Integrating observational and modelled data to advance the understanding of heat stress effects on pregnant subsistence farmers in the gambia

Abstract

Studies on the effect of heat stress on pregnant women are scarce, particularly in highly vulnerable populations. To support the risk assessment of pregnant subsistence farmers in the West Kiang district, The Gambia we conducted a study on the pathophysiological effects of extreme heat stress and assessed the applicability of heat stress indices. From ERA5 climate reanalysis we added location-specific modelled solar radiation to datasets of a previous observational cohort study involving on-site measurements of 92 women working in the heat. Associations between physiological and environmental variables were assessed through Pearson correlation coefficient analysis, mixed effect linear models with random intercepts per participant and confirmatory composite analysis. We found Pearson correlations between r-values of 0 and 0.54, as well as independent effects of environmental variables on skin- and tympanic temperature, but not on heart rate, within a confidence interval of 98%. Pregnant women experienced stronger pathophysiological effects from heat stress in their third rather than in their second trimester. Environmental heat stress significantly altered maternal heat strain, particularly under humid conditions above a 50% relative humidity threshold, demonstrating interactive effects. Based on our results, we recommend including heat stress indices (e.g. UTCI or WBGT) in local heat-health warning systems.

Keywords: Climate change; Climate change adaptation; Heat strain; Heat stress; Humidity; Maternal health.

Fig. 1

Visual overview of variables used in data analysis (own representation).

Fig. 2

Heatmap indicating the strength of the Pearson correlation coefficients between variables as colour gradients. Denoted with (E) for environmental variables and (P) for physiological variables. P-values are contained in Supplementary Table 3. The dendrogram at the left side orders variables according to the similarity of their correlation with other variables.

Fig. 3

Interaction between air temperature and relative humidity in association with skin temperature at a threshold of 50% relative humidity. The skin temperature increases more rapidly with increasing temperature under conditions in which the relative humidity is above the 50% threshold.

Fig. 4

Composite confirmatory analysis with respective loadings of path coefficients between composite artefacts (heat stress and heat strain) and observable indicators (air temperature, relative humidity, black globe temperature, solar radiation, air velocity, metabolic rate, heart rate, skin temperature).