Send to

Choose Destination
CNS Spectr. 2018 Nov 15:1-11. doi: 10.1017/S1092852918001268. [Epub ahead of print]

Neuroanatomical features and its usefulness in classification of patients with PANDAS.

Author information

1Genomics of Psychiatric and Neurodegenerative Diseases Laboratory,National Institute of Genomic Medicine (INMEGEN),Mexico City,Mexico.
2Neuroimaging Laboratory, Department of Electrical Engineering,Autonomous Metropolitan University,Mexico City,Mexico.
3Departament of Biomedical Systems, Engineering Faculty,National Autonomous University of Mexico,Mexico City,Mexico.
4Carracci Medical Group,Mexico City,Mexico.
6National Institute of Neurology and Neurosurgery "Manuel Velasco Suárez",Mexico City,Mexico.



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.


MRI; PANDAS; early-onset OCD; gaussian process classifiers; gray matter; machine learning; multivariate pattern analysis


Supplemental Content

Full text links

Icon for Cambridge University Press
Loading ...
Support Center