Data-Driven Identification of Brain-Behavioral and Sociodemographic Predictors of Anxiety Severity in Children Using
Ann M Iturra-Mena1, Melanie Wall1, Sherry Y H Chen1
1Columbia University, New York, New York.
Insights
Machine learning identified key predictors of childhood anxiety, including neural markers like error positivity (Pe) and frontal theta power, alongside sociodemographic factors such as single-mother status. These findings reveal interactions influencing anxiety severity in children.
Area of Science:
- Neuroscience
- Developmental Psychology
- Machine Learning
Background:
- Childhood anxiety is common and linked to cognitive control issues and sociodemographic risks.
- The interplay between these factors in childhood anxiety remains poorly understood.
- A data-driven approach is needed to identify key predictors.
Purpose of the Study:
- To employ machine learning to pinpoint the most significant neural, behavioral, and sociodemographic predictors of childhood anxiety severity.
- To investigate interactions between these predictors.
Main Methods:
- 181 children (4-10 years) with anxiety data from prior studies were analyzed.
- Electroencephalogram (EEG) and behavioral data from a Go/NoGo task assessed cognitive control.
- Machine learning models (Random Forest, SVR, XGBoost) identified predictors and interactions.
Main Results:
- Random Forest achieved the highest prediction accuracy.
- Error positivity (Pe), single-mother status, frontal theta power, post-error accuracy, and occipital post-error alpha power were key predictors.
- Single-mother status moderated the effect of post-error alpha power on anxiety.
- Low frontal theta power amplified the association between Pe and anxiety.
Conclusions:
- A combination of cognitive control neural markers, behavioral performance, and sociodemographic factors, particularly single-mother status, significantly predicts childhood anxiety.
- Understanding these interactions is crucial for targeted diagnosis and treatment strategies.
- This study offers insights beyond traditional hypothesis-driven research in childhood anxiety.
Objective:
Childhood anxiety is highly prevalent and linked to cognitive control deficits and sociodemographic risk factors. However, how these factors contribute and interact remain unclear. This study used a data-driven machine learning approach to identify the strongest neural, behavioral, and sociodemographic predictors of childhood anxiety severity.
Method:
A sample of 181 children (aged 4-10 years) was drawn from 3 studies examining anxiety and error monitoring. Anxiety severity was assessed using the Child Behavior Checklist DSM-Oriented Anxiety Scale. Predictors included cognitive control markers derived from electroencephalogram recordings and behavioral measures, both obtained during a Go/NoGo task, along with sociodemographic risk factors. Random Forest, Support Vector Regression, and XGBoost models were compared using cross-validation. Partial dependence plots were used to examine predictor-outcome relationships, and interactions were analyzed using H-statistic.
Results:
Random Forest yielded optimal prediction accuracy. Error positivity (Pe) emerged as the strongest predictor, followed by single-mother status, frontal theta power, post-error accuracy, and occipital post-error alpha power. Single-mother status strengthened the relationship between post-error alpha power and anxiety, indicating that impaired post-error attentional mechanisms may be more pronounced in anxious children from single-mother households. Low frontal theta power amplified the Pe-anxiety relationship, suggesting that reduced inhibitory control may intensify anxiety-related error awareness.
Conclusion:
A specific interaction among neural indices of cognitive control (Pe, frontal theta, occipital post-error alpha), behavioral performance (post-error accuracy), and a sociodemographic factor (single/unpartnered mother) predicted childhood anxiety. These findings highlight the importance of considering both neural mechanisms and environmental context in guiding diagnosis and treatment, offering insights beyond traditional hypothesis-driven approaches.
Diversity & Inclusion Statement:
We worked to ensure sex and gender balance in the recruitment of human participants. We worked to ensure race, ethnic, and/or other types of diversity in the recruitment of human participants. We worked to ensure that the study questionnaires were prepared in an inclusive way. One or more of the authors of this paper self-identifies as a member of one or more historically underrepresented racial and/or ethnic groups in science. One or more of the authors of this paper self-identifies as living with a disability. One or more of the authors of this paper self-identifies as a member of one or more historically underrepresented sexual and/or gender groups in science. One or more of the authors of this paper received support from a program designed to increase minority representation in science.
More Related Videos
05:19Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
Published on: July 7, 2023
08:05Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
Published on: June 30, 2020