Mental Health in COVID-19 Pandemic: A Meta-Review of Prevalence Meta-Analyses

Abstract

Background: Mental health burden has been massively reported during the COVID-19 pandemic period. Aiming to summarise these data, we present a meta-review of meta-analyses that evaluated the impact of COVID-19 pandemic on anxiety, depressive and stress symptoms, psychological distress, post-traumatic stress disorder/symptoms (PTSD), and sleep disturbance, reporting its prevalence on general public (GP) and health care workers (HCW). Methods: A search was performed in the PubMed, EMBASE, and the Web of Science. Sleep disturbances, psychological distress, stress, and burnout were grouped as "Psychophysiological stress," and anxiety, depression, and PTSD were grouped as "Psychopathology." A random-effects model, calculating the pooled prevalence together with 95% confidence interval was performed for each domain. Subgroup analyses were performed for each population type (GP and HCW) and for each mental health outcome. For anxiety and depression, subgroup analysis for population type was performed. Heterogeneity is reported as I ². Publication bias was assessed through visual inspection of the funnel plot, and further tested by Egger's test and trim and fill analyses. Results: A total of 18 meta-analyses were included. The prevalence of psychophysiological stress was 31.99% (CI: 26.88-37.58, I ² = 99.9%). HCW showed a higher prevalence (37.74%, CI: 33.26-42.45, I ² = 99.7%) than the GP (20.67%, 15.07-27.66, I ² = 99.9%). The overall prevalence of insomnia, psychological distress, and stress were, respectively, 32.34% (CI: 25.65-39.84), 28.25% (CI: 18.12-41.20), and 36% (CI: 29.31-43.54). Psychopathology was present at 26.45% (CI: 24.22-28.79, I ² = 99.9%) of the sample, with similar estimates for population (HCW 26.14%, CI: 23.37-29.12, I ² = 99.9%; GP: 26.99%, CI: 23.41-30.9, I ² = 99.9%). The prevalence of anxiety, depression, and PTSD was 27.77% (CI: 24.47-31.32), 26.93% (CI: 23.92-30.17), and 20% (CI: 15.54-24.37), respectively. Similar proportions between populations were found for anxiety (HCW = 27.5%, CI: 23.78-31.55; GP = 28.33%, CI: 22.1-35.5) and depression (HCW = 27.05%, CI: 23.14-31.36; GP = 26.7%, CI: 22.32-31.59). Asymmetry in the funnel plot was found, and a slight increase in the estimate of overall psychopathology (29.08%, CI: 26.42-31.89) was found after the trim and fill analysis. Conclusions: The prevalence of mental health problems ranged from 20 to 36%. HCW presented a higher prevalence of psychophysiological stress than the general population. Systematic Review Registration:https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=252221, identifier: CRD42021252221.

Keywords: COVID-19; anxiety; depression; general public; healthcare worker.

Figure 1

PRISMA diagram summarizing the records retrieval and workflow.

Figure 2

Pooled prevalence for psychophysiological stress by outcomes (upper) and by population type (lower). In the upper panel, squares represent the overall estimate prevalence for each outcome without specifying the population. In the lower panel, squares represent the overall estimate prevalence for each population without specifying the outcome. In both cases, diamonds represent the overall prevalence for the psychophysiological stress domain. GP, general public; HCW, health care workers.

Figure 3

Pooled prevalence for psychopathology by outcomes (upper) and by population type (lower). In the upper panel, squares represent the overall estimate prevalence for each outcome without specifying the population. In the lower panel, squares represent the overall estimate prevalence for each population without specifying the outcome. In both cases, diamonds represent the overall prevalence for the psychopathology domain. PTSD, post-traumatic stress disorder; GP, general public; HCW, health care workers.