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.

Cerebellar parcellation in schizophrenia and bipolar disorder.

OBJECTIVE: The cerebellum is involved in cognitive processing and emotion control. Cerebellar alterations could explain symptoms of schizophrenia spectrum disorder (SZ) and bipolar disorder (BD). In addition, literature suggests that lithium might influence cerebellar anatomy. Our aim was to study cerebellar anatomy in SZ and BD, and investigate the effect of lithium. METHODS: Participants from 7 centers worldwide underwent a 3T MRI. We included 182 patients with SZ, 144 patients with BD, and 322 controls. We automatically segmented the cerebellum using the CERES pipeline. All outputs were visually inspected. RESULTS: Patients with SZ showed a smaller global cerebellar gray matter volume compared to controls, with most of the changes located to the cognitive part of the cerebellum (Crus II and lobule VIIb). This decrease was present in the subgroup of patients with recent-onset SZ. We did not find any alterations in the cerebellum in patients with BD. However, patients medicated with lithium had a larger size of the anterior cerebellum, compared to patients not treated with lithium. CONCLUSION: Our multicenter study supports a distinct pattern of cerebellar alterations in SZ and BD.

Identifying a neuroanatomical signature of schizophrenia, reproducible across sites and stages, using machine learning with structured sparsity.

OBJECTIVE: Structural MRI (sMRI) increasingly offers insight into abnormalities inherent to schizophrenia. Previous machine learning applications suggest that individual classification is feasible and reliable and, however, is focused on the predictive performance of the clinical status in cross-sectional designs, which has limited biological perspectives. Moreover, most studies depend on relatively small cohorts or single recruiting site. Finally, no study controlled for disease stage or medication's effect. These elements cast doubt on previous findings' reproducibility. METHOD: We propose a machine learning algorithm that provides an interpretable brain signature. Using large datasets collected from 4 sites (276 schizophrenia patients, 330 controls), we assessed cross-site prediction reproducibility and associated predictive signature. For the first time, we evaluated the predictive signature regarding medication and illness duration using an independent dataset of first-episode patients. RESULTS: Machine learning classifiers based on neuroanatomical features yield significant intersite prediction accuracies (72%) together with an excellent predictive signature stability. This signature provides a neural score significantly correlated with symptom severity and the extent of cognitive impairments. Moreover, this signature demonstrates its efficiency on first-episode psychosis patients (73% accuracy). CONCLUSION: These results highlight the existence of a common neuroanatomical signature for schizophrenia, shared by a majority of patients even from an early stage of the disorder.

Connectivity of the anterior insula differentiates participants with first-episode schizophrenia spectrum disorders from controls: a machine-learning study.

BACKGROUND: Early diagnosis of schizophrenia could improve the outcomes and limit the negative effects of untreated illness. Although participants with schizophrenia show aberrant functional connectivity in brain networks, these between-group differences have a limited diagnostic utility. Novel methods of magnetic resonance imaging (MRI) analyses, such as machine learning (ML), may help bring neuroimaging from the bench to the bedside. Here, we used ML to differentiate participants with a first episode of schizophrenia-spectrum disorder (FES) from healthy controls based on resting-state functional connectivity (rsFC). METHOD: We acquired resting-state functional MRI data from 63 patients with FES who were individually matched by age and sex to 63 healthy controls. We applied linear kernel support vector machines (SVM) to rsFC within the default mode network, the salience network and the central executive network. RESULTS: The SVM applied to the rsFC within the salience network distinguished the FES from the control participants with an accuracy of 73.0% (p = 0.001), specificity of 71.4% and sensitivity of 74.6%. The classification accuracy was not significantly affected by medication dose, or by the presence of psychotic symptoms. The functional connectivity within the default mode or the central executive networks did not yield classification accuracies above chance level. CONCLUSIONS: Seed-based functional connectivity maps can be utilized for diagnostic classification, even early in the course of schizophrenia. The classification was probably based on trait rather than state markers, as symptoms or medications were not significantly associated with classification accuracy. Our results support the role of the anterior insula/salience network in the pathophysiology of FES.

Psychiatrist's adherence: a new factor in relapse prevention of schizophrenia. A randomized controlled study on relapse control through telemedicine system.

ACCESSIBLE SUMMARY: Exposure to psychotic states has detrimental effects on the long-term outcome of schizophrenia and brain integrity. Therefore, improving relapse prevention is a key component of long-term management of schizophrenia. Previous studies using continuous monitoring of an individual's early signs of relapse and adopting preventative pharmacological interventions, when early signs are detected, showed promising clinical results in terms of relapse risk reduction. This 18-month multi-centre parallel randomized controlled, open label, trial with telemedicine relapse prevention programme ITAREPS failed to show superiority of maintenance plus prodrome-based targeted medication strategy over treatment as usual. The study, marked by low investigator's adherence, confirmed that absence of pharmacological intervention at early stage of prodrome, critically influenced the risk of relapse. This and previous randomized controlled trials with telemedicine programme ITAREPS suggested that substantial improvement in relapse prevention in schizophrenia is likely to be unattainable under current clinical settings. Future preventive strategies in schizophrenia would require rapid pharmacological intervention upon occurrence of subclinical prodromal symptoms that are undetectable under conventional outpatient practice. Studies with ITAREPS suggested that integration of telemedicine relapse prevention systems and visiting nurse service might together represent practical solution capable to address those requirements. ABSTRACT: The Information Technology Aided Relapse Prevention Programme in Schizophrenia (ITAREPS) presents a telemedicine solution for weekly monitoring and management of schizophrenia. This study aims to evaluate the effectiveness of the programme in reducing the number of hospitalizations during the 18-month multi-centre parallel randomized controlled, open label, trial. Outpatients with schizophrenia or schizoaffective disorder were randomized to the active (n = 74) or control group (n = 72). In the active arm, investigators increased the antipsychotic dose upon occurrence of prodrome announced by the system. Intention-to-treat analysis showed no between-group difference in the hospitalization-free survival rate [Kaplan-Meier method; hazard ratio (HR) = 1.21, 95% confidence interval (CI): 0.56-2.61, P = 0.6). In a post hoc multivariate Cox proportional hazards model, out of 13 potential predictors, only ITAREPS-related variables (number of alerts without pharmacological intervention/HR = 1.38, P = 0.042/ and patient non-adherence with ITAREPS /HR = 1.08, P = 0.009/) increased the risk of hospitalization. In this trial ITAREPS was not effective. The results in context with previous ITAREPS studies suggest non-adherence of both psychiatrists and patients as the main reasons for the failure of this preventive strategy. Tertiary prevention in schizophrenia have to be regarded a major challenge, warranting the need for implementation of strategies with more active participation of both patient and treating psychiatrist.

White matter changes in first episode psychosis and their relation to the size of sample studied: a DTI study.

BACKGROUND: White matter abnormality has been recently proposed as a pathophysiological feature of schizophrenia (SZ). However, most of the data available has been gathered from chronic patients, and was therefore possibly confounded by factors such as duration of the disease, and treatment received. The extent and localization of these changes is also not clear. METHODS: We examined a population of early stage SZ patients using diffusion tensor imaging (DTI). 77 SZ patients and 60 healthy controls (HCs) were included in the analysis using Tract-Based Spatial Statistics (TBSS). We have also analyzed 250 randomly created subsets of the original cohort, to investigate the relation between the result of TBSS analysis, and the size of the sample studied. RESULTS: We have found a significant decrease in fractional anisotropy (FA) in the patient group. This change is present in most major white matter (WM) tracts including the corpus callosum, superior and inferior longitudinal fasciculi, inferior fronto-occipital fasciculus, and posterior thalamic radiation. Furthermore, we identified a clear trend towards an increase in the number and spatial extent of significant voxels reported, with an increasing number of subjects included in the analysis. CONCLUSION: Our study shows that FA is significantly decreased in patients at an early stage of schizophrenia, and that the extent of this finding is dependent on the size of studied sample; therefore underpowered studies might produce results with false spatial localization.

Analysis of actigraph parameters for relapse prediction in bipolar disorder: a feasibility study.

The paper presents a framework for early identification of prodromal syndromes od mania or depression in bipolar disorder. The framework may mitigate relapses and improve patient functioning. The methodology consists of long-term actigraphy monitoring and simplified self-assessment tool to determine manic or depression events. Eight patients were involved in the feasibility study, spanning period of 150 months, resulting in 17 relapses and 3 hospitalizations in total. We concluded that the most promising parameter extracted from actigraphy recording is a circadian rhythm's interdaily stability. Using developed trend analysis applied on interdaily stability parameter, we achieved sensitivity and specificity about 65, resp. 68. We hypothesized that this performance is both mainly due to missing values in data and due to small amount of relapses.

Subanesthetic dose of ketamine decreases prefrontal theta cordance in healthy volunteers: implications for antidepressant effect.

BACKGROUND: Theta cordance is a novel quantitative electroencephalography (QEEG) measure that correlates with cerebral perfusion. A series of clinical studies has demonstrated that the prefrontal theta cordance value decreases after 1 week of treatment in responders to antidepressants and that this effect precedes clinical improvement. Ketamine, a non-competitive antagonist of N-methyl-D-aspartate (NMDA) receptors, has a unique rapid antidepressant effect but its influence on theta cordance is unknown. METHOD: In a double-blind, cross-over, placebo-controlled experiment we studied the acute effect of ketamine (0.54 mg/kg within 30 min) on theta cordance in a group of 20 healthy volunteers. RESULTS: Ketamine infusion induced a decrease in prefrontal theta cordance and an increase in the central region theta cordance after 10 and 30 min. The change in prefrontal theta cordance correlated with ketamine and norketamine blood levels after 10 min of ketamine infusion. CONCLUSIONS: Our data indicate that ketamine infusion immediately induces changes similar to those that monoamineric-based antidepressants induce gradually. The reduction in theta cordance could be a marker and a predictor of the fast-acting antidepressant effect of ketamine, a hypothesis that could be tested in depressive patients treated with ketamine.

The Information Technology Aided Relapse Prevention Programme in Schizophrenia: an extension of a mirror-design follow-up.

AIMS: Decreasing a number of hospital admissions is important for improving outcomes for people with schizophrenia. The Information Technology Aided Relapse Prevention Programme in Schizophrenia (ITAREPS) programme enables early pharmacological intervention in psychosis by identification of prodromal symptoms of relapse using home telemonitoring via a phone-to-PC SMS platform. METHODS: This study was a 1-year extension of a previously published mirror-design follow-up evaluation of programme clinical effectiveness. In total, 73 patients with psychotic illness (45 patients from original sample and 28 newly added subjects) collaborating with 56 family members participated in the clinical evaluation. RESULTS: There was a statistically significant 77% decrease in the number of hospitalisations during the mean 396.8 +/- 249.4 days of participation in ITAREPS, compared with the same time period before participation in ITAREPS (Wilcoxon-signed ranks test, p < 0.00001), as well as significantly reduced number of hospitalisation days when in the ITAREPS (2365 hospitalisation days before and 991 days after ITAREPS enrolment respectively, Wilcoxon-signed ranks test, p < 0.003). CONCLUSION: The ITAREPS programme represents an effective tool in the long-term treatment of patients with psychotic disorders.

The effect of tryptophan depletion on brain activation measured by functional magnetic resonance imaging during the Stroop test in healthy subjects.

We investigated the role of serotonin in cognitive activation of the frontal cortex. The serotonergic system was affected by the administration of an amino acids mixture without tryptophan (tryptophan depletion). In a placebo-controlled double-blind cross-over study with 20 healthy volunteers, we tested the hypothesis that a tryptophan (serotonin) decrease affects the activation of prefrontal cortex by the Stroop test. Cognitive brain activation was evaluated by functional magnetic resonance imaging (fMRI). Tryptophan depletion decreased the plasma tryptophan level up to 90 % for five hours after the tryptophan-free drink had been consumed when compared with the same mixture with tryptophan (p?0.0001). Tryptophan depletion did not affect the Stroop test performance. We compared fMRI activation in both conditions (tryptophan depletion and placebo) with plasma tryptophan levels as the covariates. The tryptophan depletion increased the activation (fMRI signal) in the bilateral mediofrontal cortex, anterior cingulate and left dorsolateral prefrontal cortex. The present findings allow the postulate that serotonergic medial forebrain and cingulum bundle pathways play a role in the activity of cortical structures involved in Stroop test processing.

Differences in fMRI and MRS in a monozygotic twin pair discordant for schizophrenia (case report).

OBJECTIVE: This paper presents functional magnetic resonance imaging (fMRI) and magnetic resonance spectroscopy (MRS) findings in a monozygotic twin pair discordant for schizophrenia. METHOD: Functional magnetic resonance imaging was used to determine hemispheric lateralization for speech and proton MRS (1H-MRS) was employed to assess the extent of putative insult to anterior hippocampus. RESULTS: Despite concordant right handedness, subject with schizophrenia displayed bilateral activation in areas subserving speech with greater extent of the total activated area compared with the healthy twin. The affected twin displayed relative bilateral decrease in N-acetylaspartate/creatin concentration in the anterior hippocampus compared with the healthy one. CONCLUSION: This is an evidence for non-genetic impairment of cerebral lateralization in monozygotic twin with schizophrenia.