Key result
Unsupervised clustering of resting-state EEG data identified five distinct neurophysiological subgroups of 12-year-olds that exhibited substantial differences in psychological distress, sleep quality, and cognitive function.
Why the study?
To better understand relationships between brain activity, cognitive function, and mental health risk in adolescence by identifying data-driven neurophysiological subgroups.
Cross-Sectional (n=59)
No
Data-driven clustering of resting-state EEG features can identify neurophysiological subgroups of adolescents with distinct patterns of mental health and cognitive function.
EEG subgroups may delineate adolescent mental health heterogeneity; hypothesis-generating, requires longitudinal validation before clinical use.
1 Abstract Introduction To better understand the relationships between brain activity, cognitive function and mental health risk in adolescence there is value in identifying data-driven subgroups based on measurements of brain activity and function, and then comparing cognition and mental health symptoms between such subgroups. Methods Here we implement a multi-stage analysis pipeline to identify data-driven clusters of 12-year-olds (M = 12.64, SD = 0.32) based on frequency characteristics calculated from resting state, eyes-closed electroencephalography (EEG) recordings. EEG data was collected from 59 individuals as part of their baseline assessment in the Longitudinal Adolescent Brain Study (LABS) being undertaken in Queensland, Australia. Applying multiple unsupervised clustering algorithms to these EEG features, we identified well-separated subgroups of individuals. To study patterns of difference in cognitive function and mental health symptoms between core clusters, we applied Bayesian regression models to probabilistically identify differences in these measures between clusters. Results We identified 5 core clusters which were associated with distinct subtypes of resting state EEG frequency content. EEG features that were influential in differentiating clusters included Individual Alpha Frequency, relative power in 4 Hz bands up to 16 Hz, and 95% Spectral Edge Frequency. Bayesian models demonstrated substantial differences in psychological distress, sleep quality and cognitive function between these clusters. By examining associations between neurophysiology and health measures across clusters, we have identified preliminary risk and protective profiles linked to EEG characteristics. Conclusion In this work we have developed a flexible and scaleable pipeline to identify subgroups of individuals in early adolescence on the basis of resting state EEG activity. These findings provide new clues about neurophysiological subgroups of adolescents in the general population, and associated patterns of health and cognition that are not observed at the whole group level. This approach offers potential utility in clinical risk prediction for mental and cognitive health outcomes throughout adolescent development.
No takes yet. Share an insight, caveat, or question.
Forbes et al. (2021) conducted a cross-sectional in Healthy adolescents (community sample) (n=59). EEG-based clusters (resting state EEG frequency characteristics) vs. Between-cluster comparisons was evaluated on Differences in psychological distress, sleep quality, and cognitive function between EEG-based clusters. Unsupervised clustering of resting-state EEG data identified five distinct neurophysiological subgroups of 12-year-olds that exhibited substantial differences in psychological distress, sleep quality, and cognitive function.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: