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/

Global: Zendy Plus annual

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

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Autism spectrum disorder (ASD) is a complex, pervasive, and heterogeneous neurodevelopmental condition with varying trajectories and significant male bias. In this study, we considered functional magnetic resonance images of four sets of participants: set (1) male and female participants with autism diagnostic observation schedule (ADOS) = 2–24, set (2) only male participants with ADOS = 2–24, set (3) male and female participants with ADOS C 10 and set (4) only male participants with ADOS C 10. We matched the typical developing (TD) and ASD (N = 160 each for training model and N = 40 each for test) participants for age and head motion. All time series data were preprocessed using a standard pipeline. We extracted time series data from 237 regions of interest that has true values, and Pearson’s correlation was calculated to create a 237 9 237 matrix. Among these, the most informative features (brain connectivity) were identified on training samples through conditional random forest and the classifier model was built using random forest. Further, the performances of training model were verified in a test sample set. We obtained test accuracies of 62.5%, 65%, 70% and 73.75% for the set (1–4), respectively. Cingulo opercular task control (COTC) network contributed more number of features to achieve peak test accuracy. Moreover, we identified differences in dorsal attention (DA) to somatosensory motor hand in set (1), COTC to DA in set (2), within COTC in set (3) and COTC to default mode network in set (4) between ASD and TD. Overall, our findings suggest that severity exists in ASD participants; informative features and classification models vary with the gender and severity in varying samples of ASD.

RETRACTED ARTICLE: Classification of severe autism in fMRI using functional connectivity and conditional random forests