Accepted for/Published in: JMIR AI
Date Submitted: Mar 12, 2023
Open Peer Review Period: Mar 12, 2023 - May 7, 2023
Date Accepted: Sep 7, 2023
(closed for review but you can still tweet)
Association of Healthcare Work with Anxiety and Depression During the COVID-19 Pandemic: A Structural Topic Modeling Study
ABSTRACT
Background:
Stressors for healthcare workers (HCW) during the COVID-19 pandemic have been manifold, with high levels of depression and anxiety alongside gaps in care. Research is needed to identify the factors most tied to healthcare workers’ mental health challenges.
Objective:
In this study, we utilized Natural Language Processing (NLP) to analyze de-identified treatment transcripts, identify emerging HCW concerns, and compare them to those of the general population. Treatment took place during the initial 2020 US wave of the COVID-19 pandemic (IQR: HCW=03/31-04/27; controls=4/5-4/27).
Methods:
We examined three weeks of digitally delivered psychotherapy from 820 HCW and 820 non-HCW matched controls. Depression was measured using Patient Health Questionnaire-9 and anxiety was measured using General Anxiety Disorder-7 completed during the initial assessment. Structural Topic Models (STM) were used to determine treatment topics and their association with anxiety and depression severity.
Results:
STM identified 4 treatment topics centered on healthcare and 5 on mental health for HCW. Several topics were significantly associated with moderate to severe anxiety and depression, including discussion of working on the hospital unit (EST=.035, 95%CI=±.013, p<.001), mood disturbances (EST=.014, 95%CI=±.012, p=.028), and sleep disturbances (EST=.016, 95%CI=±.014, p=.024). No significant associations emerged between pandemic-related topics and symptoms for controls.
Conclusions:
The study provides large-scale quantitative evidence that HCWs faced unique work-related challenges associated with anxiety and depression requiring dedicated treatment efforts. The study further demonstrates how NLP methods have the potential to surface clinically relevant markers of distress predictive of validated symptom rating scales. Clinical Trial: NA
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.