Functional connectivity-based signatures of schizophrenia revealed by multiclass pattern analysis of resting-state fMRI from schizophrenic patients and their healthy siblings

Abstract

BackgroundRecently, a growing number of neuroimaging studies have begun to investigate the brains of schizophrenic patients and their healthy siblings to identify heritable biomarkers of this complex disorder. The objective of this study was to use multiclass pattern analysis to investigate the inheritable characters of schizophrenia at the individual level, by comparing whole-brain resting-state functional connectivity of patients with schizophrenia to their healthy siblings.MethodsTwenty-four schizophrenic patients, twenty-five healthy siblings and twenty-two matched healthy controls underwent the resting-state functional Magnetic Resonance Imaging (rs-fMRI) scanning. A linear support vector machine along with principal component analysis was used to solve the multi-classification problem. By reconstructing the functional connectivities with high discriminative power, three types of functional connectivity-based signatures were identified: (i) state connectivity patterns, which characterize the nature of disruption in the brain network of patients with schizophrenia; (ii) trait connectivity patterns, reflecting shared connectivities of dysfunction in patients with schizophrenia and their healthy siblings, thereby providing a possible neuroendophenotype and revealing the genetic vulnerability to develop schizophrenia; and (iii) compensatory connectivity patterns, which underlie special brain connectivities by which healthy siblings might compensate for an increased genetic risk for developing schizophrenia.ResultsOur multiclass pattern analysis achieved 62.0% accuracy via leave-one-out cross-validation (p < 0.001). The identified state patterns related to the default mode network, the executive control network and the cerebellum. For the trait patterns, functional connectivities between the cerebellum and the prefrontal lobe, the middle temporal gyrus, the thalamus and the middle temporal poles were identified. Connectivities among the right precuneus, the left middle temporal gyrus, the left angular and the left rectus, as well as connectivities between the cingulate cortex and the left rectus showed higher discriminative power in the compensatory patterns.ConclusionsBased on our experimental results, we saw some indication of differences in functional connectivity patterns in the healthy siblings of schizophrenic patients compared to other healthy individuals who have no relations with the patients. Our preliminary investigation suggested that the use of resting-state functional connectivities as classification features to discriminate among schizophrenic patients, their healthy siblings and healthy controls is meaningful.

Reduced Anterior Temporal and Hippocampal Functional Connectivity During Face Processing Discriminates Individuals with Social Anxiety Disorder from Healthy Controls and Panic Disorder, and Increases Following Treatment

“…Here, pattern analysis of FC was more sensitive and specific in discriminating SAD than was multivariate pattern analysis of activation (when using the canonical HRF to model activity), likely due to the fact that it captures information inherent in the interactions among brain regions. Previous large-scale FC approaches capture this information, but only during resting state (ie, resting-state fMRI BOLD to predict schizophrenia (Yu et al, 2013) and age (Dosenbach et al, 2010)). The current approach measures conditiondependent FC (ie, large-scale FC during emotional face viewing), combining the sensitivity of multivariate machine-learning analysis with the advantages of both taskbased and resting-state FC approaches.…”

Abnormalities of Frontal-Parietal Resting-State Functional Connectivity Are Related to Disease Activity in Patients with Systemic Lupus Erythematosus

“…Of note, in the last few years multivariate methods have provided more objective neuroimaging-based biomarkers in neuropsychiatric disorders. By using these multivariate methods, important and interesting results have been reported by analyzing fMRI data [56–59]. For example, Zeng et al [58] demonstrated that multivariate pattern analysis (MVPA) methods can identify major depressive individuals from healthy controls based on resting-state fMRI data with 94.3% accuracy.…”

Thalamus and posterior temporal lobe show greater inter-network connectivity at rest and across sensory paradigms in schizophrenia

“…These differences include a link between prefrontal cortex activation and vulnerability to psychosis (Fusar-Poli, 2007), reduced network activation during executive task performance (Minzenberg, 2009), and abnormal activation patterns in working memory tasks (Glahn et al, 2005). There has been growing interest in investigating the integrity of the neural circuits in schizophrenia that work together to support sensory, cognitive, and emotional processes (Calhoun et al, 2009;Liu et al, 2012; Yu et al, 2013). …”