English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the zaia usage as premium feature

ZAIA

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the access of premium content as premium feature

Premium Content

Zendy Tools

Zendy Open

Resting-state functional Magnetic Resonance Imaging (R-fMRI) holds thepromise to reveal functional biomarkers of neuropsychiatric disorders. However,extracting such biomarkers is challenging for complex multi-facetedneuropatholo-gies, such as autism spectrum disorders. Large multi-site datasetsincrease sample sizes to compensate for this complexity, at the cost ofuncontrolled heterogeneity. This heterogeneity raises new challenges, akin tothose face in realistic diagnostic applications. Here, we demonstrate thefeasibility of inter-site classification of neuropsychiatric status, with anapplication to the Autism Brain Imaging Data Exchange (ABIDE) database, a large(N=871) multi-site autism dataset. For this purpose, we investigate pipelinesthat extract the most predictive biomarkers from the data. These R-fMRIpipelines build participant-specific connectomes from functionally-definedbrain areas. Connectomes are then compared across participants to learnpatterns of connectivity that differentiate typical controls from individualswith autism. We predict this neuropsychiatric status for participants from thesame acquisition sites or different, unseen, ones. Good choices of methods forthe various steps of the pipeline lead to 67% prediction accuracy on the fullABIDE data, which is significantly better than previously reported results. Weperform extensive validation on multiple subsets of the data defined bydifferent inclusion criteria. These enables detailed analysis of the factorscontributing to successful connectome-based prediction. First, predictionaccuracy improves as we include more subjects, up to the maximum amount ofsubjects available. Second, the definition of functional brain areas is ofparamount importance for biomarker discovery: brain areas extracted from largeR-fMRI datasets outperform reference atlases in the classification tasks.

Deriving reproducible biomarkers from multi-site resting-state data: An Autism-based example