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.

Automated cortical thickness and skewness feature selection in bipolar disorder using a semi-supervised learning method.

BACKGROUND: Bipolar disorder (BD) broadly affects brain structure, in particular areas involved in emotion processing and cognition. In the last years, the psychiatric field's interest in machine learning approaches has been steadily growing, thanks to the potentiality of automatically discriminating patients from healthy controls. METHODS: In this work, we employed cortical thickness of 58 regions of interest obtained from magnetic resonance imaging scans of 41 BD patients and 34 healthy controls, to automatically identify the regions which are mostly involved with the disease. We used a semi-supervised method, addressing the criticisms on supervised methods, related to the fact that the diagnosis is not unaffected by uncertainty. RESULTS: Our results confirm findings in previous studies, with a classification accuracy of about 75% when mean thickness and skewness of up to five regions are considered. We obtained that the parietal lobe and some areas in the temporal sulcus were the regions which were the most involved with BD. LIMITATIONS: The major limitation of our work is the limited size or our dataset, but in line with other recent machine learning works in the field. Moreover, we considered chronic patients, whose brain characteristics may thus be affected. CONCLUSIONS: The automatic selection of the brain regions most involved in BD may be of great importance when dealing with the pathogenesis of the disorder. Our method selected regions which are known to be involved with BD, indicating that damage to the identified areas can be considered as a marker of disease.

Association of increased genotypes risk for bipolar disorder with brain white matter integrity investigated with tract-based spatial statistics: Special Section on "Translational and Neuroscience Studies in Affective Disorders". Section Editor, Maria Nobile MD, PhD. This Section of JAD focuses on the relevance of translational and neuroscience studies in providing a better understanding of the neural basis of affective disorders. The main aim is to briefly summarise relevant research findings in clinical neuroscience with particular regards to specific innovative topics in mood and anxiety disorders.

BACKGROUND: Diffusion tensor imaging (DTI) studies, which allow the in-vivo investigation of brain tissue integrity, have shown that bipolar disorder (BD) patients present signs of white matter dysconnectivity. In parallel, genome-wide association studies (GWAS) identified several risk genetic variants for BD. I METHODS: In this mini-review, we summarized DTI studies coupling tract-based spatial statistics (TBSS), a reliable technique exploring white matter axon bundles, and genetics in BD. We performed a bibliographic search on PUBMED, using the search terms "TBSS", "genetics", "genome", "genes", "polymorphism", "bipolar disorder". RESULTS: Ten studies met these inclusion criteria. ANK3 and ZNF804A polymorphisms have shown the most consistent results, with the risk alleles showing abnormal white matter integrity in patients with BD. LIMITATIONS: Current studies are limited by the investigation of single SNPs in small and chronically treated samples. CONCLUSIONS: Most considered TBSS-DTI studies found associations between decreased white matter integrity and genetic risk variants. These results suggest an involvement of dysmyelination in the pathogenesis of BD. The combination of TBSS with genotyping can be powerful to unveil the role of white matter in BD, in conjunction with risk genes. Future DTI studies should combine TBSS and GWAS in large populations of drug-free or minimally treated patients with BD at the onset of the disease.

A review of altered biochemistry in the anterior cingulate cortex of first-episode psychosis.

Relevant biochemicals of the brain can be quantified in vivo, non-invasively, using proton Magnetic Resonance Spectroscopy (¹H MRS). This includes metabolites associated with neural general functioning, energetics, membrane phospholipid metabolism and neurotransmission. Moreover, there is substantial evidence of implication of the frontal and prefrontal areas in the pathogenesis of psychotic disorders such as schizophrenia. In particular, the anterior cingulate cortex (ACC) plays an important role in cognitive control of emotional and non-emotional processes. Thus the study of its extent of biochemistry dysfunction in the early stages of psychosis is of particular interest in gaining a greater understanding of its aetiology. In this review, we selected ¹H MRS studies focused on the ACC of first-episode psychosis (FEP). Four studies reported increased glutamatergic levels in FEP, while other four showed preserved concentrations. Moreover, findings on FEP do not fully mirror those in chronic patients. Due to conflicting findings, larger longitudinal ¹H MRS studies are expected to further explore glutamatergic neurotransmission in ACC of FEP in order to have a better understanding of the glutamatergic mechanisms underlying psychosis, possibly using ultra high field MR scanners.

Progressive disability and prefrontal shrinkage in schizophrenia patients with poor outcome: A 3-year longitudinal study.

INTRODUCTION: Schizophrenia is a severe disabling disorder with heterogeneous illness courses. In this longitudinal study we characterized schizophrenia patients with poor and good outcome (POS, GOS), using functional and imaging metrics. Patients were defined in accordance to Keefe's criteria (i.e. Kraepelinian and non-Kraepelinian patients). METHODS: 35 POS patients, 35 GOS patients and 76 healthy controls (H) underwent clinical, functioning and magnetic resonance imaging (MRI) assessments twice over three years of follow-up. Information on psychopathology, treatment, disability (using the World Health Organization Disability Assessment Scale II, WHO-DAS-2) and prefrontal morphology was collected. Dorsolateral prefrontal cortex (DLPFC) and orbitofrontal cortex (OFC) were manually traced. RESULTS: At baseline, subjects with POS showed significantly decreased right dorsolateral prefrontal cortex (DLPFC) white matter volumes (WM) compared to healthy controls and GOS patients (POS VS HC, p<0.001; POS vs GOS, p=0.03), with shrinkage of left DLPFC WM volumes at follow up (t=2.66, p=0.01). Also, POS patients had higher disability in respect to GOS subjects both at baseline and after 3years at the WHO-DAS-2 (p<0.05). DISCUSSION: Our study supports the hypothesis that POS is characterized by progressive deficits in brain structure and in "real-life" functioning. These are particularly notable in the DLPFC.

Twin studies for the investigation of the relationships between genetic factors and brain abnormalities in bipolar disorder.

The pathogenesis of bipolar disorder (BD) is to date not entirely clear. Classical genetic research showed that there is a contribution of genetic factors in BD, with high heritability. Twin studies, thanks to the fact that confounding factors as genetic background or family environment are shared, allow etiological inferences. In this work, we selected twin studies, which focus on the relationship between BD, genetic factors and brain structure, evaluated with magnetic resonance imaging. All the studies found differences in brain structure between BD patients and their co-twins, and also in respect to healthy controls. Genetic effects are predominant in white matter, except corpus callosum, while gray matter resulted more influenced by environment, or by the disease itself. All studies found no interactions between BD and shared environment between twins. Twin studies have been demonstrated to be useful in exploring BD pathogenesis and could be extremely effective at discriminating the neural mechanisms underlying BD.