Characterizing functional regional homogeneity (ReHo) as a B-SNIP psychosis biomarker using traditional and machine learning approaches

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Unique functional neuroimaging signatures of genetic versus clinical high risk for psychosis

BACKGROUND

22q11.2 Deletion Syndrome (22qDel) is a copy number variant (CNV) associated with psychosis and other neurodevelopmental disorders. Adolescents at clinical high risk for psychosis (CHR) are identified based on the presence of subthreshold psychosis symptoms. Whether common neural substrates underlie these distinct high-risk populations is unknown. We compared functional brain measures in 22qDel and CHR cohorts and mapped results to biological pathways.

METHODS

We analyzed two large multi-site cohorts with resting-state functional MRI (rs-fMRI): 1) 22qDel (n=164, 47% female) and typically developing (TD) controls (n=134, 56% female); 2) CHR individuals (n=244, 41% female) and TD controls (n=151, 46% female) from the North American Prodrome Longitudinal Study-2. We computed global brain connectivity (GBC), local connectivity (LC), and brain signal variability (BSV) across cortical regions, testing case-control differences for 22qDel and CHR separately. Group difference maps were related to published brain maps using autocorrelation-preserving permutation.

RESULTS

BSV, LC, and GBC are significantly disrupted in 22qDel compared with TD controls (False Discovery Rate q<0.05). Spatial maps of BSV and LC differences are highly correlated with each other, unlike GBC. In CHR, only LC is significantly altered versus controls, with a different spatial pattern compared to 22qDel. Group differences map onto biological gradients, with 22qDel effects strongest in regions with high predicted blood flow and metabolism.

CONCLUSION

22qDel and CHR exhibit divergent effects on fMRI temporal variability and multi-scale functional connectivity. In 22qDel, strong and convergent disruptions in BSV and LC not seen in CHR individuals suggest distinct functional brain alterations.

Bridging Neurobiological Insights and Clinical Biomarkers in Postpartum Depression: A Narrative Review

Postpartum depression (PPD) affects 174 million women worldwide and is characterized by profound sadness, anxiety, irritability, and debilitating fatigue, which disrupt maternal caregiving and the mother-infant relationship. Limited pharmacological interventions are currently available. Our understanding of the neurobiological pathophysiology of PPD remains incomplete, potentially hindering the development of novel treatment strategies. Recent hypotheses suggest that PPD is driven by a complex interplay of hormonal changes, neurotransmitter imbalances, inflammation, genetic factors, psychosocial stressors, and hypothalamic-pituitary-adrenal (HPA) axis dysregulation. This narrative review examines recent clinical studies on PPD within the past 15 years, emphasizing advancements in neuroimaging findings and blood biomarker detection. Additionally, we summarize recent laboratory work using animal models to mimic PPD, focusing on hormone withdrawal, HPA axis dysfunction, and perinatal stress theories. We also revisit neurobiological results from several brain regions associated with negative emotions, such as the amygdala, prefrontal cortex, hippocampus, and striatum. These insights aim to improve our understanding of PPD's neurobiological mechanisms, guiding future research for better early detection, prevention, and personalized treatment strategies for women affected by PPD and their families.

Beyond average outcomes: A latent profile analysis of diverse developmental trajectories in preterm and early term-born children from the Adolescent Brain Cognitive Development study

Preterm birth poses a major public health challenge, with significant and heterogeneous developmental impacts. Latent profile analysis was applied to the National Institutes of Health Toolbox performance of 1891 healthy prematurely born children from the Adolescent Brain and Cognitive Development study (970 boys, 921 girls; 10.00 ± 0.61 years; 1.3% Asian, 13.7% Black, 17.5% Hispanic, 57.0% White, 10.4% Other). Three distinct neurocognitive profiles emerged: consistently performing above the norm (19.7%), mixed scores (41.0%), and consistently performing below the norm (39.3%). These profiles were associated with lasting cognitive, neural, behavioral, and academic differences. These findings underscore the importance of recognizing diverse developmental trajectories in prematurely born children, advocating for personalized diagnosis and intervention to enhance care strategies and long-term outcomes for this heterogeneous population.

Unraveling multi-scale neuroimaging biomarkers and molecular foundations for schizophrenia: A combined multivariate pattern analysis and transcriptome-neuroimaging association study

AIMS

Schizophrenia is characterized by alterations in resting-state spontaneous brain activity; however, it remains uncertain whether variations at diverse spatial scales are capable of effectively distinguishing patients from healthy controls. Additionally, the genetic underpinnings of these alterations remain poorly elucidated. We aimed to address these questions in this study to gain better understanding of brain alterations and their underlying genetic factors in schizophrenia.

METHODS

A cohort of 103 individuals with diagnosed schizophrenia and 110 healthy controls underwent resting-state functional MRI scans. Spontaneous brain activity was assessed using the regional homogeneity (ReHo) metric at four spatial scales: voxel-level (Scale 1) and regional-level (Scales 2-4: 272, 53, 17 regions, respectively). For each spatial scale, multivariate pattern analysis was performed to classify schizophrenia patients from healthy controls, and a transcriptome-neuroimaging association analysis was performed to establish connections between gene expression data and ReHo alterations in schizophrenia.

RESULTS

The ReHo metrics at all spatial scales effectively discriminated schizophrenia from healthy controls. Scale 2 showed the highest classification accuracy at 84.6%, followed by Scale 1 (83.1%) and Scale 3 (78.5%), while Scale 4 exhibited the lowest accuracy (74.2%). Furthermore, the transcriptome-neuroimaging association analysis showed that there were not only shared but also unique enriched biological processes across the four spatial scales. These related biological processes were mainly linked to immune responses, inflammation, synaptic signaling, ion channels, cellular development, myelination, and transporter activity.

CONCLUSIONS

This study highlights the potential of multi-scale ReHo as a valuable neuroimaging biomarker in the diagnosis of schizophrenia. By elucidating the complex molecular basis underlying the ReHo alterations of this disorder, this study not only enhances our understanding of its pathophysiology, but also pave the way for future advancements in genetic diagnosis and treatment of schizophrenia.

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.

Neurometabolic and Brain Functional Alterations Associated with Cognitive Impairment in Patients with Myasthenia Gravis: A Combined 1H-MRS and fMRI Study

Whether patients with myasthenia gravis (MG) exhibit cognitive impairment is controversial. Also the underlying mechanisms are unknown. We aimed to investigate alterations in cognitive function, neurometabolite levels, and brain function in patients with MG and to explore the associations between abnormal regional brain functional activity, neurometabolite concentrations in the MPFC and left thalamus, and cognitive activity in patients with MG. Neuropsychological tests, proton magnetic resonance spectroscopy, and resting-state functional magnetic resonance imaging were performed on 41 patients with MG and 45 race-, sex-, age-, and education-matched healthy controls (HCs). The results suggest that MG is accompanied by cognitive decline, as indicated by global cognitive function, visual-spatial function, language, memory, abnormalities in regional brain functional activity, and neurometabolite alterations (including GABA, NAA, and Cho) in the medial prefrontal cortex (MPFC) and left thalamus. Cognitive impairment in patients with MG may be related to abnormal regional brain functional activity and changes in neurometabolites, and regional brain functional activity may be modulated by specific neurometabolites.

Identifying psychosis subtypes use individualized covariance structural differential networks and multi-site clustering

BACKGROUND

Similarities among schizophrenia (SZ), schizoaffective disorder (SAD) and bipolar disorder (BP) including clinical phenotypes, brain alterations and risk genes, make it challenging to perform reliable separation among them. However, previous subtype identification that transcend traditional diagnostic boundaries were based on group-level neuroimaging features, ignoring individual-level inferences.

METHODS

455 psychoses (178 SZs, 134 SADs and 143 BPs), their first-degree relatives (N = 453) and healthy controls (HCs, N = 220) were collected from Bipolar-Schizophrenia Network on Intermediate Phenotypes (B-SNIP I) consortium. Individualized covariance structural differential networks (ICSDNs) were constructed for each patient and multi-site clustering was used to identify psychosis subtypes. Group differences between subtypes in clinical phenotypes and voxel-wise fractional amplitude of low frequency fluctuation (fALFF) were calculated, as well as between the corresponding relatives.

RESULTS

Two psychosis subtypes were identified with increased whole brain structural covariance, with decreased connectivity between amygdala-hippocampus and temporal-occipital cortex in subtype I (S-I) compared to subtype II (S-II), which was replicated under different clustering methods, number of edges and across datasets (B-SNIP II) and different brain atlases. S-I had higher emotional-related symptoms than S-II and showed significant fALFF decrease in temporal and occipital cortex, while S-II was more similar to HC. This pattern was consistently validated on relatives of S-I and S-II in both fALFF and clinical symptoms.

CONCLUSIONS

These findings reconcile categorical and dimensional perspectives of psychosis neurobiological heterogeneity, indicating that relatives of S-I might have greater predisposition in developing psychosis, while relatives of S-II are more likely to be healthy. This study contributes to the development of neuroimaging informed diagnostic classifications within psychosis spectrum.

Deep learning-based multimodality classification of chronic mild traumatic brain injury using resting-state functional MRI and PET imaging

Mild traumatic brain injury (mTBI) is a public health concern. The present study aimed to develop an automatic classifier to distinguish between patients with chronic mTBI (n = 83) and healthy controls (HCs) (n = 40). Resting-state functional MRI (rs-fMRI) and positron emission tomography (PET) imaging were acquired from the subjects. We proposed a novel deep-learning-based framework, including an autoencoder (AE), to extract high-level latent and rectified linear unit (ReLU) and sigmoid activation functions. Single and multimodality algorithms integrating multiple rs-fMRI metrics and PET data were developed. We hypothesized that combining different imaging modalities provides complementary information and improves classification performance. Additionally, a novel data interpretation approach was utilized to identify top-performing features learned by the AEs. Our method delivered a classification accuracy within the range of 79-91.67% for single neuroimaging modalities. However, the performance of classification improved to 95.83%, thereby employing the multimodality model. The models have identified several brain regions located in the default mode network, sensorimotor network, visual cortex, cerebellum, and limbic system as the most discriminative features. We suggest that this approach could be extended to the objective biomarkers predicting mTBI in clinical settings.

Hippocampal alterations after SARS-CoV-2 infection: A systematic review

SARS-CoV-2 infection produces a wide range of symptoms. Some of the structural changes caused by the virus in the nervous system are found in the medial temporal lobe, and several neuropsychological sequelae of COVID-19 are related to the function of the hippocampus. The main objective of the systematic review is to update and further analyze the existing evidence of hippocampal and related cortices' structural and functional alterations due to SARS-CoV-2 infection. Both clinical and preclinical studies that used different methodologies to explore the effects of this disease at different stages and grades of severity were considered, besides exploring related cognitive and emotional symptomatology. A total of 24 studies were identified by searching in SCOPUS, Web Of Science (WOS), PubMed, and PsycInfo databases up to October 3rd, 2022. Thirteen studies were performed in clinical human samples, 9 included preclinical animal models, 3 were performed post-mortem, and 1 included both post-mortem and preclinical samples. Alterations in the hippocampus were detected in the acute stage and after several months of infection. Clinical studies revealed alterations in hippocampal connectivity and metabolism. Memory alterations correlated with altered metabolic profiles or changes in grey matter volumes. Hippocampal human postmortem and animal studies observed alterations in neurogenesis, dendrites, and immune response, besides high apoptosis and neuroinflammation. Preclinical studies reported the viral load in the hippocampus. Olfactory dysfunction was associated with alterations in brain functionality. Several clinical studies revealed cognitive complaints, neuropsychological alterations, and depressive and anxious symptomatology.

Applying dimensional psychopathology: transdiagnostic prediction of executive cognition using brain connectivity and inflammatory biomarkers

BACKGROUND

The association between executive dysfunction, brain dysconnectivity, and inflammation is a prominent feature across major psychiatric disorders (MPDs), schizophrenia, bipolar disorder, and major depressive disorder. A dimensional approach is warranted to delineate their mechanistic interplay across MPDs.

METHODS

This single site study included a total of 1543 participants (1058 patients and 485 controls). In total, 1169 participants underwent diffusion tensor and resting-state functional magnetic resonance imaging (745 patients and 379 controls completed the Wisconsin Card Sorting Test). Fractional anisotropy (FA) and regional homogeneity (ReHo) assessed structural and functional connectivity, respectively. Pro-inflammatory cytokine levels [interleukin (IL)-1β, IL-6, and tumor necrosis factor-α] were obtained in 325 participants using blood samples collected with 24 h of scanning. Group differences were determined for main measures, and correlation and mediation analyses and machine learning prediction modeling were performed.

RESULTS

Executive deficits were associated with decreased FA, increased ReHo, and elevated IL-1β and IL-6 levels across MPDs, compared to controls. FA and ReHo alterations in fronto-limbic-striatal regions contributed to executive deficits. IL-1β mediated the association between FA and cognition, and IL-6 mediated the relationship between ReHo and cognition. Executive cognition was better predicted by both brain connectivity and cytokine measures than either one alone for FA-IL-1β and ReHo-IL-6.

CONCLUSIONS

Transdiagnostic associations among brain connectivity, inflammation, and executive cognition exist across MPDs, implicating common neurobiological substrates and mechanisms for executive deficits in MPDs. Further, inflammation-related brain dysconnectivity within fronto-limbic-striatal regions may represent a transdiagnostic dimension underlying executive dysfunction that could be leveraged to advance treatment.

Behavioral and biologic characteristics of cancer-related cognitive impairment biotypes

Psychiatric diagnosis is moving away from symptom-based classification and towards multi-dimensional, biologically-based characterization, or biotyping. We previously identified three biotypes of chemotherapy-related cognitive impairment based on functional brain connectivity. In this follow-up study of 80 chemotherapy-treated breast cancer survivors and 80 non-cancer controls, we evaluated additional factors to help explain biotype expression: neurofunctional stability, brain age, apolipoprotein (APOE) genotype, and psychoneurologic symptoms. We also compared the discriminative ability of a traditional, symptom-based cognitive impairment definition with that of biotypes. We found significant differences in cortical brain age (F = 10.50, p < 0.001), neurofunctional stability (F = 2.83, p = 0.041), APOE e4 genotype (X2 = 7.68, p = 0.050), and psychoneurological symptoms (Pillai = 0.378, p < 0.001) across the three biotypes. The more resilient Biotype 2 demonstrated significantly higher neurofunctional stability compared to the other biotypes. Symptom-based classification of cognitive impairment did not differentiate biologic or other behavioral variables, suggesting that traditional categorization of cancer-related cognitive effects may miss important characteristics which could inform targeted treatment strategies. Additionally, biotyping, but not symptom-typing, was able to distinguish survivors with cognitive versus psychological effects. Our results suggest that Biotype 1 survivors might benefit from first addressing symptoms of anxiety and fatigue, Biotype 3 might benefit from a treatment plan which includes sleep hygiene, and Biotype 2 might benefit most from cognitive skills training or rehabilitation. Future research should include additional demographic and clinical information to further investigate biotype expression related to risk and resilience and examine integration of more clinically feasible imaging approaches.

Abnormal degree centrality can be a potential imaging biomarker in first-episode, drug-naive bipolar mania

Brain network abnormalities in emotional response exist in bipolar mania. However, few studies have been published on network degree centrality of first-episode, drug-naive bipolar mania, and healthy controls. This study aimed to assess the utility of neural activity values analyzed via degree centrality methods. Sixty-six first-episode, drug-naive patients with bipolar mania and 60 healthy controls participated in resting-state functional magnetic resonance rescanning and scale estimating. The degree centrality and receiver operating characteristic (ROC) curve methods were used for an analysis of the imaging data. Relative to healthy controls, first-episode bipolar mania patients displayed increased degree centrality values in the left middle occipital gyrus, precentral gyrus, supplementary motor area, Precuneus, and decreased degree centrality values in the left parahippocampal gyrus, right insula and superior frontal gyrus, medial. ROC results exhibited degree centrality values in the left parahippocampal gyrus that could distinguish first-episode bipolar mania patients from healthy controls with 0.8404 for AUC. Support vector machine results showed that reductions in degree centrality values in the left parahippocampal gyrus can be used to effectively differentiate between bipolar disorder patients and healthy controls with respective accuracy, sensitivity, and specificity values of 83.33%, 85.51%, and 88.41%. Increased activity in the left parahippocampal gyrus may be a distinctive neurobiological feature of first-episode, drug-naive bipolar mania. Degree centrality values in the left parahippocampal gyrus might be served as a potential neuroimaging biomarker to discriminate first-episode, drug-naive bipolar mania patients from healthy controls.

Aberrant resting-state regional activity in patients with postpartum depression

Background

Postpartum depression (PPD) is a common disorder with corresponding cognitive impairments such as depressed mood, memory deficits, poor concentration, and declining executive functions, but little is known about its underlying neuropathology.

Method

A total of 28 patients with PPD and 29 healthy postpartum women were recruited. Resting-state functional magnetic resonance imaging (rs-fMRI) scans were performed in the fourth week after delivery. Individual local activity of PPD patients was observed by regional homogeneity (ReHo) during resting state, and the ReHo value was computed as Kendall's coecient of concordance (KCC) and analyzed for differences between voxel groups. Correlations between ReHo values and clinical variables were also analyzed.

Result

Compared with healthy postpartum women, patients with PPD exhibited significantly higher ReHo values in the left precuneus and right hippocampus. ReHo value was significantly lower in the left dorsolateral prefrontal cortex (dlPFC) and right insula. Furthermore, ReHo values within the dlPFC were negatively correlated with the Edinburgh PPD scale (EPDS) score. The functional connectivity (FC) of the right hippocampus to the left precuneus and left superior frontal gyrus (SFG) was stronger in patients with PPD than that in controls.

Conclusion

The present study provided evidence of aberrant regional functional activity and connectivity within brain regions in PPD, and it may contribute to further understanding of the neuropathology underlying PPD.

Abnormal regional homogeneity and amplitude of low frequency fluctuation in chronic kidney patients with and without dialysis

Purpose

The study characterizes regional homogeneity (ReHo) and amplitude of low frequency fluctuations (ALFF) in abnormal regions of brain in patients of chronic kidney disease (CKD).

Materials and methods

A total of 64 patients of CKD were divided into 26 cases of non-dialysis-dependent chronic kidney disease (NDD-CKD), and 38 cases of dialysis-dependent chronic kidney disease (DD-CKD). A total of 43 healthy controls (normal control, NC) were also included. All subjects underwent resting-state functional magnetic resonance imaging (rs-fMRI). ALFF and ReHo data was processed for monitoring the differences in spontaneous brain activity between the three groups. ALFF and ReHo values of extracted differential brain regions were correlated to the clinical data and cognitive scores of CKD patients.

Results

Non-dialysis-dependent group has increased ALFF levels in 13 brain regions while that of DD group in 28 brain regions as compared with NC group. ReHo values are altered in six brain regions of DD group. ALFF is correlated with urea nitrogen and ReHo with urea nitrogen and creatinine. DD group has altered ReHo in two brain regions compared with NDD group. The differences are located in basal ganglia, cerebellar, and hippocampus regions.

Conclusion

Abnormal activity in basal ganglia, cerebellar, and hippocampal regions may be involved in the cognitive decline of CKD patients. This link can provide theoretical basis for understanding the cognitive decline.

Exploring neurometabolic alterations in bipolar disorder with suicidal ideation based on proton magnetic resonance spectroscopy and machine learning technology

Bipolar disorder (BD) is associated with a high risk of suicide. We used proton magnetic resonance spectroscopy (1H-MRS) to detect biochemical metabolite ratios in the bilateral prefrontal white matter (PWM) and hippocampus in 32 BD patients with suicidal ideation (SI) and 18 BD patients without SI, identified potential brain biochemical differences and used abnormal metabolite ratios to predict the severity of suicide risk based on the support vector machine (SVM) algorithm. Furthermore, we analyzed the correlations between biochemical metabolites and clinical variables in BD patients with SI. There were three main findings: (1) the highest classification accuracy of 88% and an area under the curve of 0.9 were achieved in distinguishing BD patients with and without SI, with N-acetyl aspartate (NAA)/creatine (Cr), myo-inositol (mI)/Cr values in the bilateral PWM, NAA/Cr and choline (Cho)/Cr values in the left hippocampus, and Cho/Cr values in the right hippocampus being the features contributing the most; (2) the above seven features could be used to predict Self-rating Idea of Suicide Scale scores (r = 0.4261, p = 0.0302); and (3) the level of neuronal function in the left hippocampus may be related to the duration of illness, the level of membrane phospholipid catabolism in the left hippocampus may be related to the severity of depression, and the level of inositol metabolism in the left PWM may be related to the age of onset in BD patients with SI. Our results showed that the combination of multiple brain biochemical metabolites could better predict the risk and severity of suicide in patients with BD and that there was a significant correlation between biochemical metabolic values and clinical variables in BD patients with SI.

Functional Connectivity within the Frontal–Striatal Network Differentiates Checkers from Washers of Obsessive-Compulsive Disorder

Background: Obsessive-compulsive disorder (OCD) is a psychiatric disorder with high clinical heterogeneity manifested by the presence of obsessions and/or compulsions. The classification of the symptom dimensional subtypes is helpful for further exploration of the pathophysiological mechanisms underlying the clinical heterogeneity of OCD. Washing and checking symptoms are the two major symptom subtypes in OCD, but the neural mechanisms of the different types of symptoms are not yet clearly understood. The purpose of this study was to compare regional and network functional alterations between washing and checking OCD based on resting-state functional magnetic resonance imaging (rs-fMRI). Methods: In total, 90 subjects were included, including 15 patients in the washing group, 30 patients in the checking group, and 45 healthy controls (HCs). Regional homogeneity (ReHo) was used to compare the differences in regional spontaneous neural activity among the three groups, and local indicators were analyzed by receiver operating characteristic (ROC) curves as imaging markers for the prediction of the clinical subtypes of OCD. Furthermore, differently activated local brain areas, as regions of interest (ROIs), were used to explore differences in altered brain functioning between washing and checking OCD symptoms based on a functional connectivity (FC) analysis. Results: Extensive abnormalities in spontaneous brain activity involving frontal, temporal, and occipital regions were observed in the patients compared to the HCs. The differences in local brain functioning between checking and washing OCD were mainly concentrated in the bilateral middle frontal gyrus, right supramarginal gyrus, right angular gyrus, and right inferior occipital gyrus. The ROC curve analysis revealed that the hyperactivation right middle frontal gyrus had a better discriminatory value for checking and washing OCD. Furthermore, the seed-based FC analysis revealed higher FC between the left medial superior frontal gyrus and right caudate nucleus compared to that in the healthy controls. Conclusions: These findings suggest that extensive local differences exist in intrinsic spontaneous activity among the checking group, washing group, and HCs. The neural basis of checking OCD may be related to dysfunction in the frontal–striatal network, which distinguishes OCD from washing OCD.

Dopaminergic dysfunction and excitatory/inhibitory imbalance in treatment-resistant schizophrenia and novel neuromodulatory treatment

Antipsychotic drugs are the mainstay in the treatment of schizophrenia. However, one-third of patients do not show adequate improvement in positive symptoms with non-clozapine antipsychotics. Additionally, approximately half of them show poor response to clozapine, electroconvulsive therapy, or other augmentation strategies. However, the development of novel treatment for these conditions is difficult due to the complex and heterogenous pathophysiology of treatment-resistant schizophrenia (TRS). Therefore, this review provides key findings, potential treatments, and a roadmap for future research in this area. First, we review the neurobiological pathophysiology of TRS, particularly the dopaminergic, glutamatergic, and GABAergic pathways. Next, the limitations of existing and promising treatments are presented. Specifically, this article focuses on the therapeutic potential of neuromodulation, including electroconvulsive therapy, repetitive transcranial magnetic stimulation, transcranial direct current stimulation, and deep brain stimulation. Finally, we propose multivariate analyses that integrate various perspectives of the pathogenesis, such as dopaminergic dysfunction and excitatory/inhibitory imbalance, thereby elucidating the heterogeneity of TRS that could not be obtained by conventional statistics. These analyses can in turn lead to a precision medicine approach with closed-loop neuromodulation targeting the detected pathophysiology of TRS.

Altered Intrinsic Regional Spontaneous Brain Activity in Patients With Severe Obesity and Meibomian Gland Dysfunction: A Resting-State Functional Magnetic Resonance Imaging Study

Purpose

To evaluate potential regional homogeneity (ReHo) cerebrum function lesions in people with severe obesity and meibomian gland dysfunction (SM) and probe the connection between aberrant cerebrum activity and clinical manifestations.

Patients and Methods

An aggregation of 12 patients with SM, and 12 healthy controls (HCs) closely matched in age and gender were enrolled. We applied corneal confocal microscopy and fundus angiography to compare imaging distinctions between the two groups. SMs were required to carefully fill out the Hospital Anxiety Depression Scale (HADS) forms, and a correlation analysis was performed. ReHo was also utilized to appraise partial differences in spontaneous cerebrum function. Receiver operating characteristic (ROC) curves were created to partition ReHo values between patients with SM and the HCs.

Results

ReHo values for the left cerebellum (LC), right fusiform gyrus (RFG), left inferior temporal gyrus (LITG), left rectus gyrus (LRG), right thalamus (RT), right caudate (RC), left insula (LI), and left thalamus (LT) of subjects with SM were notably higher than those of the HCs (P < 0.05). ReHo values of the right middle frontal gyrus (RMFG) in subjects with SM were decreased notably compared to the HCs (P < 0.05). ReHo values for the RMFG showed a negative correlation with the anxiety scores (ASs; r = −0.961, P < 0.001) and ReHo values for the RFG showed a positive correlation with the depression scores (DSs; r = 0.676, P = 0.016). The areas under the ROC curve were 1.000 (P < 0.001) for the RMFG, LC, LITG, LRG, RC, LI, and LT and 0.993 (P < 0.001) for the RFG and RT. The results from the ROC curve analysis indicated that changes in the ReHo values of some brain regions may help diagnose SM.

Conclusion

Our research emphasized that patients with SM had lesions in synchronized neural activity in many encephalic areas. Our discoveries may provide beneficial information for exploring the neuromechanics of SM.

Improving Depressive Symptoms of Post-stroke Depression Using the Shugan Jieyu Capsule: A Resting-State Functional Magnetic Resonance Imaging Study

Regional homogeneity (ReHo) and fractional amplitude of low-frequency fluctuation (fALFF) were used to detect the neuroimaging mechanism of Shugan Jieyu Capsule (SG) in ameliorating depression of post-stroke depression (PSD) patients. Fifteen PSD patients took SG for 8 weeks, completed the 24-item Hamilton Depression Scale (HAMD) assessment at the baseline and 8 weeks later, and underwent functional magnetic resonance imaging (fMRI) scanning. Twenty-one healthy controls (HCs) underwent these assessments at the baseline. We found that SG improved depression of PSD patients, in which ReHo values decreased in the left calcarine sulcus (CAL.L) and increased in the left superior frontal gyrus (SFG.L) of PSD patients at the baseline. The fALFF values of the left inferior parietal cortex (IPL.L) decreased in PSD patients at the baseline. Abnormal functional activities in the brain regions were reversed to normal levels after the administration of SG for 8 weeks. Receiver operating characteristic (ROC) analysis found that the changes in three altered brain regions could be used to differentiate PSD patients at the baseline and HCs. Average signal values of altered regions were related to depression in all subjects at the baseline. Our results suggest that SG may ameliorate depression of PSD patients by affecting brain region activity and local synchronization.

Weight Status Modulated Brain Regional Homogeneity in Long-Term Male Smokers

BACKGROUND

Tobacco smoking and being overweight could lead to adverse health effects, which remain an important public health problem worldwide. Research indicates that overlapping pathophysiology may contribute to tobacco addiction and being overweight, but the neurobiological interaction mechanism between the two factors is still unclear.

METHODS

The current study used a mixed sample design, including the following four groups: (i) overweight long-term smokers (n = 24); (ii) normal-weight smokers (n = 28); (iii) overweight non-smokers (n = 19), and (iv) normal-weight non-smokers (n = 28), for a total of 89 male subjects. All subjects underwent resting-state functional magnetic resonance imaging (rs-fMRI). Regional homogeneity (ReHo) was used to compare internal cerebral activity among the four groups. Interaction effects between tobacco addiction and weight status on ReHo were detected using a two-way analysis of variance, correcting for age, years of education, and head motion.

RESULTS

A significant interaction effect between tobacco addiction and weight status is shown in right superior frontal gyrus. Correlation analyses show that the strengthened ReHo value in the right superior frontal gyrus is positively associated with pack-year. Besides, the main effect of tobacco addiction is specially observed in the occipital lobe and cerebellum posterior lobe. As for the main effect of weight status, the right lentiform nucleus, left postcentral gyrus, and brain regions involved in default mode network (DMN) survived.

CONCLUSIONS

These results shed light on an antagonistic interaction on brain ReHo between tobacco addiction and weight status in the right superior frontal gyrus, which may be a clinical neuro-marker of comorbid tobacco addiction and overweight. Our findings may provide a potential target to develop effective treatments for the unique population of comorbid tobacco addiction and overweight people.

Searching for Imaging Biomarkers of Psychotic Dysconnectivity

BACKGROUND

Progress in precision psychiatry is predicated on identifying reliable individual-level diagnostic biomarkers. For psychosis, measures of structural and functional connectivity could be promising biomarkers given consistent reports of dysconnectivity across psychotic disorders using magnetic resonance imaging.

METHODS

We leveraged data from four independent cohorts of patients with psychosis and control subjects with observations from approximately 800 individuals. We used group-level analyses and two supervised machine learning algorithms (support vector machines and ridge regression) to test within-, between-, and across-sample classification performance of white matter and resting-state connectivity metrics.

RESULTS

Although we replicated group-level differences in brain connectivity, individual-level classification was suboptimal. Classification performance within samples was variable across folds (highest area under the curve [AUC] range = 0.30) and across datasets (average support vector machine AUC range = 0.50; average ridge regression AUC range = 0.18). Classification performance between samples was similarly variable or resulted in AUC values of approximately 0.65, indicating a lack of model generalizability. Furthermore, collapsing across samples (resting-state functional magnetic resonance imaging, N = 888; diffusion tensor imaging, N = 860) did not improve model performance (maximal AUC = 0.67). Ridge regression models generally outperformed support vector machine models, although classification performance was still suboptimal in terms of clinical relevance. Adjusting for demographic covariates did not greatly affect results.

CONCLUSIONS

Connectivity measures were not suitable as diagnostic biomarkers for psychosis as assessed in this study. Our results do not negate that other approaches may be more successful, although it is clear that a systematic approach to individual-level classification with large independent validation samples is necessary to properly vet neuroimaging features as diagnostic biomarkers.

Comparison of resting-state spontaneous brain activity between treatment-naive schizophrenia and obsessive-compulsive disorder

BACKGROUND

Schizophrenia (SZ) and obsessive-compulsive disorder (OCD) share many demographic characteristics and severity of clinical symptoms, genetic risk factors, pathophysiological underpinnings, and brain structure and function. However, the differences in the spontaneous brain activity patterns between the two diseases remain unclear. Here this study aimed to compare the features of intrinsic brain activity in treatment-naive participants with SZ and OCD and to explore the relationship between spontaneous brain activity and the severity of symptoms.

METHODS

In this study, 22 treatment-naive participants with SZ, 27 treatment-naive participants with OCD, and sixty healthy controls (HC) underwent a resting-state functional magnetic resonance imaging (fMRI) scan. The amplitude of low-frequency fluctuation (ALFF), regional homogeneity (ReHo) and degree of centrality (DC) were performed to examine the intrinsic brain activity of participants. Additionally, the relationships among spontaneous brain activity, the severity of symptoms, and the duration of illness were explored in SZ and OCD groups.

RESULTS

Compared with SZ group and HC group, participants with OCD had significantly higher ALFF in the right angular gyrus and the left middle frontal gyrus/precentral gyrus and significantly lower ALFF in the left superior temporal gyrus/insula/rolandic operculum and the left postcentral gyrus, while there was no significant difference in ALFF between SZ group and HC group. Compared with HC group, lower ALFF in the right supramarginal gyrus/inferior parietal lobule and lower DC in the right lingual gyrus/calcarine fissure and surrounding cortex of the two patient groups, higher ReHo in OCD group and lower ReHo in SZ group in the right angular gyrus/middle occipital gyrus brain region were documented in the present study. DC in SZ group was significantly higher than that in HC group in the right inferior parietal lobule/angular gyrus, while there were no significant DC differences between OCD group and HC group. In addition, ALFF in the left postcentral gyrus were positively correlated with positive subscale score (r = 0.588, P = 0.013) and general psychopathology subscale score (r = 0.488, P = 0.047) respectively on the Positive and Negative Syndrome Scale (PANSS) in SZ group. ALFF in the left superior temporal gyrus/insula/rolandic operculum of participants with OCD were positively correlated with compulsion subscale score (r = 0.463, P = 0.030) on the Yale-Brown Obsessive-Compulsive Scale (Y-BOCS). The longer the illness duration in SZ group, the smaller the ALFF of the left superior temporal gyrus/insula/rolandic operculum (Rho = 0.-492, P = 0.020). The longer the illness duration in OCD group, the higher the ALFF of the right supramarginal gyrus/inferior parietal lobule (Rho = 0.392, P = 0.043) and the left postcentral gyrus (Rho = 0.385, P = 0.048), and the lower the DC of the right inferior parietal lobule/angular gyrus (Rho = - 0.518, P = 0.006).

CONCLUSION

SZ and OCD show some similarities in spontaneous brain activity in parietal and occipital lobes, but exhibit different patterns of spontaneous brain activity in frontal, temporal, parietal, occipital, and insula brain regions, which might imply different underlying neurobiological mechanisms in the two diseases. Compared with OCD, SZ implicates more significant abnormalities in the functional connections among brain regions.

A Diagnosis and Biotype Comparison Across the Psychosis Spectrum: Investigating Volume and Shape Amygdala-Hippocampal Differences from the B-SNIP Study

OBJECTIVE

Brain-based Biotypes for psychotic disorders have been developed as part of the B-SNIP consortium to create neurobiologically distinct subgroups within idiopathic psychosis, independent from traditional phenomenological diagnostic methods. In the current study, we aimed to validate the Biotype model by assessing differences in volume and shape of the amygdala and hippocampus contrasting traditional clinical diagnoses with Biotype classification.

METHODS

A total of 811 participants from 6 sites were included: probands with schizophrenia (n = 199), schizoaffective disorder (n = 122), psychotic bipolar disorder with psychosis (n = 160), and healthy controls (n = 330). Biotype classification, previously developed using cognitive and electrophysiological data and K-means clustering, was used to categorize psychosis probands into 3 Biotypes, with Biotype-1 (B-1) showing reduced neural salience and severe cognitive impairment. MAGeT-Brain segmentation was used to determine amygdala and hippocampal volumetric data and shape deformations.

RESULTS

When using Biotype classification, B-1 showed the strongest reductions in amygdala-hippocampal volume and the most widespread shape abnormalities. Using clinical diagnosis, probands with schizophrenia and schizoaffective disorder showed the most significant reductions of amygdala and hippocampal volumes and the most abnormal hippocampal shape compared with healthy controls. Biotype classification provided the strongest neuroanatomical differences compared with conventional DSM diagnoses, with the best discrimination seen using bilateral amygdala and right hippocampal volumes in B-1.

CONCLUSION

These findings characterize amygdala and hippocampal volumetric and shape abnormalities across the psychosis spectrum. Grouping individuals by Biotype showed greater between-group discrimination, suggesting a promising approach and a favorable target for characterizing biological heterogeneity across the psychosis spectrum.

Resting-state functional reorganisation in Alzheimer's disease and amnestic mild cognitive impairment: protocol for a systematic review and meta-analysis

INTRODUCTION

The incidence of Alzheimer's disease (AD) is increasing rapidly, causing a growing burden to health and economic worldwide. Several clinical trials in the past decade failed to find solutions, and there remains a lack of an effective treatment. The evidence suggests that early intervention for neurodegeneration would likely be effective in preventing cognitive decline. Cognitive decline in AD occurs continuously over a long period; however, there remains a lack of simple, rapid and accurate approach for diagnosis of amnestic mild cognitive impairment or subjective cognitive decline due to underlying Alzheimer's pathology. Resting-state functional MRI (rs-fMRI) determines the functional activities of the human brain non-invasively. The amplitude of low-frequency fluctuation (ALFF), fractional ALFF (fALFF) and regional homogeneity (ReHo) are rs-fMRI indicators with high repeatability. They have been studied as early diagnostic imaging markers for other diseases and may be promising markers also for AD.

METHODS AND ANALYSIS

The following electronic literature databases will be searched from inception to December 2021: Medline-Ovid, Medline-PubMed, EMBase-Ovid, Cochrane Central and ClinicalTrials.gov. Two independent reviewers will select studies with eligible criteria, extract data and assess the quality of the original studies with our quality assessment tool individually. Missing data will be requested by sending emails to the corresponding authors. Brain regions will be presented for ALFF/fALFF and ReHo by performing activation likelihood estimation with the Seed-based d Mapping-Permutation of subject images V.6.21 software. Meta-regression will be performed to determine the potential brain regions that may strongly correlate with cognitive decline progression. Subgroup analysis, funnel plot, Egger's test and sensitivity analysis will be conducted to detect and explain potential heterogeneity.

ETHICS AND DISSEMINATION

This study does not require formal ethical approval. The findings will be submitted to a peer-review journal.

PROSPERO REGISTRATION NUMBER

CRD42021229009.

Correlation analysis between regional homogeneity and executive dysfunction in anti-N-methyl-D-aspartate receptor encephalitis patients

BACKGROUND AND PURPOSE

Anti-N-methyl-d-aspartate receptor (NMDAR) encephalitis is characterized by a range of cognitive impairments, especially in executive function. Our study aims to identify the abnormal regional homogeneity (ReHo) in anti-NMDAR encephalitis patients and its relationship with the executive function.

METHODS

Forty patients and 42 healthy volunteers undertook an Attention Network Test and a resting-state functional magnetic resonance imaging scan. ReHo analysis was performed to investigate the neuronal activity synchronization in all subjects. Based on ReHo analysis, a multivariate pattern analysis (MVPA) was carried out to identify the brain regions that differed the most between the two groups.

RESULTS

Compared to controls, the patients had higher executive control scores (p < 0.05). The patients presented reduced ReHo values in the bilateral posterior cerebellar lobe, anterior cerebellar lobe, midbrain, bilateral caudate nucleus, right superior frontal gyrus, right middle temporal gyrus, bilateral inferior parietal lobule and the left middle frontal gyrus. The ReHo values of the bilateral inferior parietal lobule in patients were found to be negatively associated with executive control scores. The classification of patients and controls using MVPA had an accuracy of 76.83%, a sensitivity of 82.50%, a specificity of 71.43% and the area under the curve was 0.83.

CONCLUSIONS

Our study provides evidence of abnormal cerebral function in anti-NMDAR encephalitis patients, which may contribute to unveiling the neuropathological mechanisms of anti-NMDAR encephalitis and their influences on executive dysfunction. The MVPA classifier, based on ReHo, is helpful in identifying anti-NMDAR encephalitis patients from healthy controls.

The gut microbiome is associated with brain structure and function in schizophrenia

The effect of the gut microbiome on the central nervous system and its possible role in mental disorders have received increasing attention. However, knowledge about the relationship between the gut microbiome and brain structure and function is still very limited. Here, we used 16S rRNA sequencing with structural magnetic resonance imaging (sMRI) and resting-state functional (rs-fMRI) to investigate differences in fecal microbiota between 38 patients with schizophrenia (SZ) and 38 demographically matched normal controls (NCs) and explored whether such differences were associated with brain structure and function. At the genus level, we found that the relative abundance of Ruminococcus and Roseburia was significantly lower, whereas the abundance of Veillonella was significantly higher in SZ patients than in NCs. Additionally, the analysis of MRI data revealed that several brain regions showed significantly lower gray matter volume (GMV) and regional homogeneity (ReHo) but significantly higher amplitude of low-frequency fluctuation in SZ patients than in NCs. Moreover, the alpha diversity of the gut microbiota showed a strong linear relationship with the values of both GMV and ReHo. In SZ patients, the ReHo indexes in the right STC (r = − 0.35, p = 0.031, FDR corrected p = 0.039), the left cuneus (r = − 0.33, p = 0.044, FDR corrected p = 0.053) and the right MTC (r = − 0.34, p = 0.03, FDR corrected p = 0.052) were negatively correlated with the abundance of the genus Roseburia. Our results suggest that the potential role of the gut microbiome in SZ is related to alterations in brain structure and function. This study provides insights into the underlying neuropathology of SZ.

White matter microstructure across brain-based biotypes for psychosis - findings from the bipolar-schizophrenia network for intermediate phenotypes

The B-SNIP consortium identified three brain-based Biotypes across the psychosis spectrum, independent of clinical phenomenology. To externally validate the Biotype model, we used free-water fractional volume (FW) and free-water corrected fractional anisotropy (FA_T) to compare white matter differences across Biotypes and clinical diagnoses. Diffusion tensor imaging data from 167 individuals were included: 41 healthy controls, 55 schizophrenia probands, 47 schizoaffective disorder probands, and 24 probands with psychotic bipolar disorder. Compared to healthy controls, FAt reductions were observed in the body of corpus callosum (BCC) for schizoaffective disorder (d = 0.91) and schizophrenia (d = 0.64). Grouping by Biotype, Biotype 1 showed FAt reductions in the CC and fornix, with largest effect in the BCC (d = 0.87). Biotype 2 showed significant FAt reductions in the BCC (d = 0.90). Schizoaffective disorder individuals had elevated FW in the CC, fornix and anterior corona radiata (ACR), with largest effect in the BCC (d = 0.79). Biotype 2 showed elevated FW in the CC, fornix and ACR, with largest effect in the BCC (d = 0.94). While significant diagnosis comparisons were observed, overall greater discrimination from healthy controls was observed for lower FAt in Biotype 1 and elevated FW in Biotype 2. However, between-group differences were modest, with one region (cerebral peduncle) showing a between-Biotype effect. No between-group effects were observed for diagnosis groupings.

Biotyping in psychosis: using multiple computational approaches with one data set

Focusing on biomarker identification and using biomarkers individually or in clusters to define biological subgroups in psychiatry requires a re-orientation from behavioral phenomenology to quantifying brain features, requiring big data approaches for data integration. Much still needs to be accomplished, not only to refine but also to build support for the application and customization of such an analytical phenotypic approach. In this review, we present some of what Bipolar-Schizophrenia Network for Intermediate Phenotypes (B-SNIP) has learned so far to guide future applications of multivariate phenotyping and their analyses to understanding psychosis. This paper describes several B-SNIP projects that use phenotype data and big data computations to generate novel outcomes and glimpse what phenotypes contribute to disease understanding and, with aspiration, to treatment. The source of the phenotypes varies from genetic data, structural neuroanatomic localization, immune markers, brain physiology, and cognition. We aim to see guiding principles emerge and areas of commonality revealed. And, we will need to demonstrate not only data stability but also the usefulness of biomarker information for subgroup identification enhancing target identification and treatment development.

Applying dimensional psychopathology: transdiagnostic associations among regional homogeneity, leptin and depressive symptoms

Dimensional psychopathology and its neurobiological underpinnings could provide important insights into major psychiatric disorders, including major depressive disorder, bipolar disorder and schizophrenia. In a dimensional transdiagnostic approach, we examined depressive symptoms and their relationships with regional homogeneity and leptin across major psychiatric disorders. A total of 728 participants (including 403 patients with major psychiatric disorders and 325 age-gender-matched healthy controls) underwent resting-state functional magnetic resonance imaging at a single site. We obtained plasma leptin levels and depressive symptom measures (Hamilton Depression Rating Scale (HAMD)) within 24 h of scanning and compared the regional homogeneity (ReHo), plasma leptin levels and HAMD total score and factor scores between patients and healthy controls. To reveal the potential relationships, we performed correlational and mediational analyses. Patients with major psychiatric disorders had significant lower ReHo in primary sensory and visual association cortices and higher ReHo in the frontal cortex and angular gyrus; plasma leptin levels were also elevated. Furthermore, ReHo alterations, leptin and HAMD factor scores had significant correlations. We also found that leptin mediated the transdiagnostic relationships among ReHo alterations in primary somatosensory and visual association cortices, core depressive symptoms and body mass index. The transdiagnostic associations we demonstrated support the common neuroanatomical substrates and neurobiological mechanisms. Moreover, leptin could be an important association among ReHo, core depressive symptoms and body mass index, suggesting a potential therapeutic target for dimensional depressive symptoms across major psychiatric disorders.

Identifying commonality and specificity across psychosis sub-groups via classification based on features from dynamic connectivity analysis

It is difficult to distinguish schizophrenia (SZ), schizoaffective disorder (SAD), and bipolar disorder with psychosis (BPP) as their clinical diagnoses rely on symptoms that overlap. In this paper, we investigate if there is biological evidence to support the symptom-based clinical categories by looking across the three disorders using dynamic connectivity measures, and provide meaningful characteristics on which brain functional connectivity measures are commonly or uniquely impaired. Large-sample functional magnetic resonance image (fMRI) datasets from 623 subjects including 238 healthy controls (HCs), 113 SZ patients, 132 SAD patients, and 140 BPP patients were analyzed. First, we computed whole-brain dynamic functional connectivity (DFC) using a sliding-window technique, and then extracted the individual connectivity states by applying our previously proposed decomposition-based DFC analysis method. Next, with the features from the dominant connectivity state, we assessed the clinical categories by performing both four-group (SZ, SAD, BPP and healthy control groups) and pair-wise classification using a support vector machine within cross-validation. Furthermore, we comprehensively summarized the shared and unique connectivity alterations among the disorders. In terms of the classification performance, our method achieved 69% in the four-group classification and >80% in the between-group classifications for the mean overall accuracy; and yielded 66% in the four-group classification and >80% in the between-group classifications for the mean balanced accuracy. Through summarizing the features that were automatically selected in the classifications, we found that among the three symptom-related disorders, their disorder-common impairments primarily included the decreased connectivity strength between thalamus and cerebellum and the increased strength between postcentral gyrus and thalamus. The disorder-unique changes included more various brain regions, mainly in the temporal and frontal gyrus. Our work demonstrates that dynamic functional connectivity provides biological evidence that both common and unique impairments exist in psychosis sub-groups.

Application of Support Vector Machine on fMRI Data as Biomarkers in Schizophrenia Diagnosis: A Systematic Review

Non-invasive measurements of brain function and structure as neuroimaging in patients with mental illnesses are useful and powerful tools for studying discriminatory biomarkers. To date, functional MRI (fMRI), structural MRI (sMRI) represent the most used techniques to provide multiple perspectives on brain function, structure, and their connectivity. Recently, there has been rising attention in using machine-learning (ML) techniques, pattern recognition methods, applied to neuroimaging data to characterize disease-related alterations in brain structure and function and to identify phenotypes, for example, for translation into clinical and early diagnosis. Our aim was to provide a systematic review according to the PRISMA statement of Support Vector Machine (SVM) techniques in making diagnostic discrimination between SCZ patients from healthy controls using neuroimaging data from functional MRI as input. We included studies using SVM as ML techniques with patients diagnosed with Schizophrenia. From an initial sample of 660 papers, at the end of the screening process, 22 articles were selected, and included in our review. This technique can be a valid, inexpensive, and non-invasive support to recognize and detect patients at an early stage, compared to any currently available assessment or clinical diagnostic methods in order to save crucial time. The higher accuracy of SVM models and the new integrated methods of ML techniques could play a decisive role to detect patients with SCZ or other major psychiatric disorders in the early stages of the disease or to potentially determine their neuroimaging risk factors in the near future.