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 access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Research in machine learning for autism spectrum disorder (ASD)classification bears the promise to improve clinical diagnoses. However, recentstudies in clinical imaging have shown the limited generalization of biomarkersacross and beyond benchmark datasets. Despite increasing model complexity andsample size in neuroimaging, the classification performance of ASD remains faraway from clinical application. This raises the question of how we can overcomethese barriers to develop early biomarkers for ASD. One approach might be torethink how we operationalize the theoretical basis of this disease in machinelearning models. Here we introduced unsupervised graph representations thatexplicitly map the neural mechanisms of a core aspect of ASD, deficits indyadic social interaction, as assessed by dual brain recordings, termedhyperscanning, and evaluated their predictive performance. The proposed methoddiffers from existing approaches in that it is more suitable to capture socialinteraction deficits on a neural level and is applicable to young children andinfants. First results from functional near-infrared spectroscopy data indicatepotential predictive capacities of a task-agnostic, interpretable graphrepresentation. This first effort to leverage interaction-related deficits onneural level to classify ASD may stimulate new approaches and methods toenhance existing models to achieve developmental ASD biomarkers in the future.

Autism spectrum disorder classification based on interpersonal neural  synchrony: Can classification be improved by dyadic neural biomarkers using  unsupervised graph representation learning?