Dataset Information

Classification of Social Anxiety Disorder With Support Vector Machine Analysis Using Neural Correlates of Social Signals of Threat.

ABSTRACT: Threatening faces are potent cues in social anxiety disorder (SAD); therefore, neural response to threatening faces, particularly regions in the "fear" circuit such as amygdala, may classify individuals with SAD. Previous studies of indirect/implicit processing of threatening faces have shown that support vector machine (SVM) pattern recognition significantly differentiates individuals with SAD from healthy participants, though evidence for the role of the fear circuit in classification has been inconsistent. We extend this literature by using SVM during direct face processing. Individuals with SAD (n=47) and healthy controls (n=46) completed a validated emotional face matching task during functional MRI, which included a matching shapes control condition. SVM was based on brain response to threat (vs. happy) faces, threat faces (vs. shapes), and threat/happy faces (vs. shapes) in 90 regions encompassing frontal, limbic, parietal, temporal, and occipital systems. Recursive feature elimination (RFE) was used for feature selection and to rank the contribution of regions in predicting SAD diagnosis. SVM results for threat (vs. happy) faces revealed satisfactory accuracy (e.g., area under the curve=0.72); results with shapes as "baseline" yielded less optimal classification. RFE for threat (vs. happy) indicated that all 90 brain regions were necessary for classification. RFE-based ranking suggested diffuse neurofunctional activation to threat (vs. happy) faces in classification. When using an RFE cut-point, regions implicated in sensory and goal-directed processes contributed relatively more in differentiating SAD from controls than other regions. Results suggest that neural activity across large-scale systems, as opposed to fear circuitry alone, may aid in the diagnosis of SAD.

SUBMITTER: Xing M

PROVIDER: S-EPMC7082922 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundAnxiety and irritability frequently co-occur in youth and are mediated by aberrant threat responses. However, empirical evidence on neural mechanisms underlying this co-occurrence is limited. To address this, we apply data-driven latent phenotyping to data from a prior report of a well-validated threat extinction recall fMRI paradigm.MethodsParticipants included 59 youth (28 anxiety disorder, 31 healthy volunteers; Mage=13.15 yrs) drawn from a transdiagnostic sample of 331 youth, in which bifactor analysis was conducted to derive latent factors representing shared vs. unique variance of dimensionally-assessed anxiety and irritability. Participants underwent threat conditioning and extinction. Approximately three weeks later, during extinction recall fMRI, participants made threat-safety discriminations under two task conditions: current threat appraisal and explicit recall of threat contingencies. Linear mixed-effects analyses examined associations of a "negative affectivity" factor reflecting shared anxiety and irritability variance with whole-brain activation and task-dependent amygdala connectivity.ResultsDuring recall of threat-safety contingencies, higher negative affectivity was associated with greater prefrontal (ventrolateral/ventromedial, dorsolateral, orbitofrontal), motor, temporal, parietal, and occipital activation. During threat appraisal, higher negative affectivity was associated with greater amygdala-inferior parietal lobule connectivity to threat/safety ambiguity.LimitationsSample included only healthy youth and youth with anxiety disorders. Results may not generalize to other diagnoses for which anxiety and irritability are also common, and our negative affectivity factor should be interpreted as anxiety disorders with elevated irritability. Reliability of some subfactors was poor.ConclusionsAberrant amygdala-prefrontal-parietal circuitry during extinction recall of threat-safety stimuli may be a mechanism underlying the co-occurrence of pediatric anxiety and irritability.

Dataset Information

Classification of Social Anxiety Disorder With Support Vector Machine Analysis Using Neural Correlates of Social Signals of Threat.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets