Accepted for/Published in: JMIR Mental Health
Date Submitted: Aug 12, 2021
Date Accepted: Oct 20, 2021
Date Submitted to PubMed: Oct 27, 2021
Machine Learning-based Predictive Modelling of Anxiety and Depressive Symptoms During Eight Months of the COVID-19 Global Pandemic: Repeated Cross-Sectional Survey Study
ABSTRACT
Background:
The COVID-19 global pandemic has increased the burden of mental illness on Canadian adults. However, the complex combination of demographic, economic, lifestyle, and perceived health risks contributing to patterns of anxiety and depression have not been explored.
Objective:
To harness flexible machine learning methods to identify constellations of factors related to symptoms of mental illness, and to understand their changes over time during the COVID-19 pandemic.
Methods:
Cross-sectional samples of Canadian adults (≥18yrs) completed online surveys in six waves, May–Dec 2020 (n=6,021), using quota sampling strategies to match the English-speaking Canadian population on age, gender, and region. Surveys measured anxiety and depression symptoms, socio-demographics, substance use, and perceived COVID-19 risks and worries. First, principal components analysis was used to condense highly comorbid anxiety and depression symptoms into a single data-driven measure of emotional distress. Second, eXtreme Gradient Boosting (XGBoost), a machine learning algorithm that can model non-linear and interactive relationships, was used to regress this measure on all included explanatory variables. Variable importance and effects across time were explored using SHapley Additive exPlanations (SHAP).
Results:
PCA of responses to nine anxiety and depression questions on an ordinal scale revealed a primary latent factor, termed “emotional distress”, explaining 76% of variation in all nine measures. Our XGBoost model explained a substantial proportion of variance in emotional distress (r2=0.39). The three most important items predicting elevated emotional distress were increased worries about finances (SHAP=0.17), worries about getting COVID-19 (0.17), and younger age (0.13). Hopefulness was associated with emotional distress and moderated the impacts of several other factors. Predicted emotional distress exhibited a non-linear pattern over time, with highest predicted symptoms in May and November, and lowest in June.
Conclusions:
Our results highlight factors which may exacerbate emotional distress during the current and possible future pandemics, including a role of hopefulness in moderating distressing effects of other factors. The pandemic disproportionately affected emotional distress among younger adults and those economically impacted. Clinical Trial: N/A
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.