Static and Dynamic Dysconnectivity in Early Psychosis: Relationship With Symptom Dimensions.

BACKGROUND AND HYPOTHESIS: Altered functional connectivity (FC) has been frequently reported in psychosis. Studying FC and its time-varying patterns in early-stage psychosis allows the investigation of the neural mechanisms of this disorder without the confounding effects of drug treatment or illness-related factors. STUDY DESIGN: We employed resting-state functional magnetic resonance imaging (rs-fMRI) to explore FC in individuals with early psychosis (EP), who also underwent clinical and neuropsychological assessments. 96 EP and 56 demographically matched healthy controls (HC) from the Human Connectome Project for Early Psychosis database were included. Multivariate analyses using spatial group independent component analysis were used to compute static FC and dynamic functional network connectivity (dFNC). Partial correlations between FC measures and clinical and cognitive variables were performed to test brain-behavior associations. STUDY RESULTS: Compared to HC, EP showed higher static FC in the striatum and temporal, frontal, and parietal cortex, as well as lower FC in the frontal, parietal, and occipital gyrus. We found a negative correlation in EP between cognitive function and FC in the right striatum FC (pFWE = 0.009). All dFNC parameters, including dynamism and fluidity measures, were altered in EP, and positive symptoms were negatively correlated with the meta-state changes and the total distance (pFWE = 0.040 and pFWE = 0.049). CONCLUSIONS: Our findings support the view that psychosis is characterized from the early stages by complex alterations in intrinsic static and dynamic FC, that may ultimately result in positive symptoms and cognitive deficits.

Neuropsychological performance in women at risk of postpartum depression and postpartum psychosis.

PURPOSE: While neuropsychological deficits are commonly observed in affective and psychotic disorders, this remains unexplored in these disorders when they occur during pregnancy and the postpartum period. METHODS: A neuropsychological test battery was administered to women defined at risk of postpartum depression (PD, N = 53) because having either a current or past diagnosis of major depressive disorder, women at risk of postpartum psychosis (PP, N = 43) because of a diagnosis of bipolar disorder or schizoaffective disorder and/or a previous episode of PP and women not at risk (NR, N = 48) in the third trimester of pregnancy. Generalized and specific cognitive abilities were compared between groups. RESULTS: Women at risk of PP presented worse executive functions and processing speed compared to NR and worse performance compared to women at risk of PD across all cognitive domains. In addition, women at risk of PP who developed a psychiatric relapse in the first four weeks post-partum showed worse verbal learning and memory, visual memory, executive functions and processing speed in pregnancy compared to NR, whereas women at risk of PP who remained well presented neuropsychological performance that was intermediate between that of the women NR and those at risk of PP who developed symptoms. There were no differences in performance between women at risk of PD and the NR women, even if 31 women at risk of PD presented depressive symptoms at the time of cognitive assessment. CONCLUSIONS: Our findings in women at risk of PP align with neuropsychological findings in individuals with, or at risk of psychosis unrelated to pregnancy. In addition, initial evidence that women at risk of PP who develop a psychiatric relapse in the postpartum show a particularly poor neuropsychological performance in pregnancy suggests that this could be considered part of a phenotype for the disease and help guiding future preventive strategies in this clinical population. In women at risk of PD, the presence of depressive symptoms did not influence cognitive performance.

Resting-state functional magnetic resonance imaging alterations in first-degree relatives of individuals with bipolar disorder: A systematic review.

BACKGROUND: Relatives of individuals with bipolar disorder (BD) are at higher risk of developing the disorder. Identifying brain alterations associated with familial vulnerability in BD can help discover endophenotypes, which are quantifiable biological traits more prevalent in unaffected relatives of BD (BD-RELs) than the general population. This review aimed at expanding our knowledge on endophenotypes of BD by providing an overview of resting-state functional magnetic resonance imaging (rs-fMRI) alterations in BD-RELs. METHODS: A systematic search of PubMed, Scopus, and Web of Science was performed to identify all available rs-fMRI studies conducted in BD-RELs up to January 2024. A total of 18 studies were selected. Six included BD-RELs with no history of psychiatric disorders and 10 included BD-RELs that presented psychiatric disorders. Two investigations examined rs-fMRI alterations in BD-RELs with and without subthreshold symptoms for BD. RESULTS: BD-RELs presented rs-fMRI alterations in the cortico-limbic network, fronto-thalamic-striatal circuit, fronto-occipital network, and, to a lesser extent, in the default mode network. This was true both for BD-RELs with no history of psychopathology and for BD-RELs that presented psychiatric disorders. The direct comparison of rs-fMRI alterations in BD-RELs with and without psychiatric symptoms displayed largely non-overlapping patterns of rs-fMRI abnormalities. LIMITATIONS: Small sample sizes and the clinical heterogeneity of BD-RELs limit the generalizability of our findings. CONCLUSIONS: The current literature suggests that first-degree BD-RELs exhibit rs-fMRI alterations in brain circuits involved in emotion regulation, cognition, reward processing, and psychosis susceptibility. Future studies are needed to validate these findings and to explore their potential as biomarkers for early detection and intervention.

Machine learning applied to the prediction of relapse, hospitalization, and suicide in bipolar disorder using neuroimaging and clinical data: A systematic review.

BACKGROUND: Bipolar disorder (BD) is associated with increased morbidity/mortality. Adverse outcome prediction might help with the management of patients with BD. METHODS: We systematically reviewed the performance of machine learning (ML) studies in predicting adverse outcomes (relapse or recurrence, hospital admission, and suicide-related events) in patients with BD. Demographic, clinical, and neuroimaging-related poor outcome predictors were also reviewed. Three databases (PubMed, Scopus, and Web of Science) were explored from inception to July 2023. RESULTS: Eighteen studies, accounting for >30,000 patients, were included. Support vector machine, decision trees, random forest, and logistic regression were the most frequently used ML algorithms. ML models' area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, and specificity ranged from 0.71 to 0.98, 72.7-92.8 %, and 59.0-95.2 % for relapse/recurrence prediction (4 studies (3 on relapses and 1 on recurrences). The corresponding values were 0.78-0.88, 21.4-100 %, and 77.0-99.7 % for hospital admissions (3 studies, 21,266 patients), and 0.71-0.99, 44.4-97.9 %, and 38.9-95.0 % for suicide-related events (10 studies, 5558 patients). Also, one study addressed a combination of the interest outcomes. Adverse outcome predictors included early onset BD, BD type I, comorbid psychiatric or substance use disorder, circadian rhythm disruption, hospitalization characteristics, and neuroimaging parameters, including increased dynamic amplitude of low-frequency fluctuation, decreased frontolimbic functional connectivity and aberrant dynamic functional connectivity in corticostriatal circuitry. CONCLUSIONS: ML models can predict adverse outcomes of BD with relatively acceptable performance measures. Future studies with larger samples and nested cross-validation validation should be conducted to reach more reliable results.

Perioperative esketamine administration for prevention of postpartum depression after the cesarean section: A systematic review and meta-analysis.

BACKGROUND: Postpartum Depression (PPD) exerts a substantial negative effect on maternal well-being post-delivery, particularly among Cesarean Section (C/S) recipients. In this study, we aimed to review the efficacy of perioperative esketamine, the S-enantiomer of ketamine, in preventing PPD incidence and depressive symptoms as measured with the Edinburgh Postnatal Depression Scale (EPDS) after C/S. METHODS: A systematic search for relevant articles was conducted in Scopus, PubMed, Web of Sciences, and PsycINFO until April 6, 2024. Meta-analyses were conducted using random-effect models to compare the PPD incidence and EPDS scores via log odds ratio and Hedge's g, respectively, during the first week post-C/S and at 42 days post-C/S in the esketamine and control group. RESULTS: Fourteen studies, including 12 randomized controlled trials and 2 retrospective cohorts, were reviewed. Our meta-analyses found lower PPD incidence during the first week (log odds ratio: -0.956 [95 % confidence interval: -1.420, -0.491]) and at day 42 post-C/S (log odds ratio: -0.989 [95 % confidence interval: -1.707, -0.272]) among patients administered esketamine compared to controls. Additionally, EPDS scores for the esketamine group were significantly lower than controls during the first week (Hedge's g: -0.682 [95 % confidence interval: -1.088, -0.276]) and at day 42 post-C/S (Hedge's g: -0.614 [95 % confidence interval: -1.098, -0.129]). LIMITATIONS: Presence of various concomitant medications and heterogeneous study designs. CONCLUSION: Our review highlights the potential impact of esketamine in PPD prevention, as well as in alleviating depressive symptoms post-C/S, regardless of PPD occurrence, therefore suggesting the benefits of adding esketamine to peri-C/S analgesic regimen.

Diagnostic value of regional homogeneity and fractional amplitude of low-frequency fluctuations in the classification of schizophrenia and bipolar disorders.

Schizophrenia (SCZ) and bipolar disorders (BD) show significant neurobiological and clinical overlap. In this study, we wanted to identify indexes of intrinsic brain activity that could differentiate these disorders. We compared the diagnostic value of the fractional amplitude of low-frequency fluctuations (fALFF) and regional homogeneity (ReHo) estimated from resting-state functional magnetic resonance imaging in a support vector machine classification of 59 healthy controls (HC), 40 individuals with SCZ, and 43 individuals with BD type I. The best performance, measured by balanced accuracy (BAC) for binary classification relative to HC was achieved by a stacking model (87.4% and 90.6% for SCZ and BD, respectively), with ReHo performing better than fALFF, both in SCZ (86.2% vs. 79.4%) and BD (89.9% vs. 76.9%). BD were better differentiated from HC by fronto-temporal ReHo and striato-temporo-thalamic fALFF. SCZ were better classified from HC using fronto-temporal-cerebellar ReHo and insulo-tempo-parietal-cerebellar fALFF. In conclusion, we provided evidence of widespread aberrancies of spontaneous activity and local connectivity in SCZ and BD, demonstrating that ReHo features exhibited superior discriminatory power compared to fALFF and achieved higher classification accuracies. Our results support the complementarity of these measures in the classification of SCZ and BD and suggest the potential for multivariate integration to improve diagnostic precision.

Effects of antidepressants on brain structure and function in patients with obsessive-compulsive disorder: A review of neuroimaging studies.

Obsessive-compulsive disorder (OCD) affects 2-3% of people worldwide. Although antidepressants are the standard pharmachological treatment of OCD, their effect on the brain of individuals with OCD has not yet been fully clarified. We conducted a systematic search on PubMed, Scopus, Embase, and Web of Science to explore the effects of antidepressants on neuroimaging findings in OCD. Thirteen neuroimaging investigations were included. After antidepressant treatment, structural magnetic resonance imaging studies suggested thalamic, amygdala, and pituitary volume changes in patients. In addition, the use of antidepressants was associated with alterations in diffusion tensor imaging metrics in the left striatum, the right midbrain, and the posterior thalamic radiation in the right parietal lobe. Finally, functional magnetic resonance imaging highlighted possible changes in the ventral striatum, frontal, and prefrontal cortex. The small number of included studies and sample sizes, short durations of follow-up, different antidepressants, variable regions of interest, and heterogeneous samples limit the robustness of the findings of the present review. In conclusion, our review suggests that antidepressant treatment is associated with brain changes in individuals with OCD, and these results may help to deepen our knowledge of the pathophysiology of OCD and the brain mechanisms underlying the effects of antidepressants.

Machine Learning for prediction of violent behaviors in schizophrenia spectrum disorders: a systematic review.

Background: Schizophrenia spectrum disorders (SSD) can be associated with an increased risk of violent behavior (VB), which can harm patients, others, and properties. Prediction of VB could help reduce the SSD burden on patients and healthcare systems. Some recent studies have used machine learning (ML) algorithms to identify SSD patients at risk of VB. In this article, we aimed to review studies that used ML to predict VB in SSD patients and discuss the most successful ML methods and predictors of VB. Methods: We performed a systematic search in PubMed, Web of Sciences, Embase, and PsycINFO on September 30, 2023, to identify studies on the application of ML in predicting VB in SSD patients. Results: We included 18 studies with data from 11,733 patients diagnosed with SSD. Different ML models demonstrated mixed performance with an area under the receiver operating characteristic curve of 0.56-0.95 and an accuracy of 50.27-90.67% in predicting violence among SSD patients. Our comparative analysis demonstrated a superior performance for the gradient boosting model, compared to other ML models in predicting VB among SSD patients. Various sociodemographic, clinical, metabolic, and neuroimaging features were associated with VB, with age and olanzapine equivalent dose at the time of discharge being the most frequently identified factors. Conclusion: ML models demonstrated varied VB prediction performance in SSD patients, with gradient boosting outperforming. Further research is warranted for clinical applications of ML methods in this field.

The functional connectivity of the right superior temporal gyrus is associated with psychological risk and resilience factors for suicidality.

INTRODUCTION: Suicide attempters show increased activation in the right superior temporal gyrus (rSTG). Here, we investigated the rSTG functional connectivity (FC) to identify a functional network involved in suicidality and its associations with psychological suicidality risk and resilience factors. METHODS: The resting state functional magnetic resonance imaging data of 151 healthy individuals from the Human Connectome Project Young Adult database were used to explore the FC of the rSTG with itself and with the rest of the brain. The correlation between the rSTG FC and loneliness and purpose in life scores was assessed with the NIH Toolbox. The effect of sex was also investigated. RESULTS: The rSTG had a positive FC with bilateral cortical and subcortical regions, including frontal, temporal, parietal, occipital, limbic, and cerebellar regions, and a negative FC with the medulla oblongata. The FC of the rSTG with itself and with the left central operculum were associated with loneliness scores. The within rSTG FC was also negatively correlated with purpose in life scores, although at a trend level. We did not find any effect of sex on FC and its associations with psychological factors. LIMITATIONS: The cross-sectional design, the limited age range, and the lack of measures of suicidality limit the generalizability of our findings. CONCLUSIONS: The rSTG functional network is associated with loneliness and purpose in life. Together with the existing literature on suicide, this supports the idea that the neural activity of rSTG may contribute to suicidality by modulating risk and resilience factors associated with suicidality.

Cerebellar dysconnectivity in schizophrenia and bipolar disorder is associated with cognitive and clinical variables.

BACKGROUND: Abnormal cerebellar functional connectivity (FC) has been implicated in the pathophysiology of schizophrenia (SCZ) and bipolar disorder (BD). However, the patterns of cerebellar dysconnectivity in these two disorders and their association with cognitive functioning and clinical symptoms have not been fully clarified. In this study, we examined cerebellar FC alterations in SCZ and BD-I and their association with cognition and psychotic symptoms. METHODS: Resting-state functional magnetic resonance imaging (rs-fMRI) data of 39 SCZ, 43 BD-I, and 61 healthy controls from the Consortium for Neuropsychiatric Phenomics dataset were examined. The cerebellum was parcellated into ten functional networks, and seed-based FC was calculated for each cerebellar system. Principal component analyses were used to reduce the dimensionality of the diagnosis-related FC and cognitive variables. Multiple regression analyses were used to assess the relationship between FC and cognitive and clinical data. RESULTS: We observed decreased cerebellar FC with the frontal, temporal, occipital, and thalamic areas in individuals with SCZ, and a more widespread decrease in cerebellar FC in individuals with BD-I, involving the frontal, cingulate, parietal, temporal, occipital, and thalamic regions. SCZ had increased within-cerebellum and cerebellar frontal FC compared to BD-I. In BD-I, memory and verbal learning performances, which were higher compared to SCZ, showed a greater interaction with cerebellar FC patterns. Additionally, patterns of increased cortico-cerebellar FC were marginally associated with positive symptoms in patients. CONCLUSIONS: Our findings suggest that shared and distinct patterns of cortico-cerebellar dysconnectivity in SCZ and BD-I could underlie cognitive impairments and psychotic symptoms in these disorders.

Effects of electroconvulsive therapy on cortical thickness in depression: a systematic review.

OBJECTIVE: Electroconvulsive therapy (ECT) is one of the most studied and validated available treatments for severe or treatment-resistant depression. However, little is known about the neural mechanisms underlying ECT. This systematic review aims to critically review all structural magnetic resonance imaging studies investigating longitudinal cortical thickness (CT) changes after ECT in patients with unipolar or bipolar depression. METHODS: We performed a search on PubMed, Medline, and Embase to identify all available studies published before April 20, 2023. A total of 10 studies were included. RESULTS: The investigations showed widespread increases in CT after ECT in depressed patients, involving mainly the temporal, insular, and frontal regions. In five studies, CT increases in a non-overlapping set of brain areas correlated with the clinical efficacy of ECT. The small sample size, heterogeneity in terms of populations, comorbidities, and ECT protocols, and the lack of a control group in some investigations limit the generalisability of the results. CONCLUSIONS: Our findings support the idea that ECT can increase CT in patients with unipolar and bipolar depression. It remains unclear whether these changes are related to the clinical response. Future larger studies with longer follow-up are warranted to thoroughly address the potential role of CT as a biomarker of clinical response after ECT.

The Therapeutic Role of Intermittent Theta Burst Stimulation in Schizophrenia: A Systematic Review and Meta-analysis.

ABSTRACT: Schizophrenia affects approximately 1% of the population worldwide. Multifactorial reasons, ranging from drug resistance to adverse effects of medications, have necessitated exploring further therapeutic options. Intermittent theta burst stimulation (iTBS) is a novel high-frequency form of transcranial magnetic stimulation, a safe procedure with minor adverse effects with faster and longer-lasting poststimulation effects with a potential role in treating symptoms; however, the exact target brain regions and symptoms are still controversial. Therefore, we aimed to systematically investigate the current literature regarding the therapeutic utilities of iTBS using Preferred Reporting Items for Systematic reviews and Meta-Analyses guidelines. Twelve studies were included among which 9 found iTBS effective to some degree. These studies targeted the dorsolateral prefrontal cortex and the midline cerebellum. We performed a random-effects meta-analysis on studies that compared the effects of iTBS on schizophrenia symptoms measured by the Positive and Negative Syndrome Scale (PANSS) to sham treatment. Our results showed no significant difference between iTBS and sham in PANSS positive and negative scores, but a trend-level difference in PANSS general scores ( k = 6, P = 0.07), and a significant difference in PANSS total scores ( k = 6, P = 0.03). Analysis of the studies targeting the dorsolateral prefrontal cortex showed improvement in PANSS negative scores ( k = 5, standardized mean difference = -0.83, P = 0.049), but not in PANSS positive scores. Moderators (intensity, pulse, quality, sessions) did not affect the results. However, considering the small number of studies included in this meta-analysis, future works are required to further explore the effects of these factors and also find optimum target regions for positive symptoms.

White matter alterations in affective and non-affective early psychosis: A diffusion MRI study.

BACKGROUND: The early years after the onset of psychotic disorders, known as "early psychosis" (EP) are critical to determining the path of psychosis trajectory. We used a Diffusion Magnetic Resonance Imaging (DMRI) connectometry approach to assess the microstructural changes of white matter (WM) associated with EP. METHODS: We used the Human Connectome Project in Early Psychosis (HCP-EP) dataset to collect DMRI data from patients with EP. The imaging data were processed in the Montreal Neuroimaging Initiative space and transformed into quantitative anisotropy (QA). The QA value was translated into the WM connectivity of each tract and used in the subsequent analysis. RESULTS: 121 patients with EP (94 non-affective/27 affective) and 56 healthy controls were recruited. EP was associated with increased QA in the body and tapetum of corpus callosum (CC) and decreased QA in the bilateral cerebellum, and middle cerebellar peduncle. Compared to non-affective psychosis, affective psychosis showed increased QA in the bilateral cerebellum and vermis and decreased QA in the forceps minor, body of CC, right cingulum, and bilateral inferior fronto-occipital fasciculus. Furthermore, QA changes in several WM tracts were correlated with positive and negative symptom scale scores. LIMITATIONS: DMRI intrinsic limitations, limited sample size, and neurobiological effects of psychotropic treatment. CONCLUSIONS: EP is associated with alterations in WM connectivity primarily in the CC and cerebellar regions. Also, affective and non-affective psychosis have distinct alterations in WM connectivity. These results can be used for the early diagnosis and differentiation of psychotic disorders.

Whole-brain structural and functional neuroimaging of individuals who attempted suicide and people who did not: A systematic review and exploratory coordinate-based meta-analysis.

Suicide is the cause of death of approximately 800,000 people a year. Despite the relevance of this behaviour, risk assessment tools rely on clinician experience and subjective ratings. Given that previous suicide attempts are the single strongest predictors of future attempts, we designed a systematic review and coordinate-based meta-analysis to demonstrate whether neuroimaging features can help distinguish individuals who attempted suicide from subjects who did not. Out of 5,659 publications from PubMed, Scopus, and Web of Science, we summarised 102 experiments and meta-analysed 23 of them. A cluster in the right superior temporal gyrus, a region implicated in emotional processing, might be functionally hyperactive in individuals who attempted suicide. No statistically significant differences in brain morphometry were evidenced. Furthermore, we used JuSpace to show that this cluster is enriched in 5-HT1A heteroreceptors in the general population. This exploratory meta-analysis provides a putative neural substrate linked to previous suicide attempts. Heterogeneity in the analytical techniques and weak or absent power analysis of the studies included in this review currently limit the applicability of the findings, the replication of which should be prioritised.

Microstructural white matter alterations associated with social anxiety disorders: A systematic review.

BACKGROUND: Social anxiety disorder (SAD) is a psychiatric condition characterized by impaired social functioning that negatively impacts individuals' quality of life. Previous neuroimaging studies have revealed morphological and functional changes in various brain regions associated with SAD. Recent advances in diffusion tensor imaging (DTI) and diffusion-weighted imaging (DWI) have enabled the investigation of microstructural white matter (WM) alterations in SAD. This study aims to provide an overview of DTI/DWI studies exploring WM microstructure changes in SAD. METHODS: A systematic search on PubMed, Scopus, Web of Science, and PsycINFO was conducted for relevant records on July 8, 2023. An exploratory meta-analysis was also performed. RESULTS: Eight studies were reviewed. Consistent findings indicated reduced fractional anisotropy and increased diffusivity measures in different WM tracts in SAD patients compared to healthy controls. These alterations were mostly observed within regions of the fronto-limbic network, like uncinate fasciculus (UF) and superior and inferior longitudinal fasciculi (SLF and ILF). Finally, our exploratory meta-analysis on four studies utilizing a voxel-wise analytic approach yielded no significant differences between SAD patients and controls. LIMITATIONS: Limited number of studies, small sample sizes, and heterogeneity in analysis methods. CONCLUSIONS: Patients with SAD exhibited altered WM integrity, particularly in the UF, SLF, and ILF, compared to healthy controls. However, due to the limited number of included studies, our meta-analysis yielded no significant differences between SAD patients and controls. Therefore, future research is crucial to unravel the link between altered WM structure and the involvement of other limbic and cortical structures in SAD pathogenesis.

Spontaneous Brain Activity Alterations in First-Episode Psychosis: A Meta-analysis of Functional Magnetic Resonance Imaging Studies.

BACKGROUND AND HYPOTHESIS: Several studies have shown that spontaneous brain activity, including the total and fractional amplitude of low-frequency fluctuations (LFF) and regional homogeneity (ReHo), is altered in psychosis. Nonetheless, neuroimaging results show a high heterogeneity. For this reason, we gathered the extant literature on spontaneous brain activity in first-episode psychosis (FEP), where the effects of long-term treatment and chronic disease are minimal. STUDY DESIGN: A systematic research was conducted on PubMed, Scopus, and Web of Science to identify studies exploring spontaneous brain activity and local connectivity in FEP estimated using functional magnetic resonance imaging. 20 LFF and 15 ReHo studies were included. Coordinate-Based Activation Likelihood Estimation Meta-Analyses stratified by brain measures, age (adolescent vs adult), and drug-naïve status were performed to identify spatially-convergent alterations in spontaneous brain activity in FEP. STUDY RESULTS: We found a significant increase in LFF in FEP compared to healthy controls (HC) in the right striatum and in ReHo in the left striatum. When pooling together all studies on LFF and ReHo, spontaneous brain activity was increased in the bilateral striatum and superior and middle frontal gyri and decreased in the right precentral gyrus and the right inferior frontal gyrus compared to HC. These results were also replicated in the adult and drug-naïve samples. CONCLUSIONS: Abnormalities in the frontostriatal circuit are present in early psychosis independently of treatment status. Our findings support the view that altered frontostriatal can represent a core neural alteration of the disorder and could be a target of treatment.

Machine learning applied to functional magnetic resonance imaging in anxiety disorders.

BACKGROUND: Brain functional abnormalities have been commonly reported in anxiety disorders, including generalized anxiety disorder, social anxiety disorder, panic disorder, agoraphobia, and specific phobias. The role of functional abnormalities in the discrimination of these disorders can be tested with machine learning (ML) techniques. Here, we aim to provide a comprehensive overview of ML studies exploring the potential discriminating role of functional brain alterations identified by functional magnetic resonance imaging (fMRI) in anxiety disorders. METHODS: We conducted a search on PubMed, Web of Science, and Scopus of ML investigations using fMRI as features in patients with anxiety disorders. A total of 12 studies (resting-state fMRI n = 5, task-based fMRI n = 6, resting-state and task-based fMRI n=1) met our inclusion criteria. RESULTS: Overall, the studies showed that, regardless of the classifiers, alterations in functional connectivity and aberrant neural activation involving the amygdala, anterior cingulate cortex, hippocampus, insula, orbitofrontal cortex, temporal pole, cerebellum, default mode network, dorsal attention network, sensory network, and affective network were able to discriminate patients with anxiety from controls, with accuracies spanning from 36 % to 94 %. LIMITATIONS: The small sample size, different ML approaches and heterogeneity in the selection of regions included in the multivariate pattern analyses limit the conclusions of the present review. CONCLUSIONS: ML methods using fMRI as features can distinguish patients with anxiety disorders from healthy controls, indicating that these techniques could be used as a helpful tool for the diagnosis and the development of more targeted treatments for these disorders.

Resting-state functional magnetic resonance imaging alterations in borderline personality disorder: A systematic review.

BACKGROUND: Borderline personality disorder (BPD) is a severe psychiatric disorder characterized by emotion dysregulation, impulsivity, and interpersonal disturbances. Several structural and functional neuroimaging abnormalities have been described in BPD. In particular, resting-state functional magnetic resonance imaging (rs-fMRI) studies have recently suggested various connectivity alterations within and between large-scale brain networks in BPD. This review aimed at providing an updated summary of the evidence reported by the available rs-fMRI studies in BPD individuals. METHODS: A search on PubMed, Scopus, and Web of Science was performed to identify rs-fMRI alterations in BPD. A total of 15 studies met our inclusion criteria. RESULTS: Overall, aberrant resting-state functional connectivity (rs-FC) within and between default mode network (DMN), salience network (SN), and central executive network (CEN) were observed in BPD compared to healthy controls, as well as selective functional impairments in bilateral amygdala, anterior and posterior cingulate cortex, hippocampus, and prefrontal cortex. LIMITATIONS: The observational design, small sample size, prevalence of females, high rates of concurrent comorbidities and medications, and heterogeneity across imaging methodologies limit the generalizability of the results. CONCLUSIONS: The identification of altered patterns of rs-FC within and between selective brain networks, including DMN, SN, and CEN, could further our knowledge of the clinical symptoms of BPD, and therefore, future studies with multimodal methodologies and longitudinal designs are warranted to further explore the neural correlates of this disorder.

The Risk for Schizophrenia-Bipolar Spectrum: Does the Apple Fall Close to the Tree? A Narrative Review.

Schizophrenia (SCZ) and bipolar disorder (BD) are severe psychiatric disorders that share clinical features and several risk genes. Important information about their genetic underpinnings arises from intermediate phenotypes (IPs), quantifiable biological traits that are more prevalent in unaffected relatives (RELs) of patients compared to the general population and co-segregate with the disorders. Within IPs, neuropsychological functions and neuroimaging measures have the potential to provide useful insight into the pathophysiology of SCZ and BD. In this context, the present narrative review provides a comprehensive overview of the available evidence on deficits in neuropsychological functions and neuroimaging alterations in unaffected relatives of SCZ (SCZ-RELs) and BD (BD-RELs). Overall, deficits in cognitive functions including intelligence, memory, attention, executive functions, and social cognition could be considered IPs for SCZ. Although the picture for cognitive alterations in BD-RELs is less defined, BD-RELs seem to present worse performances compared to controls in executive functioning, including adaptable thinking, planning, self-monitoring, self-control, and working memory. Among neuroimaging markers, SCZ-RELs appear to be characterized by structural and functional alterations in the cortico-striatal-thalamic network, while BD risk seems to be associated with abnormalities in the prefrontal, temporal, thalamic, and limbic regions. In conclusion, SCZ-RELs and BD-RELs present a pattern of cognitive and neuroimaging alterations that lie between patients and healthy individuals. Similar abnormalities in SCZ-RELs and BD-RELs may be the phenotypic expression of the shared genetic mechanisms underlying both disorders, while the specificities in neuropsychological and neuroimaging profiles may be associated with the differential symptom expression in the two disorders.

Classification of suicidality by training supervised machine learning models with brain MRI findings: A systematic review.

BACKGROUND: Suicide is a global public health issue causing around 700,000 deaths worldwide each year. Therefore, identifying suicidal thoughts and behaviors in patients can help lower the suicide-related mortality rate. This review aimed to investigate the feasibility of suicidality identification by applying supervised Machine Learning (ML) methods to Magnetic Resonance Imaging (MRI) data. METHODS: We conducted a systematic search on PubMed, Scopus, and Web of Science to identify studies examining suicidality by applying ML methods to MRI features. Also, the Prediction Model Risk of Bias Assessment Tool (PROBAST) was employed for the quality assessment. RESULTS: 23 studies met the inclusion criteria. Of these, 20 developed prediction models without external validation and 3 developed prediction models with external validation. The performance of ML models varied among the reviewed studies, with the highest reported values of accuracies and Area Under the Curve (AUC) ranging from 51.7 % to 100 % and 0.52 to 1, respectively. Over half of the studies that reported accuracy (12/21) or AUC (13/16) achieved values of ≥0.8. Our comparative analysis indicated that deep learning exhibited the highest predictive performance compared to other ML models. The most commonly identified discriminative imaging features were resting-state functional connectivity and grey matter volume within prefrontal-limbic structures. LIMITATIONS: Small sample sizes, lack of external validation, heterogeneous study designs, and ML model development. CONCLUSIONS: Most of the studies developed ML models capable of ML-based suicide identification, although ML models' predictive performance varied across the reviewed studies. Thus, further well-designed is necessary to uncover the true potential of different ML models in this field.