder (SSD) from healthy controls (HCs), we conducted a systematic review of the studies that used multivariate pattern recognition for this objective.

METHODS

We systematically searched PubMed, Scopus, and Web of Science for studies on SSD classification using multivariate pattern analysis on magnetic resonance imaging data. We employed a bivariate random-effects meta-analytic model to explore the classification of sensitivity (SE) and specificity (SP) across studies while also evaluating the moderator effects of clinical and non-clinical variables.

RESULTS

A total of 119 studies (with 12,723 patients with SSD and 13,196 HCs) were identified. The meta-analysis estimated a SE of 79.1% (95% confidence interval [CI], 77.1%-81.0%) and a SP of 80.0% (95% CI, 77.8%-82.0%). In particular, the Positive and Negative Syndrome Scale and the Global Assessment of Functioning scores, age, age of onset, duration of untreated psychosis, deep learning, algorithm type, features selection, and validation methods had significant effects on classification performance.

CONCLUSIONS

Multivariate pattern analysis reliably identifies neuroimaging-based biomarkers of SSD, achieving ∼80% SE and SP. Despite clinical heterogeneity, discernible brain modifications effectively differentiate SSD from HCs. Classification performance depends on patient-related and methodological factors crucial for the development, validation, and application of prospective models in clinical settings.

Statistical and Machine Learning Analysis in Brain-Imaging Genetics: A Review of Methods

Brain-imaging-genetic analysis is an emerging field of research that aims at aggregating data from neuroimaging modalities, which characterize brain structure or function, and genetic data, which capture the structure and function of the genome, to explain or predict normal (or abnormal) brain performance. Brain-imaging-genetic studies offer great potential for understanding complex brain-related diseases/disorders of genetic etiology. Still, a combined brain-wide genome-wide analysis is difficult to perform as typical datasets fuse multiple modalities, each with high dimensionality, unique correlational landscapes, and often low statistical signal-to-noise ratios. In this review, we outline the progress in brain-imaging-genetic methodologies starting from early massive univariate to current deep learning approaches, highlighting each approach's strengths and weaknesses and elongating it with the field's development. We conclude by discussing selected remaining challenges and prospects for the field.

A novel diagnosis method for schizophrenia based on globus pallidus data

This research aims to diagnose schizophrenia with machine learning-based algorithms. Bayesian neural network, logistic regression, decision tree, k-nearest neighbor, and gaussian kernel classification techniques are investigated to diagnose schizophrenia with data from 125 persons. This study showed that left lateral ventricles and left globus pallidus volumes and their percentages in the brain were significantly lower than HCs in FEP patients. Using brain volumes, we were able to diagnose FEP with an accuracy of 73.6 % via logistic regression and with an accuracy of 86.4 % using the SVM kernel classifier method. Therefore, brain volumes can be used to diagnose FEP with the SVM kernel classifier method.

Multivariate Associations Among White Matter, Neurocognition, and Social Cognition Across Individuals With Schizophrenia Spectrum Disorders and Healthy Controls

BACKGROUND AND HYPOTHESIS

Neurocognitive and social cognitive abilities are important contributors to functional outcomes in schizophrenia spectrum disorders (SSDs). An unanswered question of considerable interest is whether neurocognitive and social cognitive deficits arise from overlapping or distinct white matter impairment(s).

STUDY DESIGN

We sought to fill this gap, by harnessing a large sample of individuals from the multi-center Social Processes Initiative in the Neurobiology of the Schizophrenia(s) (SPINS) dataset, unique in its collection of advanced diffusion imaging and an extensive battery of cognitive assessments. We applied canonical correlation analysis to estimates of white matter microstructure, and cognitive performance, across people with and without an SSD.

STUDY RESULTS

Our results established that white matter circuitry is dimensionally and strongly related to both neurocognition and social cognition, and that microstructure of the uncinate fasciculus and the rostral body of the corpus callosum may assume a "privileged role" subserving both. Further, we found that participant-wise estimates of white matter microstructure, weighted by cognitive performance, were largely consistent with participants' categorical diagnosis, and predictive of (cross-sectional) functional outcomes.

CONCLUSIONS

The demonstrated strength of the relationship between white matter circuitry and neurocognition and social cognition underscores the potential for using relationships among these variables to identify biomarkers of functioning, with potential prognostic and therapeutic implications.

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.

A tablet-based quantitative assessment of manual dexterity for detection of early psychosis

Background

We performed a pilot study on whether tablet-based measures of manual dexterity can provide behavioral markers for detection of first-episode psychosis (FEP), and whether cortical excitability/inhibition was altered in FEP.

Methods

Behavioral and neurophysiological testing was undertaken in persons diagnosed with FEP (N = 20), schizophrenia (SCZ, N = 20), autism spectrum disorder (ASD, N = 20), and in healthy control subjects (N = 20). Five tablet tasks assessed different motor and cognitive functions: Finger Recognition for effector (finger) selection and mental rotation, Rhythm Tapping for temporal control, Sequence Tapping for control/memorization of motor sequences, Multi Finger Tapping for finger individuation, and Line Tracking for visuomotor control. Discrimination of FEP (from other groups) based on tablet-based measures was compared to discrimination through clinical neurological soft signs (NSS). Cortical excitability/inhibition, and cerebellar brain inhibition were assessed with transcranial magnetic stimulation.

Results

Compared to controls, FEP patients showed slower reaction times and higher errors in Finger Recognition, and more variability in Rhythm Tapping. Variability in Rhythm Tapping showed highest specificity for the identification of FEP patients compared to all other groups (FEP vs. ASD/SCZ/Controls; 75% sensitivity, 90% specificity, AUC = 0.83) compared to clinical NSS (95% sensitivity, 22% specificity, AUC = 0.49). Random Forest analysis confirmed FEP discrimination vs. other groups based on dexterity variables (100% sensitivity, 85% specificity, balanced accuracy = 92%). The FEP group had reduced short-latency intra-cortical inhibition (but similar excitability) compared to controls, SCZ, and ASD. Cerebellar inhibition showed a non-significant tendency to be weaker in FEP.

Conclusion

FEP patients show a distinctive pattern of dexterity impairments and weaker cortical inhibition. Easy-to-use tablet-based measures of manual dexterity capture neurological deficits in FEP and are promising markers for detection of FEP in clinical practice.

Psychotic disorders as a framework for precision psychiatry

People with psychotic disorders can show marked interindividual variations in the onset of illness, responses to treatment and relapse, but they receive broadly similar clinical care. Precision psychiatry is an approach that aims to stratify people with a given disorder according to different clinical outcomes and tailor treatment to their individual needs. At present, interindividual differences in outcomes of psychotic disorders are difficult to predict on the basis of clinical assessment alone. Therefore, current research in psychosis seeks to build models that predict outcomes by integrating clinical information with a range of biological measures. Here, we review recent progress in the application of precision psychiatry to psychotic disorders and consider the challenges associated with implementing this approach in clinical practice.

Effects of psychosis-associated genetic markers on brain volumetry: a systematic review of replicated findings and an independent validation

BACKGROUND

Given psychotic illnesses' high heritability and associations with brain structure, numerous neuroimaging-genetics findings have been reported in the last two decades. However, few findings have been replicated. In the present independent sample we aimed to replicate any psychosis-implicated SNPs (single nucleotide polymorphisms), which had previously shown at least two main effects on brain volume.

METHODS

A systematic review for SNPs showing a replicated effect on brain volume yielded 25 studies implicating seven SNPs in five genes. Their effect was then tested in 113 subjects with either schizophrenia, bipolar disorder, 'at risk mental state' or healthy state, for whole-brain and region-of-interest (ROI) associations with grey and white matter volume changes, using voxel-based morphometry.

RESULTS

We found FWER-corrected (Family-wise error rate) (i.e. statistically significant) associations of: (1) CACNA1C-rs769087-A with larger bilateral hippocampus and thalamus white matter, across the whole brain; and (2) CACNA1C-rs769087-A with larger superior frontal gyrus, as ROI. Higher replication concordance with existing literature was found, in decreasing order, for: (1) CACNA1C-rs769087-A, with larger dorsolateral-prefrontal/superior frontal gyrus and hippocampi (both with anatomical and directional concordance); (2) ZNF804A-rs11681373-A, with smaller angular gyrus grey matter and rectus gyri white matter (both with anatomical and directional concordance); and (3) BDNF-rs6265-T with superior frontal and middle cingulate gyri volume change (with anatomical and allelic concordance).

CONCLUSIONS

Most literature findings were not herein replicated. Nevertheless, high degree/likelihood of replication was found for two genome-wide association studies- and one candidate-implicated SNPs, supporting their involvement in psychosis and brain structure.

Machine learning for prediction of schizophrenia using genetic and demographic factors in the UK biobank

Machine learning (ML) holds promise for precision psychiatry, but its predictive performance is unclear. We assessed whether ML provided added value over logistic regression for prediction of schizophrenia, and compared models built using polygenic risk scores (PRS) or clinical/demographic factors. LASSO and ridge-penalised logistic regression, support vector machines (SVM), random forests, boosting, neural networks and stacked models were trained to predict schizophrenia, using PRS for schizophrenia (PRS_SZ), sex, parental depression, educational attainment, winter birth, handedness and number of siblings as predictors. Models were evaluated for discrimination using area under the receiver operator characteristic curve (AUROC) and relative importance of predictors using permutation feature importance (PFI). In a secondary analysis, fitted models were tested for association with schizophrenia-related traits which had not been used in model development. Following learning curve analysis, 738 cases and 3690 randomly sampled controls were selected from the UK Biobank. ML models combining all predictors showed the highest discrimination (linear SVM, AUROC = 0.71), but did not significantly outperform logistic regression. AUROC was robust over 100 random resamples of controls. PFI identified PRS_SZ as the most important predictor. Highest variance in fitted models was explained by schizophrenia-related traits including fluid intelligence (most associated: linear SVM), digit symbol substitution (RBF SVM), BMI (XGBoost), smoking status (XGBoost) and deprivation (linear SVM). In conclusion, ML approaches did not provide substantial added value for prediction of schizophrenia over logistic regression, as indexed by AUROC; however, risk scores derived with different ML approaches differ with respect to association with schizophrenia-related traits.

Prediction of transition to psychosis from an at-risk mental state using structural neuroimaging, genetic, and environmental data

INTRODUCTION

Psychosis is usually preceded by a prodromal phase in which patients are clinically identified as being at in an "At Risk Mental State" (ARMS). A few studies have demonstrated the feasibility of predicting psychosis transition from an ARMS using structural magnetic resonance imaging (sMRI) data and machine learning (ML) methods. However, the reliability of these findings is unclear due to possible sampling bias. Moreover, the value of genetic and environmental data in predicting transition to psychosis from an ARMS is yet to be explored.

METHODS

In this study we aimed to predict transition to psychosis from an ARMS using a combination of ML, sMRI, genome-wide genotypes, and environmental risk factors as predictors, in a sample drawn from a pool of 246 ARMS subjects (60 of whom later transitioned to psychosis). First, the modality-specific values in predicting transition to psychosis were evaluated using several: (a) feature types; (b) feature manipulation strategies; (c) ML algorithms; (d) cross-validation strategies, as well as sample balancing and bootstrapping. Subsequently, the modalities whose at least 60% of the classification models showed an balanced accuracy (BAC) statistically better than chance level were included in a multimodal classification model.

RESULTS AND DISCUSSION

Results showed that none of the modalities alone, i.e., neuroimaging, genetic or environmental data, could predict psychosis from an ARMS statistically better than chance and, as such, no multimodal classification model was trained/tested. These results suggest that the value of structural MRI data and genome-wide genotypes in predicting psychosis from an ARMS, which has been fostered by previous evidence, should be reconsidered.

Adverse clinical outcomes in people at clinical high-risk for psychosis related to altered interactions between hippocampal activity and glutamatergic function

Preclinical rodent models suggest that psychosis involves alterations in the activity and glutamatergic function in the hippocampus, driving dopamine activity through projections to the striatum. The extent to which this model applies to the onset of psychosis in clinical subjects is unclear. We assessed whether interactions between hippocampal glutamatergic function and activity/striatal connectivity are associated with adverse clinical outcomes in people at clinical high-risk (CHR) for psychosis. We measured functional Magnetic Resonance Imaging of hippocampal activation/connectivity, and 1H-Magnetic Resonance Spectroscopy of hippocampal glutamatergic metabolites in 75 CHR participants and 31 healthy volunteers. At follow-up, 12 CHR participants had transitioned to psychosis and 63 had not. Within the clinical high-risk cohort, at follow-up, 35 and 17 participants had a poor or a good functional outcome, respectively. The onset of psychosis (ppeakFWE = 0.003, t = 4.4, z = 4.19) and a poor functional outcome (ppeakFWE < 0.001, t = 5.52, z = 4.81 and ppeakFWE < 0.001, t = 5.25, z = 4.62) were associated with a negative correlation between the hippocampal activation and hippocampal Glx concentration at baseline. In addition, there was a negative association between hippocampal Glx concentration and hippocampo-striatal connectivity (ppeakFWE = 0.016, t = 3.73, z = 3.39, ppeakFWE = 0.014, t = 3.78, z = 3.42, ppeakFWE = 0.011, t = 4.45, z = 3.91, ppeakFWE = 0.003, t = 4.92, z = 4.23) in the total CHR sample, not seen in healthy volunteers. As predicted by preclinical models, adverse clinical outcomes in people at risk for psychosis are associated with altered interactions between hippocampal activity and glutamatergic function.

Multisite schizophrenia classification by integrating structural magnetic resonance imaging data with polygenic risk score

Previous brain structural magnetic resonance imaging studies reported that patients with schizophrenia have brain structural abnormalities, which have been used to discriminate schizophrenia patients from normal controls. However, most existing studies identified schizophrenia patients at a single site, and the genetic features closely associated with highly heritable schizophrenia were not considered. In this study, we performed standardized feature extraction on brain structural magnetic resonance images and on genetic data to separate schizophrenia patients from normal controls. A total of 1010 participants, 508 schizophrenia patients and 502 normal controls, were recruited from 8 independent sites across China. Classification experiments were carried out using different machine learning methods and input features. We tested a support vector machine, logistic regression, and an ensemble learning strategy using 3 feature sets of interest: (1) imaging features: gray matter volume, (2) genetic features: polygenic risk scores, and (3) a fusion of imaging features and genetic features. The performance was assessed by leave-one-site-out cross-validation. Finally, some important brain and genetic features were identified. We found that the models with both imaging and genetic features as input performed better than models with either alone. The average accuracy of the classification models with the best performance in the cross-validation was 71.6%. The genetic feature that measured the cumulative risk of the genetic variants most associated with schizophrenia contributed the most to the classification. Our work took the first step toward considering both structural brain alterations and genome-wide genetic factors in a large-scale multisite schizophrenia classification. Our findings may provide insight into the underlying pathophysiology and risk mechanisms of schizophrenia.

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.

DNA methylation differences in cortical grey and white matter in schizophrenia

Aim: Identify grey- and white-matter-specific DNA-methylation differences between schizophrenia (SCZ) patients and controls in postmortem brain cortical tissue. Materials & methods: Grey and white matter were separated from postmortem brain tissue of the superior temporal and medial frontal gyrus from SCZ (n = 10) and control (n = 11) cases. Genome-wide DNA-methylation analysis was performed using the Infinium EPIC Methylation Array (Illumina, CA, USA). Results: Four differentially methylated regions associated with SCZ status and tissue type (grey vs white matter) were identified within or near KLF9, SFXN1, SPRED2 and ALS2CL genes. Gene-expression analysis showed differential expression of KLF9 and SFXN1 in SCZ. Conclusion: Our data show distinct differences in DNA methylation between grey and white matter that are unique to SCZ, providing new leads to unravel the pathogenesis of SCZ.

Disturbances in White Matter Integrity in the Ultra-High-Risk Psychosis State-A Systematic Review

Schizophrenia is a severe and disabling mental illness whose etiology still remains unclear. The available literature indicates that there exist white matter (WM) abnormalities in people with schizophrenia spectrum disorders. Recent developments in modern neuroimaging methods have enabled the identification of the structure, morphology, and function of the underlying WM fibers in vivo. The purpose of this paper is to review the existing evidence about WM abnormalities in individuals at ultra-high risk of psychosis (UHR) with the use of diffusion tensor imaging (DTI) available from the National Center for Biotechnology Information PubMed (Medline) and Health Source: Nursing/Academic Edition databases. Of 358 relevant articles identified, 25 papers published in the years 2008–2020 were ultimately included in the review. Most of them supported the presence of subtle aberrations in WM in UHR individuals, especially in the superior longitudinal fasciculus (SLF), the inferior longitudinal fasciculus (ILF), and the inferior fronto-occipital fasciculus (IFOF). These alterations may therefore be considered a promising neurobiological marker for the risk of psychosis. However, due to methodological discrepancies and the relative scarcity of evidence, further investigation is called for, especially into connectome analysis in UHR patients.

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.

Classification of first-episode psychosis using cortical thickness: A large multicenter MRI study

Machine learning classifications of first-episode psychosis (FEP) using neuroimaging have predominantly analyzed brain volumes. Some studies examined cortical thickness, but most of them have used parcellation approaches with data from single sites, which limits claims of generalizability. To address these limitations, we conducted a large-scale, multi-site analysis of cortical thickness comparing parcellations and vertex-wise approaches. By leveraging the multi-site nature of the study, we further investigated how different demographical and site-dependent variables affected predictions. Finally, we assessed relationships between predictions and clinical variables. 428 subjects (147 females, mean age 27.14) with FEP and 448 (230 females, mean age 27.06) healthy controls were enrolled in 8 centers by the ClassiFEP group. All subjects underwent a structural MRI and were clinically assessed. Cortical thickness parcellation (68 areas) and full cortical maps (20,484 vertices) were extracted. Linear Support Vector Machine was used for classification within a repeated nested cross-validation framework. Vertex-wise thickness maps outperformed parcellation-based methods with a balanced accuracy of 66.2% and an Area Under the Curve of 72%. By stratifying our sample for MRI scanner, we increased generalizability across sites. Temporal brain areas resulted as the most influential in the classification. The predictive decision scores significantly correlated with age at onset, duration of treatment, and positive symptoms. In conclusion, although far from the threshold of clinical relevance, temporal cortical thickness proved to classify between FEP subjects and healthy individuals. The assessment of site-dependent variables permitted an increase in the across-site generalizability, thus attempting to address an important machine learning limitation.

Application of machine learning to predict reduction in total PANSS score and enrich enrollment in schizophrenia clinical trials

Clinical trial efficiency, defined as facilitating patient enrollment, and reducing the time to reach safety and efficacy decision points, is a critical driving factor for making improvements in therapeutic development. The present work evaluated a machine learning (ML) approach to improve phase II or proof‐of‐concept trials designed to address unmet medical needs in treating schizophrenia. Diagnostic data from the Clinical Antipsychotic Trials of Intervention Effectiveness (CATIE) trial were used to develop a binary classification ML model predicting individual patient response as either “improvement,” defined as greater than 20% reduction in total Positive and Negative Syndrome Scale (PANSS) score, or “no improvement,” defined as an inadequate treatment response (<20% reduction in total PANSS). A random forest algorithm performed best relative to other tree‐based approaches in model ability to classify patients after 6 months of treatment. Although model ability to identify true positives, a measure of model sensitivity, was poor (<0.2), its specificity, true negative rate, was high (0.948). A second model, adapted from the first, was subsequently applied as a proof‐of‐concept for the ML approach to supplement trial enrollment by identifying patients not expected to improve based on their baseline diagnostic scores. In three virtual trials applying this screening approach, the percentage of patients predicted to improve ranged from 46% to 48%, consistently approximately double the CATIE response rate of 22%. These results show the promising application of ML to improve clinical trial efficiency and, as such, ML models merit further consideration and development.

Cellular and extracellular white matter alterations indicate conversion to psychosis among individuals at clinical high-risk for psychosis

OBJECTIVES

It is important to find biomarkers associated with transition to illness in individuals at clinical high-risk for psychosis (CHR). Here, we use free-water imaging, an advanced diffusion MRI technique, to identify white matter alterations in the brains of CHR subjects who subsequently develop psychosis (CHR-P) compared to those who do not (CHR-NP).

METHODS

Twenty-four healthy controls (HC) and 30 CHR individuals, 8 of whom converted to schizophrenia after a mean follow-up of 15.16 months, received baseline MRI scans. Maps of fractional anisotropy (FA), FA of cellular tissue (FA_T), and extracellular free-water (FW) were extracted using tract-based spatial statistics after which voxel-wise non-parametric group statistics and correlations with symptom severity were performed.

RESULTS

There were no significant differences between HCs and the combined CHR group. However, prior to conversion, CHR-P showed widespread lower FA compared to CHR-NP (p_FWE < 0.05). FA changes in CHR-P were associated with significantly lower FA_T and higher FW, compared to CHR-NP. Positive symptoms correlated significantly with diffusion parameters in similar regions as those discriminating CHR-P from CHR-NP.

CONCLUSIONS

Our study suggests that cellular (FA_T) and extracellular (FW) white matter alterations are associated with positive symptom severity and indicate an elevated illness risk among CHR individuals.

Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research

By promising more accurate diagnostics and individual treatment recommendations, deep neural networks and in particular convolutional neural networks have advanced to a powerful tool in medical imaging. Here, we first give an introduction into methodological key concepts and resulting methodological promises including representation and transfer learning, as well as modelling domain-specific priors. After reviewing recent applications within neuroimaging-based psychiatric research, such as the diagnosis of psychiatric diseases, delineation of disease subtypes, normative modeling, and the development of neuroimaging biomarkers, we discuss current challenges. This includes for example the difficulty of training models on small, heterogeneous and biased data sets, the lack of validity of clinical labels, algorithmic bias, and the influence of confounding variables.

Alterations in white matter microstructure in individuals at persistent risk for psychosis

Abnormalities in brain white matter (WM) are reported in youth at-risk for psychosis. Yet, the neurodevelopmental time course of these abnormalities remains unclear. Thus, longitudinal diffusion-weighted imaging (DWI) was used to investigate WM abnormalities in youth at-risk for psychosis. A subset of individuals from the Philadelphia Neurodevelopmental Cohort (PNC) completed two DWI scans approximately 20 months apart. Youths were identified through structured interview as having subthreshold persistent psychosis risk symptoms (n = 46), and were compared to healthy typically developing participants (TD; n = 98). Analyses were conducted at voxelwise and regional levels. Nonlinear developmental patterns were examined using penalized splines within a generalized additive model. Compared to TD, youth with persistent psychosis risk symptoms had lower whole-brain WM fractional anisotropy (FA) and higher radial diffusivity (RD). Voxelwise analyses revealed clusters of significant WM abnormalities within the temporal and parietal lobes. Lower FA within the cingulum bundle of hippocampus and cerebrospinal tracts were the most robust deficits in individuals with persistent psychosis symptoms. These findings were consistent over two visits. Thus, it appears that WM abnormalities are present early in youth with persistent psychosis risk symptoms, however, there is little evidence to suggest that these features emerge in late adolescence or early adulthood. Future studies should seek to characterize WM abnormalities in younger individuals and follow individuals as subthreshold psychotic symptoms emerge.

Individualized Diagnostic and Prognostic Models for Patients With Psychosis Risk Syndromes: A Meta-analytic View on the State of the Art

BACKGROUND

The clinical high risk (CHR) paradigm has facilitated research into the underpinnings of help-seeking individuals at risk for developing psychosis, aiming at predicting and possibly preventing transition to the overt disorder. Statistical methods such as machine learning and Cox regression have provided the methodological basis for this research by enabling the construction of diagnostic models (i.e., distinguishing CHR individuals from healthy individuals) and prognostic models (i.e., predicting a future outcome) based on different data modalities, including clinical, neurocognitive, and neurobiological data. However, their translation to clinical practice is still hindered by the high heterogeneity of both CHR populations and methodologies applied.

METHODS

We systematically reviewed the literature on diagnostic and prognostic models built on Cox regression and machine learning. Furthermore, we conducted a meta-analysis on prediction performances investigating heterogeneity of methodological approaches and data modality.

RESULTS

A total of 44 articles were included, covering 3707 individuals for prognostic studies and 1052 individuals for diagnostic studies (572 CHR patients and 480 healthy control subjects). CHR patients could be classified against healthy control subjects with 78% sensitivity and 77% specificity. Across prognostic models, sensitivity reached 67% and specificity reached 78%. Machine learning models outperformed those applying Cox regression by 10% sensitivity. There was a publication bias for prognostic studies yet no other moderator effects.

CONCLUSIONS

Our results may be driven by substantial clinical and methodological heterogeneity currently affecting several aspects of the CHR field and limiting the clinical implementability of the proposed models. We discuss conceptual and methodological harmonization strategies to facilitate more reliable and generalizable models for future clinical practice.

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.

Functional Magnetic Resonance Imaging Connectivity Accurately Distinguishes Cases With Psychotic Disorders From Healthy Controls, Based on Cortical Features Associated With Brain Network Development

BACKGROUND

Machine learning (ML) can distinguish cases with psychotic disorder from healthy controls based on magnetic resonance imaging (MRI) data, but it is not yet clear which MRI metrics are the most informative for case-control ML, or how ML algorithms relate to the underlying biology.

METHODS

We analyzed multimodal MRI data from 2 independent case-control studies of psychotic disorders (cases, n = 65, 28; controls, n = 59, 80) and compared ML accuracy across 5 selected MRI metrics from 3 modalities. Cortical thickness, mean diffusivity, and fractional anisotropy were estimated at each of 308 cortical regions, as well as functional and structural connectivity between each pair of regions. Functional connectivity data were also used to classify nonpsychotic siblings of cases (n = 64) and to distinguish cases from controls in a third independent study (cases, n = 67; controls, n = 81).

RESULTS

In both principal studies, the most informative metric was functional MRI connectivity: The areas under the receiver operating characteristic curve were 88% and 76%, respectively. The cortical map of diagnostic connectivity features (ML weights) was replicable between studies (r = .27, p < .001); correlated with replicable case-control differences in functional MRI degree centrality and with a prior cortical map of adolescent development of functional connectivity; predicted intermediate probabilities of psychosis in siblings; and was replicated in the third case-control study.

CONCLUSIONS

ML most accurately distinguished cases from controls by a replicable pattern of functional MRI connectivity features, highlighting abnormal hubness of cortical nodes in an anatomical pattern consistent with the concept of psychosis as a disorder of network development.

A Systematic Characterization of Structural Brain Changes in Schizophrenia

A systematic characterization of the similarities and differences among different methods for detecting structural brain abnormalities in schizophrenia, such as voxel-based morphometry (VBM), tensor-based morphometry (TBM), and projection-based thickness (PBT), is important for understanding the brain pathology in schizophrenia and for developing effective biomarkers for a diagnosis of schizophrenia. However, such studies are still lacking. Here, we performed VBM, TBM, and PBT analyses on T1-weighted brain MR images acquired from 116 patients with schizophrenia and 116 healthy controls. We found that, although all methods detected wide-spread structural changes, different methods captured different information - only 10.35% of the grey matter changes in cortex were detected by all three methods, and VBM only detected 11.36% of the white matter changes detected by TBM. Further, pattern classification between patients and controls revealed that combining different measures improved the classification accuracy (81.9%), indicating that fusion of different structural measures serves as a better neuroimaging marker for the objective diagnosis of schizophrenia.

Psychosis, vulnerability, and the moral significance of biomedical innovation in psychiatry. Why ethicists should join efforts

The study of the neuroscience and genomics of mental illness are increasingly intertwined. This is mostly due to the translation of medical technologies into psychiatry and to technological convergence. This article focuses on psychosis. I argue that the convergence of neuroscience and genomics in the context of psychosis is morally problematic, and that ethics scholarship should go beyond the identification of a number of ethical, legal, and social issues. My argument is composed of two strands. First, I argue that we should respond to technological convergence by developing an integrated, patient-centred approach focused on the assessment of individual vulnerabilities. Responding to technological convergence requires that we (i) integrate insights from several areas of ethics, (ii) translate bioethical principles into the mental health context, and (iii) proactively try to anticipate future ethical concerns. Second, I argue that a nuanced understanding of the concept of vulnerability might help us to accomplish this task. I borrow Florencia Luna's notion of 'layers of vulnerability' to show how potential harms or wrongs to individuals who experience psychosis can be conceptualised as stemming from different sources, or layers, of vulnerability. I argue that a layered notion of vulnerability might serve as a common ground to achieve the ethical integration needed to ensure that biomedical innovation can truly benefit, and not harm, individuals who suffer from psychosis.

Treatment response prediction and individualized identification of first-episode drug-naïve schizophrenia using brain functional connectivity

Identifying biomarkers in schizophrenia during the first episode without the confounding effects of treatment has been challenging. Leveraging these biomarkers to establish diagnosis and make individualized predictions of future treatment responses to antipsychotics would be of great value, but there has been limited progress. In this study, by using machine learning algorithms and the functional connections of the superior temporal cortex, we successfully identified the first-episode drug-naive (FEDN) schizophrenia patients (accuracy 78.6%) and predict their responses to antipsychotic treatment (accuracy 82.5%) at an individual level. The functional connections (FC) were derived using the mutual information and the correlations, between the blood-oxygen-level dependent signals of the superior temporal cortex and other cortical regions acquired with the resting-state functional magnetic resonance imaging. We also found that the mutual information and correlation FC was informative in identifying individual FEDN schizophrenia and prediction of treatment response, respectively. The methods and findings in this paper could provide a critical step toward individualized identification and treatment response prediction in first-episode drug-naive schizophrenia, which could complement other biomarkers in the development of precision medicine approaches for this severe mental disorder.

Towards Precision Medicine in Psychosis: Benefits and Challenges of Multimodal Multicenter Studies-PSYSCAN: Translating Neuroimaging Findings From Research into Clinical Practice

In the last 2 decades, several neuroimaging studies investigated brain abnormalities associated with the early stages of psychosis in the hope that these could aid the prediction of onset and clinical outcome. Despite advancements in the field, neuroimaging has yet to deliver. This is in part explained by the use of univariate analytical techniques, small samples and lack of statistical power, lack of external validation of potential biomarkers, and lack of integration of nonimaging measures (eg, genetic, clinical, cognitive data). PSYSCAN is an international, longitudinal, multicenter study on the early stages of psychosis which uses machine learning techniques to analyze imaging, clinical, cognitive, and biological data with the aim of facilitating the prediction of psychosis onset and outcome. In this article, we provide an overview of the PSYSCAN protocol and we discuss benefits and methodological challenges of large multicenter studies that employ neuroimaging measures.

Functional, Anatomical, and Morphological Networks Highlight the Role of Basal Ganglia-Thalamus-Cortex Circuits in Schizophrenia

Evidence from electrophysiological, functional, and structural research suggests that abnormal brain connectivity plays an important role in the pathophysiology of schizophrenia. However, most previous studies have focused on single modalities only, each of which is associated with its own limitations. Multimodal combinations can more effectively utilize various information, but previous multimodal research mostly focuses on extracting local features, rather than carrying out research based on network perspective. This study included 135 patients with schizophrenia and 148 sex- and age-matched healthy controls. Functional magnetic resonance imaging, diffusion tensor imaging, and structural magnetic resonance imaging data were used to construct the functional, anatomical, and morphological networks of each participant, respectively. These networks were used in combination with machine learning to identify more consistent biomarkers of brain connectivity and explore the relationships between different modalities. We found that although each modality had divergent connectivity biomarkers, the convergent pattern was that all were mostly located within the basal ganglia-thalamus-cortex circuit. Furthermore, using the biomarkers of these 3 modalities as a feature yielded the highest classification accuracy (91.75%, relative to a single modality), suggesting that the combination of multiple modalities could be effectively utilized to obtain complementary information regarding different mode networks; furthermore, this information could help distinguish patients. These findings provide direct evidence for the disconnection hypothesis of schizophrenia, suggesting that abnormalities in the basal ganglia-thalamus-cortex circuit can be used as a biomarker of schizophrenia.

Synapse Pathology in Schizophrenia: A Meta-analysis of Postsynaptic Elements in Postmortem Brain Studies

Changed synapse density has been suggested to be involved in the altered brain connectivity underlying schizophrenia (SCZ) pathology. However, postmortem studies addressing this topic are heterogeneous and it is not known whether changes are restricted to specific brain regions. Using meta-analysis, we systematically and quantitatively reviewed literature on the density of postsynaptic elements in postmortem brain tissue of patients with SCZ compared to healthy controls. We included 3 outcome measurements for postsynaptic elements: dendritic spine density (DSD), postsynaptic density (PSD) number, and PSD protein expression levels. Random-effects meta-analysis (31 studies) revealed an overall decrease in density of postsynaptic elements in SCZ (Hedges's g: -0.33; 95% CI: -0.60 to -0.05; P = .020). Subgroup analyses showed reduction of postsynaptic elements in cortical but not subcortical tissues (Hedges's g: -0.44; 95% CI: -0.76 to -0.12; P = .008, Hedges's g: -0.11; 95% CI: -0.54 to 0.35; P = .671) and specifically a decrease for the outcome measure DSD (Hedges's g: -0.81; 95% CI: -1.37 to -0.26; P = .004). Further exploratory analyses showed a significant decrease of postsynaptic elements in the prefrontal cortex and cortical layer 3. In all analyses, substantial heterogeneity was present. Meta-regression analyses showed no influence of age, sex, postmortem interval, or brain bank on the effect size. This meta-analysis shows a region-specific decrease in the density of postsynaptic elements in SCZ. This phenotype provides an important cellular hallmark for future preclinical and neuropathological research in order to increase our understanding of brain dysconnectivity in SCZ.

Using Machine Learning and Structural Neuroimaging to Detect First Episode Psychosis: Reconsidering the Evidence

Despite the high level of interest in the use of machine learning (ML) and neuroimaging to detect psychosis at the individual level, the reliability of the findings is unclear due to potential methodological issues that may have inflated the existing literature. This study aimed to elucidate the extent to which the application of ML to neuroanatomical data allows detection of first episode psychosis (FEP), while putting in place methodological precautions to avoid overoptimistic results. We tested both traditional ML and an emerging approach known as deep learning (DL) using 3 feature sets of interest: (1) surface-based regional volumes and cortical thickness, (2) voxel-based gray matter volume (GMV) and (3) voxel-based cortical thickness (VBCT). To assess the reliability of the findings, we repeated all analyses in 5 independent datasets, totaling 956 participants (514 FEP and 444 within-site matched controls). The performance was assessed via nested cross-validation (CV) and cross-site CV. Accuracies ranged from 50% to 70% for surfaced-based features; from 50% to 63% for GMV; and from 51% to 68% for VBCT. The best accuracies (70%) were achieved when DL was applied to surface-based features; however, these models generalized poorly to other sites. Findings from this study suggest that, when methodological precautions are adopted to avoid overoptimistic results, detection of individuals in the early stages of psychosis is more challenging than originally thought. In light of this, we argue that the current evidence for the diagnostic value of ML and structural neuroimaging should be reconsidered toward a more cautious interpretation.

Using structural MRI to identify bipolar disorders - 13 site machine learning study in 3020 individuals from the ENIGMA Bipolar Disorders Working Group

Bipolar disorders (BDs) are among the leading causes of morbidity and disability. Objective biological markers, such as those based on brain imaging, could aid in clinical management of BD. Machine learning (ML) brings neuroimaging analyses to individual subject level and may potentially allow for their diagnostic use. However, fair and optimal application of ML requires large, multi-site datasets. We applied ML (support vector machines) to MRI data (regional cortical thickness, surface area, subcortical volumes) from 853 BD and 2167 control participants from 13 cohorts in the ENIGMA consortium. We attempted to differentiate BD from control participants, investigated different data handling strategies and studied the neuroimaging/clinical features most important for classification. Individual site accuracies ranged from 45.23% to 81.07%. Aggregate subject-level analyses yielded the highest accuracy (65.23%, 95% CI = 63.47-67.00, ROC-AUC = 71.49%, 95% CI = 69.39-73.59), followed by leave-one-site-out cross-validation (accuracy = 58.67%, 95% CI = 56.70-60.63). Meta-analysis of individual site accuracies did not provide above chance results. There was substantial agreement between the regions that contributed to identification of BD participants in the best performing site and in the aggregate dataset (Cohen's Kappa = 0.83, 95% CI = 0.829-0.831). Treatment with anticonvulsants and age were associated with greater odds of correct classification. Although short of the 80% clinically relevant accuracy threshold, the results are promising and provide a fair and realistic estimate of classification performance, which can be achieved in a large, ecologically valid, multi-site sample of BD participants based on regional neurostructural measures. Furthermore, the significant classification in different samples was based on plausible and similar neuroanatomical features. Future multi-site studies should move towards sharing of raw/voxelwise neuroimaging data.

Accuracy of diagnostic classification algorithms using cognitive-, electrophysiological-, and neuroanatomical data in antipsychotic-naïve schizophrenia patients

BACKGROUND

A wealth of clinical studies have identified objective biomarkers, which separate schizophrenia patients from healthy controls on a group level, but current diagnostic systems solely include clinical symptoms. In this study, we investigate if machine learning algorithms on multimodal data can serve as a framework for clinical translation.

METHODS

Forty-six antipsychotic-naïve, first-episode schizophrenia patients and 58 controls underwent neurocognitive tests, electrophysiology, and magnetic resonance imaging (MRI). Patients underwent clinical assessments before and after 6 weeks of antipsychotic monotherapy with amisulpride. Nine configurations of different supervised machine learning algorithms were applied to first estimate the unimodal diagnostic accuracy, and next to estimate the multimodal diagnostic accuracy. Finally, we explored the predictability of symptom remission.

RESULTS

Cognitive data significantly classified patients from controls (accuracies = 60-69%; p values = 0.0001-0.009). Accuracies of electrophysiology, structural MRI, and diffusion tensor imaging did not exceed chance level. Multimodal analyses with cognition plus any combination of one or more of the remaining three modalities did not outperform cognition alone. None of the modalities predicted symptom remission.

CONCLUSIONS

In this multivariate and multimodal study in antipsychotic-naïve patients, only cognition significantly discriminated patients from controls, and no modality appeared to predict short-term symptom remission. Overall, these findings add to the increasing call for cognition to be included in the definition of schizophrenia. To bring about the full potential of machine learning algorithms in first-episode, antipsychotic-naïve schizophrenia patients, careful a priori variable selection based on independent data as well as inclusion of other modalities may be required.

Can we accurately classify schizophrenia patients from healthy controls using magnetic resonance imaging and machine learning? A multi-method and multi-dataset study

Machine learning is a powerful tool that has previously been used to classify schizophrenia (SZ) patients from healthy controls (HC) using magnetic resonance images. Each study, however, uses different datasets, classification algorithms, and validation techniques. Here, we perform a critical appraisal of the accuracy of machine learning methodologies used in SZ/HC classifications studies by comparing three machine learning algorithms (logistic regression [LR], support vector machines [SVMs], and linear discriminant analysis [LDA]) on three independent datasets (435 subjects total) using two tissue density estimates and cortical thickness (CT). Performance is assessed using 10-fold cross-validation, as well as a held-out validation set. Classification using CT outperformed tissue densities, but there was no clear effect of dataset. LR, SVMs, and LDA each yielded the highest accuracies for a different feature set and validation paradigm, but most accuracies were between 55 and 70%, well below previously reported values. The highest accuracy achieved was 73.5% using CT data and an SVM. Taken together, these results illustrate some of the obstacles to constructing effective disease classifiers, and suggest that tissue densities and CT may not be sufficiently sensitive for SZ/HC classification given current available methodologies and sample sizes.

Integrating machining learning and multimodal neuroimaging to detect schizophrenia at the level of the individual

Schizophrenia is a severe psychiatric disorder associated with both structural and functional brain abnormalities. In the past few years, there has been growing interest in the application of machine learning techniques to neuroimaging data for the diagnostic and prognostic assessment of this disorder. However, the vast majority of studies published so far have used either structural or functional neuroimaging data, without accounting for the multimodal nature of the disorder. Structural MRI and resting‐state functional MRI data were acquired from a total of 295 patients with schizophrenia and 452 healthy controls at five research centers. We extracted features from the data including gray matter volume, white matter volume, amplitude of low‐frequency fluctuation, regional homogeneity and two connectome‐wide based metrics: structural covariance matrices and functional connectivity matrices. A support vector machine classifier was trained on each dataset separately to distinguish the subjects at individual level using each of the single feature as well as their combination, and 10‐fold cross‐validation was used to assess the performance of the model. Functional data allow higher accuracy of classification than structural data (mean 82.75% vs. 75.84%). Within each modality, the combination of images and matrices improves performance, resulting in mean accuracies of 81.63% for structural data and 87.59% for functional data. The use of all combined structural and functional measures allows the highest accuracy of classification (90.83%). We conclude that combining multimodal measures within a single model is a promising direction for developing biologically informed diagnostic tools in schizophrenia.

Gray matter volume reductions in patients with schizophrenia: A replication study across two cultural backgrounds

Structural gray matter (GM) volume reductions in patients with schizophrenia have rarely been replicated across two different sites, the impact of culture and clinical characteristics remains unresolved. Hence, we assessed GM volume reductions in patients with schizophrenia using 3 T magnetic resonace imaging to replicate results across two independent and culturally different backgrounds (Germany, Japan), and to investigate the impact of brain volume reductions on clinical characteristics. In total, 163 German (80 patients) and 203 Japanese (83 patients) participants were included in the analysis. Voxel-based morphometry (VBM) was used to investigate structural differences between the groups and across the two sites, comparing local GM volumes. Clinical variables were used to analyze effects unrelated to the socio-cultural background. Across both data sets, widespread GM reductions in frontal and temporal cortical parts were found between patients and controls, indicating strong effects of diagnosis and only small effects of site. The investigation of clinical characteristics revealed the strongest effects for chlorpromazine equivalents on GM volume reductions primarily in the Japanese sample. Although the effects of site are small, several brain regions do not overlap between the two groups. Thus, GM may be affected differently at the two sites in patients with schizophrenia.

Clinical-learning versus machine-learning for transdiagnostic prediction of psychosis onset in individuals at-risk

Predicting the onset of psychosis in individuals at-risk is based on robust prognostic model building methods including a priori clinical knowledge (also termed clinical-learning) to preselect predictors or machine-learning methods to select predictors automatically. To date, there is no empirical research comparing the prognostic accuracy of these two methods for the prediction of psychosis onset. In a first experiment, no improved performance was observed when machine-learning methods (LASSO and RIDGE) were applied-using the same predictors-to an individualised, transdiagnostic, clinically based, risk calculator previously developed on the basis of clinical-learning (predictors: age, gender, age by gender, ethnicity, ICD-10 diagnostic spectrum), and externally validated twice. In a second experiment, two refined versions of the published model which expanded the granularity of the ICD-10 diagnosis were introduced: ICD-10 diagnostic categories and ICD-10 diagnostic subdivisions. Although these refined versions showed an increase in apparent performance, their external performance was similar to the original model. In a third experiment, the three refined models were analysed under machine-learning and clinical-learning with a variable event per variable ratio (EPV). The best performing model under low EPVs was obtained through machine-learning approaches. The development of prognostic models on the basis of a priori clinical knowledge, large samples and adequate events per variable is a robust clinical prediction method to forecast psychosis onset in patients at-risk, and is comparable to machine-learning methods, which are more difficult to interpret and implement. Machine-learning methods should be preferred for high dimensional data when no a priori knowledge is available.

Relative importance of symptoms, cognition, and other multilevel variables for psychiatric disease classifications by machine learning

This study used machine-learning algorithms to make unbiased estimates of the relative importance of various multilevel data for classifying cases with schizophrenia (n = 60), schizoaffective disorder (n = 19), bipolar disorder (n = 20), unipolar depression (n = 14), and healthy controls (n = 51) into psychiatric diagnostic categories. The Random Forest machine learning algorithm, which showed best efficacy (92.9% SD: 0.06), was used to generate variable importance ranking of positive, negative, and general psychopathology symptoms, cognitive indexes, global assessment of function (GAF), and parental ages at birth for sorting participants into diagnostic categories. Symptoms were ranked most influential for separating cases from healthy controls, followed by cognition and maternal age. To separate schizophrenia/schizoaffective disorder from bipolar/unipolar depression, GAF was most influential, followed by cognition and paternal age. For classifying schizophrenia from all other psychiatric disorders, low GAF and paternal age were similarly important, followed by cognition, psychopathology and maternal age. Controls misclassified as schizophrenia cases showed lower nonverbal abilities, mild negative and general psychopathology symptoms, and younger maternal or older paternal age. The importance of symptoms for classification of cases and lower GAF for diagnosing schizophrenia, notably more important and distinct from cognition and symptoms, concurs with current practices. The high importance of parental ages is noteworthy and merits further study.

Increased frontal gray matter volume in individuals with prodromal psychosis

Background

Brain anatomical deficits associated with cognitive dysfunction have been reported in patients with schizophrenia. However, it remains unknown whether such anatomical deficits exist in individuals with prodromal psychosis. The present study is designed to investigate anatomical deficits in prodromal individuals and their associations with clinical/cognitive features.

Methods

Seventy‐four prodromal individuals and seventy‐six healthy controls were scanned using structural magnetic resonance imaging. Support vector machines were applied to test whether anatomical deficits might be used to discriminate prodromal individuals from healthy controls.

Results

Prodromal individuals showed significantly increased gray matter volume (GMV) in the right inferior frontal gyrus (IFG) and right rectus gyrus relative to healthy controls. No correlations were observed between increased GMV and clinical/cognitive characteristics. The combination of increased GMV in the right rectus gyrus and right IFG showed a sensitivity of 74.32%, a specificity of 67.11%, and an accuracy of 70.67% in differentiating prodromal individuals from healthy controls.

Conclusion

Our results provide evidence of increased frontal GMV in prodromal individuals. A combination of GMV values in the two frontal brain areas may serve as potential markers to discriminate prodromal individuals from healthy controls. The results thus highlight the importance of the frontal regions in the pathophysiology of psychosis.

Translational machine learning for psychiatric neuroimaging

Despite its initial promise, neuroimaging has not been widely translated into clinical psychiatry to assist in the prediction of diagnoses, prognoses, and optimal therapeutic strategies. Machine learning approaches may enhance the translational potential of neuroimaging because they specifically focus on overcoming biases by optimizing the generalizability of pipelines that measure complex brain patterns to predict targets at a single-subject level. This article introduces some fundamentals of a translational machine learning approach before selectively reviewing literature to-date. Promising initial results are then balanced by the description of limitations that should be considered in order to interpret existing research and maximize the possibility of future translation. Future directions are then presented in order to inspire further research and progress the field towards clinical translation.

Brain regional homogeneity and function connectivity in attenuated psychosis syndrome -based on a resting state fMRI study

BACKGROUND

By combining regional homogeneity (ReHo) and functional connectivity (FC) analyses, this study aimed to explore brain functional alterations in Attenuated Psychosis Syndrome (APS), which could provide complementary information for the neurophysiological indicators for schizophrenia (SZ) associated brain dysfunction.

METHODS

Twenty-one APS subjects and twenty healthy controls were enrolled in the data acquisition of demographics and clinical characteristics as well as structural and resting-state functional magnetic resonance imaging (rs-fMRI). ReHo analysis was conducted to determine the peak coordinate of the abnormal regional brain activity. Then, identified brain regions were considered as seed regions and were used to calculate FC between reginal brain voxels and whole brain voxels. Finally, potential correlations between imaging indices and clinical data were also explored.

RESULTS

Four APS and two HC subjects were excluded because the largest dynamic translation or rotation had exceeded 2 mm / 2°. Compared with healthy controls (HCs), APS subjects exhibited higher ReHo values in the right middle temporal gyrus (MTG) and lower ReHo values in the left middle frontal gyrus (MFG), left superior frontal gyrus (SFG), left postcentral gyrus (PoCG), and left superior frontal gyrus, medial (SFGmed). Considered these areas as seed regions, the APS subjects showed abnormal enhancement in functional brain connections, predominantly in the frontal and temporal lobes.

CONCLUSIONS

We concluded that the APS subjects had spatially regional dysfunction and remoted synchronous dysfunction in the frontal and temporal lobes of the brain, and changes in ReHo and FC patterns may reveal the mechanism of brain dysfunctions and may serve as an imaging biomarker for the diagnosis and evaluation of SZ.

A data science approach to predicting patient aggressive events in a psychiatric hospital

Recent advances in data science were used capitalize on the extensive quantity of data available in electronic health records to predict patient aggressive events. This retrospective study utilized electronic health records (N = 29,841) collected between January 2010 and December 2015 at Harris County Psychiatric Center, a 274-bed safety net community psychiatric facility. The primary outcome of interest was the presence (1.4%) versus absence (98.6%) of an aggressive event toward staff or patients. The best-performing algorithm, penalized generalized linear modeling, achieved an area under the curve = 0.7801. The strongest predictors of patient aggressive events included homelessness (b = 0.52), having been convicted of assault (b = 0.31), and having witnessed abuse (b = -0.28). The algorithm was also used to generate a cost-optimized probability threshold (6%) for an aggressive event, theoretically affording individualized hospital-staff coverage on the 2.8% of inpatients at highest risk for aggression, based on available hospital operating costs. The present research demonstrated the utility of a data science approach to better understand a high-priority event in psychiatric inpatient settings.

Investigating brain structural patterns in first episode psychosis and schizophrenia using MRI and a machine learning approach

In this study, we employed the Maximum Uncertainty Linear Discriminant Analysis (MLDA) to investigate whether the structural brain patterns in first episode psychosis (FEP) patients would be more similar to patients with chronic schizophrenia (SCZ) or healthy controls (HC), from a schizophrenia model perspective. Brain regions volumetric data were estimated by using MRI images of SCZ and FEP patients and HC. First, we evaluated the MLDA performance in discriminating SCZ from controls, which provided a score based on a model for changes in brain structure in SCZ. In the following, we compared the volumetric patterns of FEP patients with patterns of SCZ and healthy controls using these scores. The FEP group had a score distribution more similar to patients with schizophrenia (p-value = .461; Cohen's d=-.15) in comparison with healthy subjects (p-value=.003; Cohen's d = .62). Structures related to the limbic system and the circuitry involved in goal-directed behaviours were the most discriminant regions. There is a distinct pattern of volumetric changes in patients with schizophrenia in contrast to healthy controls, and this pattern seem to be detectable already in FEP.

Evaluating verbal learning and memory in patients with an at-risk mental state or first episode psychosis using structural equation modelling

BACKGROUND

Verbal learning and memory are impaired not only in patients with a first episode of psychosis (FEP) but also-to a lower extent-in those with an at-risk mental state for psychosis (ARMS). However, little is known about the specific nature of these impairments. Hence, we aimed to study learning and memory processes in ARMS and FEP patients by making use of structural equation modelling.

METHODS

Verbal learning was assessed with the California Verbal Learning Test (CVLT) in 98 FEP patients, 126 ARMS patients and 68 healthy controls (HC) as part of the Basel early detection of psychosis (FePsy) study. The four-factorial CFA model of Donders was used to estimate test performance on latent variables of the CVLT and growth curve analysis was used to model the learning curve. The latter allows disentangling initial recall, which is strongly determined by attentional processes, from the learning rate.

RESULTS

The CFA model revealed that ARMS and FEP patients were impaired in Attention Span, Learning Efficiency and Delayed Memory and that FEP patients were additionally impaired in Inaccurate Memory. Additionally, ARMS-NT, but not ARMS-T, performed significantly worse than HC on Learning Efficiency. The growth curve model indicated that FEP patients were impaired in both initial recall and learning rate and that ARMS patients were only impaired in the learning rate.

CONCLUSIONS

Since impairments were more pronounced in the learning rate than the initial recall, our results suggest that the lower scores in the CVLT reported in previous studies are more strongly driven by impairments in the rate of learning than by attentional processes.

Machine learning classification of first-episode schizophrenia spectrum disorders and controls using whole brain white matter fractional anisotropy

BACKGROUND

Early diagnosis of schizophrenia could improve the outcome of the illness. Unlike classical between-group comparisons, machine learning can identify subtle disease patterns on a single subject level, which could help realize the potential of MRI in establishing a psychiatric diagnosis. Machine learning has previously been predominantly tested on gray-matter structural or functional MRI data. In this paper we used a machine learning classifier to differentiate patients with a first episode of schizophrenia-spectrum disorder (FES) from healthy controls using diffusion tensor imaging.

METHODS

We applied linear support-vector machine (SVM) and traditional tract based spatial statistics between group analyses to brain fractional anisotropy (FA) data from 77 FES and 77 age and sex matched healthy controls. We also evaluated the effects of medication and symptoms on the SVM classification.

RESULTS

The SVM distinguished between patients and controls with significant accuracy of 62.34% (p = 0.005). Participants with FES showed widespread FA reductions relative to controls in a large cluster (N  = 56,647 voxels, corrected p = 0.002). The white matter regions, which contributed to the correct identification of participants with FES, overlapped with the regions, which showed lower FA in patients relative to controls. There was no association between the classification performance and medication or symptoms.

CONCLUSIONS

Our results provide a proof of concept that SVM might help differentiate FES patients early in the course of illness from healthy controls using white-matter fractional anisotropy. As there was no effect of medications or symptoms, the SVM classification seemed to be based on trait rather than state markers and appeared to capture the lower FA in FES participants relative to controls.

Diagnostic value of structural and diffusion imaging measures in schizophrenia

Objectives

Many studies have attempted to discriminate patients with schizophrenia from healthy controls by machine learning using structural or functional MRI. We included both structural and diffusion MRI (dMRI) and performed random forest (RF) and support vector machine (SVM) in this study.

Methods

We evaluated the performance of classifying schizophrenia using RF method and SVM with 504 features (volume and/or fractional anisotropy and trace) from 184 brain regions. We enrolled 47 patients and 23 age- and sex-matched healthy controls and resampled our data into a balanced dataset using a Synthetic Minority Oversampling Technique method. We randomly permuted the classification of all participants as a patient or healthy control 100 times and ran the RF and SVM with leave one out cross validation for each permutation. We then compared the sensitivity and specificity of the original dataset and the permuted dataset.

Results

Classification using RF with 504 features showed a significantly higher rate of performance compared to classification by chance: sensitivity (87.6% vs. 47.0%) and specificity (95.9 vs. 48.4%) performed by RF, sensitivity (89.5% vs. 48.0%) and specificity (94.5% vs. 47.1%) performed by SVM.

Conclusions

Machine learning using RF and SVM with both volume and diffusion measures can discriminate patients with schizophrenia with a high degree of performance. Further replications are required.

Combining multi-modality data for searching biomarkers in schizophrenia

Identification of imaging biomarkers for schizophrenia is an important but still challenging problem. Even though considerable efforts have been made over the past decades, quantitative alterations between patients and healthy subjects have not yet provided a diagnostic measure with sufficient high sensitivity and specificity. One of the most important reasons is the lack of consistent findings, which is in part due to single-mode study, which only detects single dimensional information by each modality, and thus misses the most crucial differences between groups. Here, we hypothesize that multimodal integration of functional MRI (fMRI), structural MRI (sMRI), and diffusion tensor imaging (DTI) might yield more power for the diagnosis of schizophrenia. A novel multivariate data fusion method for combining these modalities is introduced without reducing the dimension or using the priors from 161 schizophrenia patients and 168 matched healthy controls. The multi-index feature for each ROI is constructed and summarized with Wilk's lambda by performing multivariate analysis of variance to calculate the significant difference between different groups. Our results show that, among these modalities, fMRI has the most significant featureby calculating the Jaccard similarity coefficient (0.7416) and Kappa index (0.4833). Furthermore, fusion of these modalities provides the most plentiful information and the highest predictive accuracy of 86.52%. This work indicates that multimodal integration can improve the ability of distinguishing differences between groups and might be assisting in further diagnosis of schizophrenia.

Machine Learning Approaches for Clinical Psychology and Psychiatry

Machine learning approaches for clinical psychology and psychiatry explicitly focus on learning statistical functions from multidimensional data sets to make generalizable predictions about individuals. The goal of this review is to provide an accessible understanding of why this approach is important for future practice given its potential to augment decisions associated with the diagnosis, prognosis, and treatment of people suffering from mental illness using clinical and biological data. To this end, the limitations of current statistical paradigms in mental health research are critiqued, and an introduction is provided to critical machine learning methods used in clinical studies. A selective literature review is then presented aiming to reinforce the usefulness of machine learning methods and provide evidence of their potential. In the context of promising initial results, the current limitations of machine learning approaches are addressed, and considerations for future clinical translation are outlined.

Imaging and Genetic Biomarkers Predicting Transition to Psychosis

The search for diagnostic and prognostic biomarkers in schizophrenia care and treatment is the focus of many within the research community. Longitudinal cohorts of patients presenting at elevated genetic and clinical risk have provided a wealth of data that has informed our understanding of the development of schizophrenia and related psychotic disorders.Imaging follow-up of high-risk cohorts has demonstrated changes in cerebral grey matter of those that eventually transition to schizophrenia that predate the onset of symptoms and evolve over the course of illness. Longitudinal follow-up studies demonstrate that observed grey matter changes can be employed to differentiate those who will transition to schizophrenia from those who will not prior to the onset of the disorder.In recent years our understanding of the genetic makeup of schizophrenia has advanced significantly. The development of modern analysis techniques offers researchers the ability to objectively quantify genetic risk; these have been successfully applied within a high-risk paradigm to assist in differentiating between high-risk individuals who will subsequently become unwell and those who will not.This chapter will discuss the application of imaging and genetic biomarkers within high-risk groups to predict future transition to schizophrenia and related psychotic disorders. We aim to provide an overview of current approaches focussing on grey matter changes that are predictive of future transition to illness, the developing field of genetic risk scores and other methods being developed to aid clinicians in diagnosis and prognosis.

Is It Possible to Predict the Future in First-Episode Psychosis?

The outcome of first-episode psychosis (FEP) is highly variable, ranging from early sustained recovery to antipsychotic treatment resistance from the onset of illness. For clinicians, a possibility to predict patient outcomes would be highly valuable for the selection of antipsychotic treatment and in tailoring psychosocial treatments and psychoeducation. This selective review summarizes current knowledge of prognostic markers in FEP. We sought potential outcome predictors from clinical and sociodemographic factors, cognition, brain imaging, genetics, and blood-based biomarkers, and we considered different outcomes, like remission, recovery, physical comorbidities, and suicide risk. Based on the review, it is currently possible to predict the future for FEP patients to some extent. Some clinical features-like the longer duration of untreated psychosis (DUP), poor premorbid adjustment, the insidious mode of onset, the greater severity of negative symptoms, comorbid substance use disorders (SUDs), a history of suicide attempts and suicidal ideation and having non-affective psychosis-are associated with a worse outcome. Of the social and demographic factors, male gender, social disadvantage, neighborhood deprivation, dysfunctional family environment, and ethnicity may be relevant. Treatment non-adherence is a substantial risk factor for relapse, but a small minority of patients with acute onset of FEP and early remission may benefit from antipsychotic discontinuation. Cognitive functioning is associated with functional outcomes. Brain imaging currently has limited utility as an outcome predictor, but this may change with methodological advancements. Polygenic risk scores (PRSs) might be useful as one component of a predictive tool, and pharmacogenetic testing is already available and valuable for patients who have problems in treatment response or with side effects. Most blood-based biomarkers need further validation. None of the currently available predictive markers has adequate sensitivity or specificity used alone. However, personalized treatment of FEP will need predictive tools. We discuss some methodologies, such as machine learning (ML), and tools that could lead to the improved prediction and clinical utility of different prognostic markers in FEP. Combination of different markers in ML models with a user friendly interface, or novel findings from e.g., molecular genetics or neuroimaging, may result in computer-assisted clinical applications in the near future.