Neuropsychological testing and structural magnetic resonance imaging as diagnostic biomarkers early in the course of schizophrenia and related psychoses

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.

Effects of Brain Atlases and Machine Learning Methods on the Discrimination of Schizophrenia Patients: A Multimodal MRI Study

Recently, machine learning techniques have been widely applied in discriminative studies of schizophrenia (SZ) patients with multimodal magnetic resonance imaging (MRI); however, the effects of brain atlases and machine learning methods remain largely unknown. In this study, we collected MRI data for 61 first-episode SZ patients (FESZ), 79 chronic SZ patients (CSZ) and 205 normal controls (NC) and calculated 4 MRI measurements, including regional gray matter volume (GMV), regional homogeneity (ReHo), amplitude of low-frequency fluctuation and degree centrality. We systematically analyzed the performance of two classifications (SZ vs NC; FESZ vs CSZ) based on the combinations of three brain atlases, five classifiers, two cross validation methods and 3 dimensionality reduction algorithms. Our results showed that the groupwise whole-brain atlas with 268 ROIs outperformed the other two brain atlases. In addition, the leave-one-out cross validation was the best cross validation method to select the best hyperparameter set, but the classification performances by different classifiers and dimensionality reduction algorithms were quite similar. Importantly, the contributions of input features to both classifications were higher with the GMV and ReHo features of brain regions in the prefrontal and temporal gyri. Furthermore, an ensemble learning method was performed to establish an integrated model, in which classification performance was improved. Taken together, these findings indicated the effects of these factors in constructing effective classifiers for psychiatric diseases and showed that the integrated model has the potential to improve the clinical diagnosis and treatment evaluation of SZ.

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.

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.

Towards a brain-based predictome of mental illness

Neuroimaging-based approaches have been extensively applied to study mental illness in recent years and have deepened our understanding of both cognitively healthy and disordered brain structure and function. Recent advancements in machine learning techniques have shown promising outcomes for individualized prediction and characterization of patients with psychiatric disorders. Studies have utilized features from a variety of neuroimaging modalities, including structural, functional, and diffusion magnetic resonance imaging data, as well as jointly estimated features from multiple modalities, to assess patients with heterogeneous mental disorders, such as schizophrenia and autism. We use the term "predictome" to describe the use of multivariate brain network features from one or more neuroimaging modalities to predict mental illness. In the predictome, multiple brain network-based features (either from the same modality or multiple modalities) are incorporated into a predictive model to jointly estimate features that are unique to a disorder and predict subjects accordingly. To date, more than 650 studies have been published on subject-level prediction focusing on psychiatric disorders. We have surveyed about 250 studies including schizophrenia, major depression, bipolar disorder, autism spectrum disorder, attention-deficit hyperactivity disorder, obsessive-compulsive disorder, social anxiety disorder, posttraumatic stress disorder, and substance dependence. In this review, we present a comprehensive review of recent neuroimaging-based predictomic approaches, current trends, and common shortcomings and share our vision for future directions.

Testing Psychosis Phenotypes From Bipolar-Schizophrenia Network for Intermediate Phenotypes for Clinical Application: Biotype Characteristics and Targets

BACKGROUND

Psychiatry aspires to the molecular understanding of its disorders and, with that knowledge, to precision medicine. Research supporting such goals in the dimension of psychosis has been compromised, in part, by using phenomenology alone to estimate disease entities. To this end, we are proponents of a deep phenotyping approach in psychosis, using computational strategies to discover the most informative phenotypic fingerprint as a promising strategy to uncover mechanisms in psychosis.

METHODS

Doing this, the Bipolar-Schizophrenia Network for Intermediate Phenotypes (B-SNIP) has used biomarkers to identify distinct subtypes of psychosis with replicable biomarker characteristics. While we have presented these entities as relevant, their potential utility in clinical practice has not yet been demonstrated.

RESULTS

Here we carried out an analysis of clinical features that characterize biotypes. We found that biotypes have unique and defining clinical characteristics that could be used as initial screens in the clinical and research settings. Differences in these clinical features appear to be consistent with biotype biomarker profiles, indicating a link between biological features and clinical presentation. Clinical features associated with biotypes differ from those associated with DSM diagnoses, indicating that biotypes and DSM syndromes are not redundant and are likely to yield different treatment predictions. We highlight 3 predictions based on biotype that are derived from individual biomarker features and cannot be obtained from DSM psychosis syndromes.

CONCLUSIONS

In the future, biotypes may prove to be useful for targeting distinct molecular, circuit, cognitive, and psychosocial therapies for improved functional outcomes.

Topographic diversity of structural connectivity in schizophrenia

The neurobiological heterogeneity of schizophrenia is widely accepted, but it is unclear how mechanistic differences converge to produce the observed phenotype. Establishing a pathophysiological model that accounts for both neurobiological heterogeneity and phenotypic similarity is essential to inform stratified treatment approaches. In this cross-sectional diffusion tensor imaging study, we recruited 77 healthy controls, and 70 patients with DSM-IV diagnosis of schizophrenia. We first confirmed the heterogeneity in structural connectivity by showing a reduced between-individual similarity of the structural connectivity in patients compared to healthy controls. Second, at a system level, we found the diversity of the topographic distribution of the strength of structural connectivity was significantly reduced in patients (P = 7.21 × 10^-7, T₁₄₂ = 5.19 [95% CI: 3.37-7.52], Cohen's d = 0.91), and this affected 65 of the 90 brain regions examined (False Discovery Rate <5%). Third, when topographic diversity was used as a discriminant feature to train a model for classifying patients from controls, it significantly improved the accuracy on an independent sample (T₉₉ = 5.54; P < 0.001). These findings suggest a highly individualized pattern of structural dysconnectivity underlies the heterogeneity of schizophrenia, but these disruptions likely converge on an emergent common pathway to generate the clinical phenotype of the disorder.

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.

Multisite Machine Learning Analysis Provides a Robust Structural Imaging Signature of Schizophrenia Detectable Across Diverse Patient Populations and Within Individuals

Past work on relatively small, single-site studies using regional volumetry, and more recently machine learning methods, has shown that widespread structural brain abnormalities are prominent in schizophrenia. However, to be clinically useful, structural imaging biomarkers must integrate high-dimensional data and provide reproducible results across clinical populations and on an individual person basis. Using advanced multi-variate analysis tools and pooled data from case-control imaging studies conducted at 5 sites (941 adult participants, including 440 patients with schizophrenia), a neuroanatomical signature of patients with schizophrenia was found, and its robustness and reproducibility across sites, populations, and scanners, was established for single-patient classification. Analyses were conducted at multiple scales, including regional volumes, voxelwise measures, and complex distributed patterns. Single-subject classification was tested for single-site, pooled-site, and leave-site-out generalizability. Regional and voxelwise analyses revealed a pattern of widespread reduced regional gray matter volume, particularly in the medial prefrontal, temporolimbic and peri-Sylvian cortex, along with ventricular and pallidum enlargement. Multivariate classification using pooled data achieved a cross-validated prediction accuracy of 76% (AUC = 0.84). Critically, the leave-site-out validation of the detected schizophrenia signature showed accuracy/AUC range of 72-77%/0.73-0.91, suggesting a robust generalizability across sites and patient cohorts. Finally, individualized patient classifications displayed significant correlations with clinical measures of negative, but not positive, symptoms. Taken together, these results emphasize the potential for structural neuroimaging data to provide a robust and reproducible imaging signature of schizophrenia. A web-accessible portal is offered to allow the community to obtain individualized classifications of magnetic resonance imaging scans using the methods described herein.

Poorer Search Efficiency in Healthy Young Adults With High Schizotypal Personality Traits

Perceptual organization (PO) difficulties have repeatedly been reported in people with schizophrenia, and in healthy individuals with high levels of schizotypy traits, who are at increased risk for schizophrenia. In particular, poor performance on the Embedded Figures Test (EFT) has been interpreted as an atypically strong preference for global over local processing, even though these processes cannot be clearly disambiguated on this test. Here we use two separate versions of the Radial Frequency Search Task (RFST), a new index of PO abilities, to selectively investigate global and local processing of shape information in trait schizotypy. Schizotypy traits were assessed using the Wisconsin Schizotypy Scales-Brief. Individuals selected for high and low levels of positive schizotypy [assessed with the Wisconsin Schizotypy Scales-Brief Perceptual Aberration (PAb) scale] completed the EFT, along with the Global RFST and the Local RFST, all of which require participants to find a target shape amongst distractor elements. The High PAb group (n = 83) were less efficient (i.e., reactions times slowed more as the set size increased) than the Low PAb group (n = 146) on the Global RFST (significant group differences for Target Absent conditions only), but not the Local RFST. High and Low PAb groups also differed on other schizotypy traits, so the specificity of the results to positive schizotypy cannot be assured. Unexpectedly, no group differences were observed on the EFT; however, there was a small, but significant, positive correlation between RFST search efficiency and EFT performance, indicating that they shared some common processes. Overall, the pattern of results suggests that global (but not local) processing difficulties may be contributing to the poorer perceptual organization observed in groups with high levels of schizotypy traits. In addition, the confinement of this result to the Target Absent condition suggests that the underlying mechanism involves differences in decisional processes on the RFST between high and low schizotypy groups. The RFST shows promise as a useful tool for measuring specific perceptual organization abilities in non-clinical, and potentially clinical, samples.

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.

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.

Improved individualized prediction of schizophrenia in subjects at familial high risk, based on neuroanatomical data, schizotypal and neurocognitive features

To date, there are no reliable markers for predicting onset of schizophrenia in individuals at high risk (HR). Substantial promise is, however, shown by a variety of pattern classification approaches to neuroimaging data. Here, we examined the predictive accuracy of support vector machine (SVM) in later diagnosing schizophrenia, at a single-subject level, using a cohort of HR individuals drawn from multiply affected families and a combination of neuroanatomical, schizotypal and neurocognitive variables. Baseline structural magnetic resonance imaging (MRI), schizotypal and neurocognitive data from 17 HR subjects, who subsequently developed schizophrenia and a matched group of 17 HR subjects who did not make the transition, yet had psychotic symptoms, were included in the analysis. We employed recursive feature elimination (RFE), in a nested cross-validation scheme to identify the most significant predictors of disease transition and enhance diagnostic performance. Classification accuracy was 94% when a self-completed measure of schizotypy, a declarative memory test and structural MRI data were combined into a single learning algorithm; higher than when either quantitative measure was used alone. The discriminative neuroanatomical pattern involved gray matter volume differences in frontal, orbito-frontal and occipital lobe regions bilaterally as well as parts of the superior, medial temporal lobe and cerebellar regions. Our findings suggest that an early SVM-based prediction of schizophrenia is possible and can be improved by combining schizotypal and neurocognitive features with neuroanatomical variables. However, our predictive model needs to be tested by classifying a new, independent HR cohort in order to estimate its validity.

Precuneus functioning differentiates first-episode psychosis patients during the fantasy movie Alice in Wonderland

BACKGROUND

While group-level functional alterations have been identified in many brain regions of psychotic patients, multivariate machine-learning methods provide a tool to test whether some of such alterations could be used to differentiate an individual patient. Earlier machine-learning studies have focused on data collected from chronic patients during rest or simple tasks. We set out to unravel brain activation patterns during naturalistic stimulation in first-episode psychosis (FEP).

METHOD

We recorded brain activity from 46 FEP patients and 32 control subjects viewing scenes from the fantasy film Alice in Wonderland. Scenes with varying degrees of fantasy were selected based on the distortion of the 'sense of reality' in psychosis. After cleaning the data with a novel maxCorr method, we used machine learning to classify patients and healthy control subjects on the basis of voxel- and time-point patterns.

RESULTS

Most (136/194) of the voxels that best classified the groups were clustered in a bilateral region of the precuneus. Classification accuracies were up to 79.5% (p = 5.69 × 10-8), and correct classification was more likely the higher the patient's positive-symptom score. Precuneus functioning was related to the fantasy content of the movie, and the relationship was stronger in control subjects than patients.

CONCLUSIONS

These findings are the first to show abnormalities in precuneus functioning during naturalistic information processing in FEP patients. Correlational findings suggest that these alterations are associated with positive psychotic symptoms and processing of fantasy. The results may provide new insights into the neuronal basis of reality distortion in psychosis.

Grey matter volume patterns in thalamic nuclei are associated with familial risk for schizophrenia

Previous evidence suggests reduced thalamic grey matter volume (GMV) in patients with schizophrenia (SCZ). However, it is not considered an intermediate phenotype for schizophrenia, possibly because previous studies did not assess the contribution of individual thalamic nuclei and employed univariate statistics. Here, we hypothesized that multivariate statistics would reveal an association of GMV in different thalamic nuclei with familial risk for schizophrenia. We also hypothesized that accounting for the heterogeneity of thalamic GMV in healthy controls would improve the detection of subjects at familial risk for the disorder. We acquired MRI scans for 96 clinically stable SCZ, 55 non-affected siblings of patients with schizophrenia (SIB), and 249 HC. The thalamus was parceled into seven regions of interest (ROIs). After a canonical univariate analysis, we used GMV estimates of thalamic ROIs, together with total thalamic GMV and premorbid intelligence, as features in Random Forests to classify HC, SIB, and SCZ. Then, we computed a Misclassification Index for each individual and tested the improvement in SIB detection after excluding a subsample of HC misclassified as patients. Random Forests discriminated SCZ from HC (accuracy=81%) and SIB from HC (accuracy=75%). Left anteromedial thalamic volumes were significantly associated with both multivariate classifications (p<0.05). Excluding HC misclassified as SCZ improved greatly HC vs. SIB classification (Cohen's d=1.39). These findings suggest that multivariate statistics identify a familial background associated with thalamic GMV reduction in SCZ. They also suggest the relevance of inter-individual variability of GMV patterns for the discrimination of individuals at familial risk for the disorder.

Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls

Neuroimaging-based single subject prediction of brain disorders has gained increasing attention in recent years. Using a variety of neuroimaging modalities such as structural, functional and diffusion MRI, along with machine learning techniques, hundreds of studies have been carried out for accurate classification of patients with heterogeneous mental and neurodegenerative disorders such as schizophrenia and Alzheimer's disease. More than 500 studies have been published during the past quarter century on single subject prediction focused on a multiple brain disorders. In the first part of this study, we provide a survey of more than 200 reports in this field with a focus on schizophrenia, mild cognitive impairment (MCI), Alzheimer's disease (AD), depressive disorders, autism spectrum disease (ASD) and attention-deficit hyperactivity disorder (ADHD). Detailed information about those studies such as sample size, type and number of extracted features and reported accuracy are summarized and discussed. To our knowledge, this is by far the most comprehensive review of neuroimaging-based single subject prediction of brain disorders. In the second part, we present our opinion on major pitfalls of those studies from a machine learning point of view. Common biases are discussed and suggestions are provided. Moreover, emerging trends such as decentralized data sharing, multimodal brain imaging, differential diagnosis, disease subtype classification and deep learning are also discussed. Based on this survey, there is extensive evidence showing the great potential of neuroimaging data for single subject prediction of various disorders. However, the main bottleneck of this exciting field is still the limited sample size, which could be potentially addressed by modern data sharing models such as the ones discussed in this paper. Emerging big data technologies and advanced data-intensive machine learning methodologies such as deep learning have coincided with an increasing need for accurate, robust and generalizable single subject prediction of brain disorders during an exciting time. In this report, we survey the past and offer some opinions regarding the road ahead.

Supervised, Multivariate, Whole-Brain Reduction Did Not Help to Achieve High Classification Performance in Schizophrenia Research

We examined how penalized linear discriminant analysis with resampling, which is a supervised, multivariate, whole-brain reduction technique, can help schizophrenia diagnostics and research. In an experiment with magnetic resonance brain images of 52 first-episode schizophrenia patients and 52 healthy controls, this method allowed us to select brain areas relevant to schizophrenia, such as the left prefrontal cortex, the anterior cingulum, the right anterior insula, the thalamus, and the hippocampus. Nevertheless, the classification performance based on such reduced data was not significantly better than the classification of data reduced by mass univariate selection using a t-test or unsupervised multivariate reduction using principal component analysis. Moreover, we found no important influence of the type of imaging features, namely local deformations or gray matter volumes, and the classification method, specifically linear discriminant analysis or linear support vector machines, on the classification results. However, we ascertained significant effect of a cross-validation setting on classification performance as classification results were overestimated even though the resampling was performed during the selection of brain imaging features. Therefore, it is critically important to perform cross-validation in all steps of the analysis (not only during classification) in case there is no external validation set to avoid optimistically biasing the results of classification studies.

Multi-center MRI prediction models: Predicting sex and illness course in first episode psychosis patients

Structural Magnetic Resonance Imaging (MRI) studies have attempted to use brain measures obtained at the first-episode of psychosis to predict subsequent outcome, with inconsistent results. Thus, there is a real need to validate the utility of brain measures in the prediction of outcome using large datasets, from independent samples, obtained with different protocols and from different MRI scanners. This study had three main aims: 1) to investigate whether structural MRI data from multiple centers can be combined to create a machine-learning model able to predict a strong biological variable like sex; 2) to replicate our previous finding that an MRI scan obtained at first episode significantly predicts subsequent illness course in other independent datasets; and finally, 3) to test whether these datasets can be combined to generate multicenter models with better accuracy in the prediction of illness course. The multi-center sample included brain structural MRI scans from 256 males and 133 females patients with first episode psychosis, acquired in five centers: University Medical Center Utrecht (The Netherlands) (n=67); Institute of Psychiatry, Psychology and Neuroscience, London (United Kingdom) (n=97); University of São Paulo (Brazil) (n=64); University of Cantabria, Santander (Spain) (n=107); and University of Melbourne (Australia) (n=54). All images were acquired on 1.5-Tesla scanners and all centers provided information on illness course during a follow-up period ranging 3 to 7years. We only included in the analyses of outcome prediction patients for whom illness course was categorized as either "continuous" (n=94) or "remitting" (n=118). Using structural brain scans from all centers, sex was predicted with significant accuracy (89%; p<0.001). In the single- or multi-center models, illness course could not be predicted with significant accuracy. However, when reducing heterogeneity by restricting the analyses to male patients only, classification accuracy improved in some samples. This study provides proof of concept that combining multi-center MRI data to create a well performing classification model is possible. However, to create complex multi-center models that perform accurately, each center should contribute a sample either large or homogeneous enough to first allow accurate classification within the single-center.

Cognitive impairment in schizophrenia across age groups: a case-control study

BACKGROUND

The potential dynamics of cognitive impairment in schizophrenia is discussed in the literature of the field. Recent publications suggest modest changes in level of cognitive impairment after first psychotic episode. Present article attempts to explore cognitive differences between patients and controls across age groups and differences between age groups in clinical group.

METHODS

One hundred and twenty-eight hospitalized patients with schizophrenia (64 women and 64 men) and 68 individuals from the control group (32 women and 32 men) aged 18-55 years were examined. The patients were divided into age groups (18-25, 26-35, 36-45, 46-55). Both groups were examined using Wisconsin Card Sorting Test, Rey Auditory Verbal Learning Test, Rey Osterrieth Complex Figure Test, Trail Making Test (A and B), Stroop Test, verbal fluency test and Wechsler digit span.

RESULTS

Patients with schizophrenia obtained significantly lower scores versus the control group in regard to all the measured cognitive functions (Mann-Whitney U; p < 0.05. Most deficits were present in all age groups, however, statistically important impairment in executive functions (WCST) were present only in "older" groups.

CONCLUSIONS

Patients with schizophrenia obtained less favourable results than the control group in all age groups. Deficits regarding executive functions do not seem to be at a significant level among the youngest group, whereas they are more noticeable in the group of 46-55-year-olds. Executive functions are significantly lowered in the group aged 36-45 in comparison to the "younger" groups. The level of cognitive functions shows a mild exacerbation in connection with age, whereas cognitive rigidity proved to be related to the number of years spent without hospital treatment.

Diffusion magnetic resonance imaging study of schizophrenia in the context of abnormal neurodevelopment using multiple site data in a Chinese Han population

Schizophrenia has increasingly been considered a neurodevelopmental disorder, and the advancement of neuroimaging techniques and associated computational methods has enabled quantitative re-examination of this important theory on the pathogenesis of the disease. Inspired by previous findings from neonatal brains, we proposed that an increase in diffusion magnetic resonance imaging (dMRI) mean diffusivity (MD) should be observed in the cerebral cortex of schizophrenia patients compared with healthy controls, corresponding to lower tissue complexity and potentially a failure to reach cortical maturation. We tested this hypothesis using dMRI data from a Chinese Han population comprising patients from four different hospital sites. Utilizing data-driven methods based on the state-of-the-art tensor-based registration algorithm, significantly increased MD measurements were consistently observed in the cortex of schizophrenia patients across all four sites, despite differences in psychopathology, exposure to antipsychotic medication and scanners used for image acquisition. Specifically, we found increased MD in the limbic system of the schizophrenic brain, mainly involving the bilateral insular and prefrontal cortices. In light of the existing literature, we speculate that this may represent a neuroanatomical signature of the disorder, reflecting microstructural deficits due to developmental abnormalities. Our findings not only provide strong support to the abnormal neurodevelopment theory of schizophrenia, but also highlight an important neuroimaging endophenotype for monitoring the developmental trajectory of high-risk subjects of the disease, thereby facilitating early detection and prevention.

From estimating activation locality to predicting disorder: A review of pattern recognition for neuroimaging-based psychiatric diagnostics

Psychiatric disorders are increasingly being recognised as having a biological basis, but their diagnosis is made exclusively behaviourally. A promising approach for 'biomarker' discovery has been based on pattern recognition methods applied to neuroimaging data, which could yield clinical utility in future. In this review we survey the literature on pattern recognition for making diagnostic predictions in psychiatric disorders, and evaluate progress made in translating such findings towards clinical application. We evaluate studies on many criteria, including data modalities used, the types of features extracted and algorithm applied. We identify problems common to many studies, such as a relatively small sample size and a primary focus on estimating generalisability within a single study. Furthermore, we highlight challenges that are not widely acknowledged in the field including the importance of accommodating disease prevalence, the necessity of more extensive validation using large carefully acquired samples, the need for methodological innovations to improve accuracy and to discriminate between multiple disorders simultaneously. Finally, we identify specific clinical contexts in which pattern recognition can add value in the short to medium term.

Overdiagnosis in the era of neuropsychiatric imaging

New guidelines proposed by the National Institute of Mental Health are intended to transform the management of patients with psychiatric disorders. It is anticipated that neuroimaging and other biomarkers will play a more prominent role in diagnosis and prognosis, especially in the prodromal phase of illness. Earlier treatment of psychiatric disorders has the potential to improve outcomes significantly. However, diagnosis in the absence of symptoms can lead to overdiagnosis. Overdiagnosis is a problem in many fields of medicine but could pose additional problems in psychiatry because of the stigmatization that often accompanies a diagnosis of mental illness. This review discusses the magnetic resonance imaging methods that hold the most promise for evaluating neuropsychiatric disorders, the likelihood that they could lead to overdiagnosis, and opportunities to minimize the impact of overdiagnosis in psychiatric disorders.

Combining various types of classifiers and features extracted from magnetic resonance imaging data in schizophrenia recognition

We investigated a combination of three classification algorithms, namely the modified maximum uncertainty linear discriminant analysis (mMLDA), the centroid method, and the average linkage, with three types of features extracted from three-dimensional T1-weighted magnetic resonance (MR) brain images, specifically MR intensities, grey matter densities, and local deformations for distinguishing 49 first episode schizophrenia male patients from 49 healthy male subjects. The feature sets were reduced using intersubject principal component analysis before classification. By combining the classifiers, we were able to obtain slightly improved results when compared with single classifiers. The best classification performance (81.6% accuracy, 75.5% sensitivity, and 87.8% specificity) was significantly better than classification by chance. We also showed that classifiers based on features calculated using more computation-intensive image preprocessing perform better; mMLDA with classification boundary calculated as weighted mean discriminative scores of the groups had improved sensitivity but similar accuracy compared to the original MLDA; reducing a number of eigenvectors during data reduction did not always lead to higher classification accuracy, since noise as well as the signal important for classification were removed. Our findings provide important information for schizophrenia research and may improve accuracy of computer-aided diagnostics of neuropsychiatric diseases.

[Neuroimaging in psychiatry: multivariate analysis techniques for diagnosis and prognosis]

BACKGROUND

Multiple studies successfully applied multivariate analysis to neuroimaging data demonstrating the potential utility of neuroimaging for clinical diagnostic and prognostic purposes.

OBJECTIVES

Summary of the current state of research regarding the application of neuroimaging in the field of psychiatry.

MATERIAL AND METHODS

Literature review of current studies.

RESULTS

Results of current studies indicate the potential application of neuroimaging data across various diagnoses, such as depression, schizophrenia, bipolar disorder and dementia. Potential applications include disease classification, differential diagnosis and prediction of disease course.

CONCLUSION

The results of the studies are heterogeneous although some studies report promising findings. Further multicentre studies are needed with clearly specified patient populations to systematically investigate the potential utility of neuroimaging for the clinical routine.

The MCIC collection: a shared repository of multi-modal, multi-site brain image data from a clinical investigation of schizophrenia

Expertly collected, well-curated data sets consisting of comprehensive clinical characterization and raw structural, functional and diffusion-weighted DICOM images in schizophrenia patients and sex and age-matched controls are now accessible to the scientific community through an on-line data repository (coins.mrn.org). The Mental Illness and Neuroscience Discovery Institute, now the Mind Research Network (MRN, http://www.mrn.org/ ), comprised of investigators at the University of New Mexico, the University of Minnesota, Massachusetts General Hospital, and the University of Iowa, conducted a cross-sectional study to identify quantitative neuroimaging biomarkers of schizophrenia. Data acquisition across multiple sites permitted the integration and cross-validation of clinical, cognitive, morphometric, and functional neuroimaging results gathered from unique samples of schizophrenia patients and controls using a common protocol across sites. Particular effort was made to recruit patients early in the course of their illness, at the onset of their symptoms. There is a relatively even sampling of illness duration in chronic patients. This data repository will be useful to 1) scientists who can study schizophrenia by further analysis of this cohort and/or by pooling with other data; 2) computer scientists and software algorithm developers for testing and validating novel registration, segmentation, and other analysis software; and 3) educators in the fields of neuroimaging, medical image analysis and medical imaging informatics who need exemplar data sets for courses and workshops. Sharing provides the opportunity for independent replication of already published results from this data set and novel exploration. This manuscript describes the inclusion/exclusion criteria, imaging parameters and other information that will assist those wishing to use this data repository.

Towards the identification of imaging biomarkers in schizophrenia, using multivariate pattern classification at a single-subject level

Standard univariate analyses of brain imaging data have revealed a host of structural and functional brain alterations in schizophrenia. However, these analyses typically involve examining each voxel separately and making inferences at group-level, thus limiting clinical translation of their findings. Taking into account the fact that brain alterations in schizophrenia expand over a widely distributed network of brain regions, univariate analysis methods may not be the most suited choice for imaging data analysis. To address these limitations, the neuroimaging community has turned to machine learning methods both because of their ability to examine voxels jointly and their potential for making inferences at a single-subject level. This article provides a critical overview of the current and foreseeable applications of machine learning, in identifying imaging-based biomarkers that could be used for the diagnosis, early detection and treatment response of schizophrenia, and could, thus, be of high clinical relevance. We discuss promising future research directions and the main difficulties facing machine learning researchers as far as their potential translation into clinical practice is concerned.

Can structural MRI aid in clinical classification? A machine learning study in two independent samples of patients with schizophrenia, bipolar disorder and healthy subjects

Although structural magnetic resonance imaging (MRI) has revealed partly non-overlapping brain abnormalities in schizophrenia and bipolar disorder, it is unknown whether structural MRI scans can be used to separate individuals with schizophrenia from those with bipolar disorder. An algorithm capable of discriminating between these two disorders could become a diagnostic aid for psychiatrists. Here, we scanned 66 schizophrenia patients, 66 patients with bipolar disorder and 66 healthy subjects on a 1.5T MRI scanner. Three support vector machines were trained to separate patients with schizophrenia from healthy subjects, patients with schizophrenia from those with bipolar disorder, and patients with bipolar disorder from healthy subjects, respectively, based on their gray matter density images. The predictive power of the models was tested using cross-validation and in an independent validation set of 46 schizophrenia patients, 47 patients with bipolar disorder and 43 healthy subjects scanned on a 3T MRI scanner. Schizophrenia patients could be separated from healthy subjects with an average accuracy of 90%. Additionally, schizophrenia patients and patients with bipolar disorder could be distinguished with an average accuracy of 88%.The model delineating bipolar patients from healthy subjects was less accurate, correctly classifying 67% of the healthy subjects and only 53% of the patients with bipolar disorder. In the latter group, lithium and antipsychotics use had no influence on the classification results. Application of the 1.5T models on the 3T validation set yielded average classification accuracies of 76% (healthy vs schizophrenia), 66% (bipolar vs schizophrenia) and 61% (healthy vs bipolar). In conclusion, the accurate separation of schizophrenia from bipolar patients on the basis of structural MRI scans, as demonstrated here, could be of added value in the differential diagnosis of these two disorders. The results also suggest that gray matter pathology in schizophrenia and bipolar disorder differs to such an extent that they can be reliably differentiated using machine learning paradigms.

Clinical utility of machine-learning approaches in schizophrenia: improving diagnostic confidence for translational neuroimaging

Machine-learning approaches are becoming commonplace in the neuroimaging literature as potential diagnostic and prognostic tools for the study of clinical populations. However, very few studies provide clinically informative measures to aid in decision-making and resource allocation. Head-to-head comparison of neuroimaging-based multivariate classifiers is an essential first step to promote translation of these tools to clinical practice. We systematically evaluated the classifier performance using back-to-back structural MRI in two field strengths (3- and 7-T) to discriminate patients with schizophrenia (n = 19) from healthy controls (n = 20). Gray matter (GM) and white matter images were used as inputs into a support vector machine to classify patients and control subjects. Seven Tesla classifiers outperformed the 3-T classifiers with accuracy reaching as high as 77% for the 7-T GM classifier compared to 66.6% for the 3-T GM classifier. Furthermore, diagnostic odds ratio (a measure that is not affected by variations in sample characteristics) and number needed to predict (a measure based on Bayesian certainty of a test result) indicated superior performance of the 7-T classifiers, whereby for each correct diagnosis made, the number of patients that need to be examined using the 7-T GM classifier was one less than the number that need to be examined if a different classifier was used. Using a hypothetical example, we highlight how these findings could have significant implications for clinical decision-making. We encourage the reporting of measures proposed here in future studies utilizing machine-learning approaches. This will not only promote the search for an optimum diagnostic tool but also aid in the translation of neuroimaging to clinical use.

Discrimination of female schizophrenia patients from healthy women using multiple structural brain measures obtained with voxel-based morphometry

AIM

Although schizophrenia and control subjects differ on a variety of neuroanatomical measures, the specificity and sensitivity of any one measure for differentiating between the two groups are low. To identify the correlative pattern of brain changes that best discriminate schizophrenia patients from healthy subjects, discriminant analysis techniques using voxel-based morphometry were applied.

METHODS

The first analysis was conducted to obtain a statistical model that classified 105 female healthy subjects and 38 female schizophrenia patients. First, the differences in gray matter and cerebrospinal fluid volume between the patients and healthy subjects were evaluated using optimized voxel-based morphometry. Then, a discriminant analysis reflecting the results of this evaluation was adopted. The second analysis was performed to prospectively validate the statistical model by successfully classifying a new group that consisted of 23 female healthy subjects and 23 female schizophrenia patients.

RESULTS

The use of these variables resulted in correct classification rates of 0.72 in the control subjects and 0.76 in the schizophrenia patients. In the second validation analysis using these variables, correct classification rates of 0.70 in the control subjects and 0.74 in the schizophrenia patients were achieved.

CONCLUSION

Schizophrenia patients have structural deviations in multiple brain areas, and a combination of structural brain measures can distinguish between patients and controls.

Individualized prediction of illness course at the first psychotic episode: a support vector machine MRI study

BACKGROUND

To date, magnetic resonance imaging (MRI) has made little impact on the diagnosis and monitoring of psychoses in individual patients. In this study, we used a support vector machine (SVM) whole-brain classification approach to predict future illness course at the individual level from MRI data obtained at the first psychotic episode.

METHOD

One hundred patients at their first psychotic episode and 91 healthy controls had an MRI scan. Patients were re-evaluated 6.2 years (s.d.=2.3) later, and were classified as having a continuous, episodic or intermediate illness course. Twenty-eight subjects with a continuous course were compared with 28 patients with an episodic course and with 28 healthy controls. We trained each SVM classifier independently for the following contrasts: continuous versus episodic, continuous versus healthy controls, and episodic versus healthy controls.

RESULTS

At baseline, patients with a continuous course were already distinguishable, with significance above chance level, from both patients with an episodic course (p=0.004, sensitivity=71, specificity=68) and healthy individuals (p=0.01, sensitivity=71, specificity=61). Patients with an episodic course could not be distinguished from healthy individuals. When patients with an intermediate outcome were classified according to the discriminating pattern episodic versus continuous, 74% of those who did not develop other episodes were classified as episodic, and 65% of those who did develop further episodes were classified as continuous (p=0.035).

CONCLUSIONS

We provide preliminary evidence of MRI application in the individualized prediction of future illness course, using a simple and automated SVM pipeline. When replicated and validated in larger groups, this could enable targeted clinical decisions based on imaging data.