Predicting longitudinal anxiety in adolescents using mixed effects random forest regression
Poster No:
412
Submission Type:
Abstract Submission
Authors:
Paola Odriozola1, Amanda Baker1, Claire Waller1, Nancy Le1, Savannah Lopez1, Katie Bessette1, Lucina Uddin1, Tara Peris1, Adriana Galván1
Institutions:
1University of California Los Angeles, Los Angeles, CA
First Author:
Co-Author(s):
Introduction:
Adolescence is a peak time for the onset of psychiatric disorders, with anxiety disorders being the most common, affecting as many as 1 in 3 youths (Beesdo et al., 2009; Kessler et al., 2005). Despite its significant costs, understanding the factors that shape the persistence and remittance of anxiety over time remains limited. Using machine learning methods with longitudinal behavioral, clinical, and fMRI data from adolescents aged 9-14, we took a data-driven approach to investigate whether it was possible to predict whose anxiety will worsen, remain the same, or remit years later. We hypothesized that mixed effects random forest regression would enable prediction of anxiety outcomes with high precision, and that the functional connectivity of brain regions previously shown to be implicated in anxiety (e.g., amygdala, hippocampus, ventral striatum, insula, dorsal anterior cingulate cortex (dACC), medial prefrontal cortex (mPFC), and the default-mode network (DMN)) would be of highest importance in predicting anxiety outcomes.
Methods:
132 adolescent participants (61 F : 71 M; 11.4 ± 1.5 years at time 1) completed the Development of Anxiety in Youth Study (Galván & Peris, 2020), a prospective longitudinal study that occurred annually for 3 years. Participants completed a resting state fMRI scan, the Screen for Child Anxiety Related Disorders (SCARED) child report questionnaires (Birmaher et al., 1997), and demographic questionnaires at each visit. The regions of interest (ROIs) came from a functionally defined atlas (Seitzman et al., 2020), which expands on the atlas from Power et al. (2011) to include subcortical regions. To reduce the dimensionality of this analysis, we selected a subset of 53 ROIs from this atlas based on a recent meta-analysis of machine learning studies of anxiety disorders using fMRI data (Rezaei et al., 2023). We then computed the functional connectivity between each spherical ROI to generate a correlation matrix using AFNI FATCAT (Taylor & Saad, 2013). Next, we submitted scaled data to a stochastic mixed effects random forest regression analysis (sMERF) implemented in R using the LongituRF package (Capitaine et al., 2021). This package combines the feature selection aspects of random forests with an extension to include mixed-effects models to account for repeated measures for high-dimensional longitudinal data. We used a standard Ornstein-Uhlenbeck process which allows the covariance structure to vary over time (Capitaine et al., 2021). We used 80% of the data for training, and the other 20% for testing the model. The model contained 1086 predictors which included functional connectivity values, and demographic variables (i.e., age, sex at birth, race, ethnicity, family income, IQ, etc.) and the outcome of interest was child-reported SCARED total score. Prediction errors were calculated as root mean square error with 25 training/test set random splits.
Results:
Prediction of future anxiety symptoms using sMERF yielded a root mean square error of 0.97. The top 5 variables that yielded the highest relative importance (i.e., highest predictive value) in the model included (in order of relative importance): functional connectivity of (1) right posterior cingulate cortex and the right orbitofrontal cortex; (2) the left mPFC and the right mPFC; (3) the right insula and the right cerebellum; (4) the left insula and the right cerebellum; and (5) the right superior parietal lobe and the left cerebellum.
Conclusions:
Results from the present study suggest that resting functional connectivity between regions often overlooked in studies of anxiety-such as the cerebellum and the superior parietal lobe-as well as regions often included in studies of anxiety-such as the insula and mPFC-may play a large role in predicting anxiety over time. Increasing our understanding of factors that predict future anxiety symptoms across development is crucial for identifying new targets for intervention for youth struggling with anxiety.
Disorders of the Nervous System:
Psychiatric (eg. Depression, Anxiety, Schizophrenia) 1
Lifespan Development:
Early life, Adolescence, Aging
Modeling and Analysis Methods:
Classification and Predictive Modeling 2
Connectivity (eg. functional, effective, structural)
Novel Imaging Acquisition Methods:
BOLD fMRI
Keywords:
Anxiety
Development
DISORDERS
FUNCTIONAL MRI
Machine Learning
Psychiatric Disorders
1|2Indicates the priority used for review
Abstract Information
By submitting your proposal, you grant permission for the Organization for Human Brain Mapping (OHBM) to distribute your work in any format, including video, audio print and electronic text through OHBM OnDemand, social media channels, the OHBM website, or other electronic publications and media.
The Open Science Special Interest Group (OSSIG) is introducing a reproducibility challenge for OHBM 2025. This new initiative aims to enhance the reproducibility of scientific results and foster collaborations between labs. Teams will consist of a “source” party and a “reproducing” party, and will be evaluated on the success of their replication, the openness of the source work, and additional deliverables. Click here for more information. Propose your OHBM abstract(s) as source work for future OHBM meetings by selecting one of the following options:
Please indicate below if your study was a "resting state" or "task-activation” study.
Healthy subjects only or patients (note that patient studies may also involve healthy subjects):
Was this research conducted in the United States?
Are you Internal Review Board (IRB) certified? Please note: Failure to have IRB, if applicable will lead to automatic rejection of abstract.
Were any human subjects research approved by the relevant Institutional Review Board or ethics panel? NOTE: Any human subjects studies without IRB approval will be automatically rejected.
Were any animal research approved by the relevant IACUC or other animal research panel? NOTE: Any animal studies without IACUC approval will be automatically rejected.
Please indicate which methods were used in your research:
For human MRI, what field strength scanner do you use?
Which processing packages did you use for your study?
Provide references using APA citation style.
Beesdo, K., Knappe, S., & Pine, D. S. (2009). Anxiety and Anxiety Disorders in Children and Adolescents: Developmental Issues and Implications for DSM-V. The Psychiatric Clinics of North America, 32(3), 483–524.
Birmaher, B., Khetarpal, S., Brent, D., Cully, M., Balach, L., Kaufman, J., & Neer, S. M. (1997). The Screen for Child Anxiety Related Emotional Disorders (SCARED): Scale Construction and Psychometric Characteristics. Journal of the American Academy of Child & Adolescent Psychiatry, 36(4), 545–553.
Capitaine, L., Genuer, R., & Thiébaut, R. (2021). Random forests for high-dimensional longitudinal data. Statistical Methods in Medical Research, 30(1), 166–184.
Galván, A., & Peris, T. S. (2020). The Development of Anxiety in Youth Study (DAYS): A Prospective Study of Trajectories of Brain Maturation among Youth at Risk for Anxiety †. Journal of Psychiatry and Brain Science, 4(3).
Kessler, R. C., Demler, O., Frank, R. G., Olfson, M., Pincus, H. A., Walters, E. E., Wang, P., Wells, K. B., & Zaslavsky, A. M. (2005). Prevalence and treatment of mental disorders, 1990 to 2003. N Engl J Med, 352(24), 2515–2523.
Power, J. D., Cohen, A. L., Nelson, S. M., Wig, G. S., Barnes, K. A., Church, J. A., Vogel, A. C., Laumann, T. O., Miezin, F. M., Schlaggar, B. L., & Petersen, S. E. (2011). Functional Network Organization of the Human Brain. Neuron, 72(4), 665–678.
Rezaei, S., Gharepapagh, E., Rashidi, F., Cattarinussi, G., Sanjari Moghaddam, H., Di Camillo, F., Schiena, G., Sambataro, F., Brambilla, P., & Delvecchio, G. (2023). Machine learning applied to functional magnetic resonance imaging in anxiety disorders. Journal of Affective Disorders, 342, 54–62.
Seitzman, B. A., Gratton, C., Marek, S., Raut, R. V., Dosenbach, N. U. F., Schlaggar, B. L., Petersen, S. E., & Greene, D. J. (2020). A set of functionally-defined brain regions with improved representation of the subcortex and cerebellum. NeuroImage, 206, 116290.
Taylor, P. A., & Saad, Z. S. (2013). FATCAT: (An Efficient) Functional And Tractographic Connectivity Analysis Toolbox. Brain Connectivity, 3(5), 523–535.