Using short-range and long-range functional connectivity to identify schizophrenia with a family-based case-control design

A meta-analysis and systematic review of single vs. multimodal neuroimaging techniques in the classification of psychosis

BACKGROUND

Psychotic disorders are characterized by structural and functional abnormalities in brain networks. Neuroimaging techniques map and characterize such abnormalities using unique features (e.g., structural integrity, coactivation). However, it is unclear if a specific method, or a combination of modalities, is particularly effective in identifying differences in brain networks of someone with a psychotic disorder.

METHODS

A systematic meta-analysis evaluated machine learning classification of schizophrenia spectrum disorders in comparison to healthy control participants using various neuroimaging modalities (i.e., T1-weighted imaging (T1), diffusion tensor imaging (DTI), resting state functional connectivity (rs-FC), or some combination (multimodal)). Criteria for manuscript inclusion included whole-brain analyses and cross-validation to provide a complete picture regarding the predictive ability of large-scale brain systems in psychosis. For this meta-analysis, we searched Ovid MEDLINE, PubMed, PsychInfo, Google Scholar, and Web of Science published between inception and March 13th 2023. Prediction results were averaged for studies using the same dataset, but parallel analyses were run that included studies with pooled sample across many datasets. We assessed bias through funnel plot asymmetry. A bivariate regression model determined whether differences in imaging modality, demographics, and preprocessing methods moderated classification. Separate models were run for studies with internal prediction (via cross-validation) and external prediction.

RESULTS

93 studies were identified for quantitative review (30 T1, 9 DTI, 40 rs-FC, and 14 multimodal). As a whole, all modalities reliably differentiated those with schizophrenia spectrum disorders from controls (OR = 2.64 (95%CI = 2.33 to 2.95)). However, classification was relatively similar across modalities: no differences were seen across modalities in the classification of independent internal data, and a small advantage was seen for rs-FC studies relative to T1 studies in classification in external datasets. We found large amounts of heterogeneity across results resulting in significant signs of bias in funnel plots and Egger's tests. Results remained similar, however, when studies were restricted to those with less heterogeneity, with continued small advantages for rs-FC relative to structural measures. Notably, in all cases, no significant differences were seen between multimodal and unimodal approaches, with rs-FC and unimodal studies reporting largely overlapping classification performance. Differences in demographics and analysis or denoising were not associated with changes in classification scores.

CONCLUSIONS

The results of this study suggest that neuroimaging approaches have promise in the classification of psychosis. Interestingly, at present most modalities perform similarly in the classification of psychosis, with slight advantages for rs-FC relative to structural modalities in some specific cases. Notably, results differed substantially across studies, with suggestions of biased effect sizes, particularly highlighting the need for more studies using external prediction and large sample sizes. Adopting more rigorous and systematized standards will add significant value toward understanding and treating this critical population.

Machine Learning and Non-Affective Psychosis: Identification, Differential Diagnosis, and Treatment

PURPOSE OF REVIEW

This review will cover the most relevant findings on the use of machine learning (ML) techniques in the field of non-affective psychosis, by summarizing the studies published in the last three years focusing on illness detection and treatment.

RECENT FINDINGS

Multiple ML tools that include mostly supervised approaches such as support vector machine, gradient boosting, and random forest showed promising results by applying these algorithms to various sources of data: socio-demographic information, EEG, language, digital content, blood biomarkers, neuroimaging, and electronic health records. However, the overall performance, in the binary classification case, varied from 0.49, which is to be considered very low (i.e., noise), to over 0.90. These results are fully justified by different factors, some of which may be attributable to the preprocessing of the data, the wide variety of the data, and the a-priori setting of hyperparameters. One of the main limitations of the field is the lack of stratification of results based on biological sex, given that psychosis presents differently in men and women; hence, the necessity to tailor identification tools and data analytic strategies. Timely identification and appropriate treatment are key factors in reducing the consequences of psychotic disorders. In recent years, the emergence of new analytical tools based on artificial intelligence such as supervised ML approaches showed promises as a potential breakthrough in this field. However, ML applications in everyday practice are still in its infancy.

Anatomical distance affects functional connectivity at rest in medicine-free obsessive-compulsive disorder

BACKGROUND

Brain functional abnormalities at rest have been observed in obsessive-compulsive disorder (OCD). However, whether and how anatomical distance influences functional connectivity (FC) at rest is ambiguous in OCD.

METHODS

Using resting-state functional magnetic resonance imaging data, we calculated the FC of each voxel in the whole-brain and divided FC into short- and long-range FCs in 40 medicine-free patients with OCD and 40 healthy controls (HCs). A support vector machine (SVM) was used to determine whether the altered short- and long-range FCs could be utilized to distinguish OCD from HCs.

RESULTS

Patients had lower short-range positive FC (spFC) and long-range positive FC (lpFC) in the left precentral/postcentral gyrus (t = -5.57 and -5.43; P < 0.05, GRF corrected) and higher lpFC in the right thalamus/caudate, left thalamus, left inferior parietal lobule (IPL) and left cerebellum CrusI/VI (t = 4.59, 4.61, 4.41, and 5.93; P < 0.05, GRF corrected). Furthermore, lower spFC in the left precentral/postcentral gyrus might be used to distinguish OCD from HCs with an accuracy of 80.77%, a specificity of 81.58%, and a sensitivity of 80.00%.

CONCLUSION

These findings highlight that anatomical distance has an effect on the whole-brain FC patterns at rest in OCD. Meanwhile, lower spFC in the left precentral/postcentral gyrus might be applied in distinguishing OCD from HCs.

Accelerated aging signatures in subjects with schizophrenia and their unaffected siblings

Schizophrenia (SZ) is a chronic debilitating disease. Subjects with SZ have significant shorter life expectancy. Growing evidence suggests that a process of pathological accelerated aging occurs in SZ, leading to early development of severe clinical diseases and worse morbimortality. Furthermore, unaffected relatives can share certain endophenotypes with subjects with SZ. We aim to characterize accelerated aging as a possible endophenotype of schizophrenia by using a machine learning (ML) model of peripheral biomarkers to accurately differentiate subjects with SZ (n = 35), their unaffected siblings (SB, n = 36) and healthy controls (HC, n = 47). We used a random forest algorithm that included biomarkers related to aging: eotaxins CCL-11 and CCL-24; the oxidative stress markers thiobarbituric acid-reactive substances (TBARS), protein carbonyl content (PCC), glutathione peroxidase (GPx); and telomere length (TL). The ML algorithm of biomarkers was able to distinguish individuals with SZ from HC with prediction accuracy of 79.7%, SZ from SB with 62.5% accuracy and SB from HC with 75.5% accuracy. These results support the hypothesis that a pathological accelerated aging might occur in SZ, and this pathological aging could be an endophenotype of the disease, once this profile was also observed in SB, suggesting that SB might suffer from an accelerated aging in some level.

Large-scale resculpting of cortical circuits in children after surgical resection

Despite the relative successes in the surgical treatment of pharmacoresistant epilepsy, there is rather little research on the neural (re)organization that potentially subserves behavioral compensation. Here, we examined the post-surgical functional connectivity (FC) in children and adolescents who have undergone unilateral cortical resection and, yet, display remarkably normal behavior. Conventionally, FC has been investigated in terms of the mean correlation of the BOLD time courses extracted from different brain regions. Here, we demonstrated the value of segregating the voxel-wise relationships into mutually exclusive populations that were either positively or negatively correlated. While, relative to controls, the positive correlations were largely normal, negative correlations among networks were increased. Together, our results point to reorganization in the contralesional hemisphere, possibly suggesting competition for cortical territory due to the demand for representation of function. Conceivably, the ubiquitous negative correlations enable the differentiation of function in the reduced cortical volume following a unilateral resection.

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.

Examining resting-state functional connectivity in first-episode schizophrenia with 7T fMRI and MEG

Schizophrenia is often characterized by dysconnections in the brain, which can be estimated via functional connectivity analyses. Commonly measured using resting-state functional magnetic resonance imaging (fMRI) in order to characterize the intrinsic or baseline function of the brain, fMRI functional connectivity has significantly contributed to the understanding of schizophrenia. However, these measures may not capture the full extent of functional connectivity abnormalities in schizophrenia as fMRI is temporally limited by the hemodynamic response. In order to extend fMRI functional connectivity findings, the complementary modality of magnetoencephalography (MEG) can be utilized to capture electrophysiological functional connectivity abnormalities in schizophrenia that are not obtainable with fMRI. Therefore, we implemented a multimodal functional connectivity analysis using resting-state 7 Tesla fMRI and MEG data in a sample of first-episode patients with schizophrenia (n = 19) and healthy controls (n = 24). fMRI and MEG data were decomposed into components reflecting resting state networks using a group spatial independent component analysis. Functional connectivity between resting-state networks was computed and group differences were observed. In fMRI, patients demonstrated hyperconnectivity between subcortical and auditory networks, as well as hypoconnectivity between interhemispheric homotopic sensorimotor network components. In MEG, patients demonstrated hypoconnectivity between sensorimotor and task positive networks in the delta frequency band. Results not only support the dysconnectivity hypothesis of schizophrenia, but also suggest the importance of jointly examining multimodal neuroimaging data as critical disorder-related information may not be detectable in a single modality alone.

Dysconnectivity of Multiple Brain Networks in Schizophrenia: A Meta-Analysis of Resting-State Functional Connectivity

Background: Seed-based studies on resting-state functional connectivity (rsFC) in schizophrenia have shown disrupted connectivity involving a number of brain networks; however, the results have been controversial. Methods: We conducted a meta-analysis based on independent component analysis (ICA) brain templates to evaluate dysconnectivity within resting-state brain networks in patients with schizophrenia. Seventy-six rsFC studies from 70 publications with 2,588 schizophrenia patients and 2,567 healthy controls (HCs) were included in the present meta-analysis. The locations and activation effects of significant intergroup comparisons were extracted and classified based on the ICA templates. Then, multilevel kernel density analysis was used to integrate the results and control bias. Results: Compared with HCs, significant hypoconnectivities were observed between the seed regions and the areas in the auditory network (left insula), core network (right superior temporal cortex), default mode network (right medial prefrontal cortex, and left precuneus and anterior cingulate cortices), self-referential network (right superior temporal cortex), and somatomotor network (right precentral gyrus) in schizophrenia patients. No hyperconnectivity between the seed regions and any other areas within the networks was detected in patients, compared with the connectivity in HCs. Conclusions: Decreased rsFC within the self-referential network and default mode network might play fundamental roles in the malfunction of information processing, while the core network might act as a dysfunctional hub of regulation. Our meta-analysis is consistent with diffuse hypoconnectivities as a dysregulated brain network model of schizophrenia.

Cerebellar structural and functional abnormalities in first-episode and drug-naive patients with schizophrenia: A meta-analysis

Schizophrenia (SZ) is a mental disorder that involves cerebral and cerebellar abnormalities. The cerebellum plays an indispensable role in the pathophysiology of SZ. However, individual studies pertaining to the structural and resting-state functional cerebellar abnormalities in patients with SZ have been inconsistent. To make a relatively robust conclusion with little interference, such as different disease episode times and antipsychotic treatment, we conducted this meta-analysis as a first attempt to comprehensively analyze and combine studies of voxel-based morphometry (VBM), amplitude of low-frequency fluctuation (ALFF), and functional connectivity strength (FCS) in first-episode and drug-naive SZ patients, employing the Seed-based d Mapping (SDM) method. Thirteen VBM studies, eight ALFF studies, and three FCS studies involving 783 patients and 704 matched healthy controls were included. Our results showed the presence of structural and functional abnormalities within the cerebellar regions, including most superior/anterior cerebellum (lobule III-V or VI) and posterior/inferior cerebellum (lobule VIII) related to motor function, and posterior cerebellum (lobule VIIa, Crus I, and II) associated with cognition and emotion, and such anomalies might be related to illness duration and clinical symptom severity.

Machine learning techniques in a structural and functional MRI diagnostic approach in schizophrenia: a systematic review

BACKGROUND

Diagnosis of schizophrenia (SCZ) is made exclusively clinically, since specific biomarkers that can predict the disease accurately remain unknown. Machine learning (ML) represents a promising approach that could support clinicians in the diagnosis of mental disorders.

OBJECTIVES

A systematic review, according to the PRISMA statement, was conducted to evaluate its accuracy to distinguish SCZ patients from healthy controls.

METHODS

We systematically searched PubMed, Embase, MEDLINE, PsychINFO and the Cochrane Library through December 2018 using generic terms for ML techniques and SCZ without language or time restriction. Thirty-five studies were included in this review: eight of them used structural neuroimaging, twenty-six used functional neuroimaging and one both, with a minimum accuracy >60% (most of them 75-90%). Sensitivity, Specificity and accuracy were extracted from each publication or obtained directly from authors.

RESULTS

Support vector machine, the most frequent technique, if associated with other ML techniques achieved accuracy close to 100%. The prefrontal and temporal cortices appeared to be the most useful brain regions for the diagnosis of SCZ. ML analysis can efficiently detect significantly altered brain connectivity in patients with SCZ (eg, default mode network, visual network, sensorimotor network, frontoparietal network and salience network).

CONCLUSION

The greater accuracy demonstrated by these predictive models and the new models resulting from the integration of multiple ML techniques will be increasingly decisive for early diagnosis and evaluation of the treatment response and to establish the prognosis of patients with SCZ. To achieve a real benefit for patients, the future challenge is to reach an accurate diagnosis not only through clinical evaluation but also with the aid of ML algorithms.

Abnormal regions in functional connectivity of chronic schizophrenia

Objectives：Schizophrenia is a predominant product of pathological alterations distributed throughout interconnected neural systems. Functional connections (FCs) methodology is an effective lever to investigate macroscopic neural activity patterns underlying critical aspects of cognition and behaviour. However, region properties of brain architecture have been less investigated by special markers of dynamical graph in general mental disorders. Methods：Embracing the eigenvector centrality in holism significance, our important process is to uncover noticeable edges and regions with antagonistic stance between morbid and normal FCs of 67 healthy controls (HCs) and 53 chronic schizophrenia patients (SZs). Results: Results suggest that, there are 12 abnormal edges with significant p value of FCs weight, such as lingual gyrus L versus cuneus L, thalamus L versus middle frontal gyrus R, superior temporal gyrus R versus thalamus R. Importantly, SZs' superior temporal gyrus R, parahippocampal gyrus L and parahippocampal gyrus R are endowed with different eigenvector centrality scores. Conclusion: Consistent with SZs' positive symptoms of hallucinations, and negative symptoms of thinking impairment, it can be infer that the functional separation and integration are destroyed in schizophrenia. Thought the strict contrastive study, it is worth stressing that eigenvector centrality is a meaningful biological marker to excavating schizophrenic psychopathology.

Alterations of Intrinsic Connectivity Networks in Antipsychotic-Naïve First-Episode Schizophrenia

BACKGROUND

The investigation of large-scale intrinsic connectivity networks in antipsychotic-naïve first-episode schizophrenia increases our understanding of system-level cerebral dysfunction in schizophrenia while enabling control of confounding effects of medication and disease progression. Reports on functional connectivity in antipsychotic-naïve patients have been mixed and the relation between network alterations, psychopathology and cognition is unclear.

METHODS

A total number of 47 patients with first-episode schizophrenia who had never received antipsychotic medication and 47 healthy controls were scanned with functional magnetic resonance imaging under resting conditions. Main outcome measures were differences in functional connectivity between groups and the relationship between network alterations, psychopathology and cognition.

RESULTS

Altered connectivity was found between right central executive network (CEN) and right ventral attention network (VAN) (patients > controls, P = .001), left CEN and left VAN (P = .002), and between posterior default mode network and auditory network (P = .006). Association between network connectivity and clinical characteristics was found as interactions between the effects of group and sustained attention (P = .005) and between group and processing speed (P = .007) on the connectivity between right CEN and right VAN.

CONCLUSIONS

Our findings suggest that the early phase of schizophrenia is characterized by increased connectivity between fronto-parietal networks suggested to be involved in the control of cognitive and sensory functions. Moreover, the present study suggests that the problem of not disengaging the VAN leads to difficulties with attention and possibly subjective awareness.