Impact of climate and public health interventions on the COVID-19 pandemic: a prospective cohort study

Abstract

Background: It is unclear whether seasonal changes, school closures or other public health interventions will result in a slowdown of the current coronavirus disease 2019 (COVID-19) pandemic. We aimed to determine whether epidemic growth is globally associated with climate or public health interventions intended to reduce transmission of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).

Methods: We performed a prospective cohort study of all 144 geopolitical areas worldwide (375 609 cases) with at least 10 COVID-19 cases and local transmission by Mar. 20, 2020, excluding China, South Korea, Iran and Italy. Using weighted random-effects regression, we determined the association between epidemic growth (expressed as ratios of rate ratios [RRR] comparing cumulative counts of COVID-19 cases on Mar. 27, 2020, with cumulative counts on Mar. 20, 2020) and latitude, temperature, humidity, school closures, restrictions of mass gatherings, and measures of social distancing during an exposure period 14 days previously (Mar. 7 to 13, 2020).

Results: In univariate analyses, there were no associations of epidemic growth with latitude and temperature, but weak negative associations with relative humidity (RRR per 10% 0.91, 95% confidence interval [CI] 0.85-0.96) and absolute humidity (RRR per 5 g/m³ 0.92, 95% CI 0.85-0.99). Strong associations were found for restrictions of mass gatherings (RRR 0.65, 95% CI 0.53-0.79), school closures (RRR 0.63, 95% CI 0.52-0.78) and measures of social distancing (RRR 0.62, 95% CI 0.45-0.85). In a multivariable model, there was a strong association with the number of implemented public health interventions (p for trend = 0.001), whereas the association with absolute humidity was no longer significant.

Interpretation: Epidemic growth of COVID-19 was not associated with latitude and temperature, but may be associated weakly with relative or absolute humidity. Conversely, public health interventions were strongly associated with reduced epidemic growth.

Figure 1:

Study design. Δ = difference between day 1 of exposure period and day 1 of follow-up period.

Figure 2:

Caterpillar plot presenting results of univariate analyses. Shown are ratios of rate ratios (RRRs) with 95% confidence intervals (CI) and 2-sided p values. The p value for number of public health interventions is a p value for trend. Reference categories are no public health intervention for number of public health interventions, and Asia for major geographical regions. An RRR of 0.62, for example, indicates a 38% relative reduction in epidemic growth. Note: GDP = gross domestic product.

Figure 3:

Bubble plot of epidemic growth against the number of public health interventions (0, 1, or 2 or more). Each bubble represents a geopolitical area, with the size of the bubble proportional to the weight of the geopolitical area in weighted random-effects regression with inverse-variance weights. Box and whisker plots: the box represents median and interquartile range; whiskers the most extreme values within 1.5 times of the interquartile range beyond the 25th and 75th percentile. The p value for trend is from univariate weighted random-effects regression (see Figure 2). A rate ratio of 2, for example, indicates that the cumulative case count in a geopolitical area doubled within 1 week; a rate ratio of 3 indicates that it tripled.

Figure 4:

Caterpillar plot presenting results of the main parsimonious multivariable model. Shown are ratios of rate ratios (RRRs) with 95% confidence intervals (CIs) and 2-sided p values. The variables presented are those included in the parsimonious model. The p value for number of public health interventions is a p value for trend. Reference categories are no public health intervention for number of public health interventions, and Asia for major geographical regions. An RRR of 0.70, for example, indicates a 30% relative reduction in epidemic growth. Note: GDP = gross domestic product.