An obsessive-compulsive disorder (OCD) subtype has been associated with streptococcal infections and is called pediatric autoimmune neuropsychiatric disorders associated with streptococci (PANDAS). The neuroanatomical characterization of subjects with this disorder is crucial for the better understanding of its pathophysiology; also, evaluation of these features as classifiers between patients and controls is relevant to determine potential biomarkers and useful in clinical diagnosis. This was the first multivariate pattern analysis (MVPA) study on an early-onset OCD subtype.

Fourteen pediatric patients with PANDAS were paired with 14 healthy subjects and were scanned to obtain structural magnetic resonance images (MRI). We identified neuroanatomical differences between subjects with PANDAS and healthy controls using voxel-based morphometry, diffusion tensor imaging (DTI), and surface analysis. We investigated the usefulness of these neuroanatomical differences to classify patients with PANDAS using MVPA.

The pattern for the gray and white matter was significantly different between subjects with PANDAS and controls. Alterations emerged in the cortex, subcortex, and cerebellum. There were no significant group differences in DTI measures (fractional anisotropy, mean diffusivity, radial diffusivity, and axial diffusivity) or cortical features (thickness, sulci, volume, curvature, and gyrification). The overall accuracy of 75% was achieved using the gray matter features to classify patients with PANDAS and healthy controls.

The results of this integrative study allow a better understanding of the neural substrates in this OCD subtype, suggesting that the anatomical gray matter characteristics could have an immune origin that might be helpful in patient classification.

Bipolar disorder (BD) is one of the leading causes of disability worldwide. Patients are further disadvantaged by delays in accurate diagnosis ranging between 5 and 10 years. We applied Gaussian process classifiers (GPCs) to structural magnetic resonance imaging (sMRI) data to evaluate the feasibility of using pattern recognition techniques for the diagnostic classification of patients with BD.

GPCs were applied to gray (GM) and white matter (WM) sMRI data derived from two independent samples of patients with BD (cohort 1: n = 26; cohort 2: n = 14). Within each cohort patients were matched on age, sex and IQ to an equal number of healthy controls.

The diagnostic accuracy of the GPC for GM was 73% in cohort 1 and 72% in cohort 2; the sensitivity and specificity of the GM classification were respectively 69% and 77% in cohort 1 and 64% and 99% in cohort 2. The diagnostic accuracy of the GPC for WM was 69% in cohort 1 and 78% in cohort 2; the sensitivity and specificity of the WM classification were both 69% in cohort 1 and 71% and 86% respectively in cohort 2. In both samples, GM and WM clusters discriminating between patients and controls were localized within cortical and subcortical structures implicated in BD.

Our results demonstrate the predictive value of neuroanatomical data in discriminating patients with BD from healthy individuals. The overlap between discriminative networks and regions implicated in the pathophysiology of BD supports the biological plausibility of the classifiers.