Dataset Information

Sub-graph entropy based network approaches for classifying adolescent obsessive-compulsive disorder from resting-state functional MRI.

ABSTRACT: This paper presents a novel approach for classifying obsessive-compulsive disorder (OCD) in adolescents from resting-state fMRI data. Currently, the state-of-the-art for diagnosing OCD in youth involves interviews with adolescent patients and their parents by an experienced clinician, symptom rating scales based on Diagnostic and Statistical Manual of Mental Disorders (DSM), and behavioral observation. Discovering signal processing and network-based biomarkers from functional magnetic resonance imaging (fMRI) scans of patients has the potential to assist clinicians in their diagnostic assessments of adolescents suffering from OCD. This paper investigates the clinical diagnostic utility of a set of univariate, bivariate and multivariate features extracted from resting-state fMRI using an information-theoretic approach in 15 adolescents with OCD and 13 matched healthy controls. Results indicate that an information-theoretic approach based on sub-graph entropy is capable of classifying OCD vs. healthy subjects with high accuracy. Mean time-series were extracted from 85 brain regions and were used to calculate Shannon wavelet entropy, Pearson correlation matrix, network features and sub-graph entropy. In addition, two special cases of sub-graph entropy, namely node and edge entropy, were investigated to identify important brain regions and edges from OCD patients. A leave-one-out cross-validation method was used for the final predictor performance. The proposed methodology using differential sub-graph (edge) entropy achieved an accuracy of 0.89 with specificity 1 and sensitivity 0.80 using leave-one-out cross-validation with in-fold feature ranking and selection. The high classification accuracy indicates the predictive power of the sub-network as well as edge entropy metric.

SUBMITTER: Sen B

PROVIDER: S-EPMC7025090 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background: Cortico-striato-thalamo-cortical (CSTC) network alterations are hypothesized to contribute to symptoms of obsessive-compulsive disorder (OCD). To date, very few studies have examined whether CSTC network alterations are present in children with OCD, who are medication naive. Medication-naive pediatric imaging samples may be optimal to study neural correlates of illness and identify brain-based markers, given the proximity to illness onset. Methods: Magnetoencephalography (MEG) data were analyzed at rest, in 18 medication-naive children with OCD (M = 12.1 years ±2.0 standard deviation [SD]; 10 M/8 F) and 13 typically developing children (M = 12.3 years ±2.2 SD; 6 M/7 F). Whole-brain MEG-derived resting-state functional connectivity (rs-fc), for alpha- and gamma-band frequencies were compared between OCD and typically developing (control) groups. Results: Increased MEG-derived rs-fc across alpha- and gamma-band frequencies was found in the OCD group compared to the control group. Increased MEG-derived rs-fc at alpha-band frequencies was evident across a number of regions within the CSTC circuitry and beyond, including the cerebellum and limbic regions. Increased MEG-derived rs-fc at gamma-band frequencies was restricted to the frontal and temporal cortices. Conclusions: This MEG study provides preliminary evidence of altered alpha and gamma networks, at rest, in medication-naive children with OCD. These results support prior findings pointing to the relevance of CSTC circuitry in pediatric OCD and further support accumulating evidence of altered connectivity between regions that extend beyond this network, including the cerebellum and limbic regions. Given the substantial portion of children and youth whose OCD symptoms do not respond to conventional treatments, our findings have implications for future treatment innovation research aiming to target and track whether brain patterns associated with having OCD may change with treatment and/or predict treatment response.

Project description:Compulsive behaviors in obsessive-compulsive disorder (OCD) may be related to deficits in reward processing mediated by corticostriatal circuitry, a brain network implicated in the pathophysiology of OCD. Performing compulsive actions can be perceived as a reward to OCD patients because it temporarily reduces the anxiety provoked by obsessions. Although most OCD literature provides evidence of altered regional activity in these corticostriatal circuits, very little is known about the connectivity between individual regions of the corticostriatal-limbic circuits, including the cognitive and affective neural circuitry associated with OCD. Thus, this study investigated the differences in functional connectivity (FC) patterns in this network during resting-state and incentive processing. Nineteen patients with OCD and 18 well-matched healthy controls were scanned during resting-state and a monetary incentive delay task (task state). FC was assessed using both voxel-wise and region-of-interest (ROI)-wise analyses. Voxel-wise FC analysis with the nucleus accumbens seed revealed that patients with OCD exhibited increased FC between the nucleus accumbens and the lateral orbitofrontal cortex during resting-state. Additionally, these patients showed decreased FC between the nucleus accumbens and limbic areas such as the amygdala during incentive processing. Exploratory ROI-wise FC analysis revealed that OCD patients demonstrated enhanced FC between the nucleus accumbens and the lateral orbitofrontal cortex and increased total connectivity of the lateral orbitofrontal cortex during resting-state. Additionally, patients showed alterations in FC between resting and task state. This study provides evidence that patients with OCD have altered FC in the corticostriatal-limbic network, particularly in striatal-amygdala and striatal-orbitofrontal circuitry, during incentive processing and resting-state. These findings also emphasize that functional connections in the network are modulated by affective/motivational states and further suggest that OCD patients may have abnormalities of such modulation in this network.

Dataset Information

Sub-graph entropy based network approaches for classifying adolescent obsessive-compulsive disorder from resting-state functional MRI.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets