Agricultural land-uses consistently exacerbate infectious disease risks in Southeast Asia

Abstract

Agriculture has been implicated as a potential driver of human infectious diseases. However, the generality of disease-agriculture relationships has not been systematically assessed, hindering efforts to incorporate human health considerations into land-use and development policies. Here we perform a meta-analysis with 34 eligible studies and show that people who live or work in agricultural land in Southeast Asia are on average 1.74 (CI 1.47-2.07) times as likely to be infected with a pathogen than those unexposed. Effect sizes are greatest for exposure to oil palm, rubber, and non-poultry based livestock farming and for hookworm (OR 2.42, CI 1.56-3.75), malaria (OR 2.00, CI 1.46-2.73), scrub typhus (OR 2.37, CI 1.41-3.96) and spotted fever group diseases (OR 3.91, CI 2.61-5.85). In contrast, no change in infection risk is detected for faecal-oral route diseases. Although responses vary by land-use and disease types, results suggest that agricultural land-uses exacerbate many infectious diseases in Southeast Asia.

Fig. 1

PRISMA diagram. A flow chart of the study selection process

Fig. 2

Regional meta-analysis. Regional meta-analysis of mutually exclusive risk estimates to determine the association between occupational or residential exposure to agricultural land-use and infectious disease prevalence. Exposure to 'agriculture' is defined as a category where a person indicates they work or live in or near agriculture regardless of the type of agriculture. Square points show the crude odds ratio for each study, solid diamonds show the pooled meta-analysis estimates and error bars are defined as the 95% confidence interval. Note: Q, the Cochrane Q-test. Df, degrees of freedom. p, p-value. I², test for heterogeneity. RE, random effects

Fig. 3

Funnel plot for the regional meta-analysis. A plot of the logarithmic risk estimates vs. the precision (standard error) for each study, with adjustment using the trim and fill method. Closed circles denote identified studies and their summary measures, respectively. Open circles represent missing studies after adjustment for funnel plot asymmetry and the summary measure incorporating hypothetical studies, respectively. Key areas of statistical significance have been superimposed on the funnel, and the plot is now centred at zero. The yellow zones show effects between p = 0.10 and p = 0.05, and the orange zones show effects between p = 0.05 and p = 0.01. Effects in the white zone are greater than p = 0.10 and effects in the grey zones are smaller than p = 0.01. A Z-test was conducted to calculate p-values

Fig. 4

Sensitivity analysis of the regional meta-analysis. A priori subgroups based on study characteristics to test the sensitivity of the regional meta-analysis. Results suggest that subgroups based on study characteristics do not significantly alter the direction of the association between occupational or residential exposure to agricultural land-use and infectious disease prevalence. Circle points show the pooled subgroup estimates and error bars are defined as the 95% confidence interval. Note: n, number of studies included in each pooled estimate. CI, confidence intervals. OHAT, Office of Health Assessment and Translation. NHLBI, National Heart, Lung and Blood Institute

Fig. 5

Agricultural exposure-based subgroup analysis. Subgroups were created a priori based on exposures that had two or more mutually exclusive estimates. Agriculture (non-specific) is defined as a category where a person indicates they work in agriculture regardless of the type of agriculture. Square points show the pooled subgroup estimates and error bars are defined as the 95% confidence interval

Fig. 6

Livestock exposure-based subgroup analysis. Livestock farming is defined as a category where a person indicates they are exposed to livestock generally regardless of the specific type of livestock (e.g., chickens). Porcine, Bovine or Poultry exposure is defined as a person being exposed to each of these respective animal types. Square points show the pooled subgroup estimates and error bars are defined as the 95% confidence interval

Fig. 7

Disease-based subgroup analysis. Subgroups were created a priori based on diseases that had two or more mutually exclusive estimates. Orientia tsutsugamushi is also known as Scrub typhus. Rickettsia typhi is otherwise known as murine typhus. Opisthorchis viverrini is also known as Opisthorchiasis. Square points show the pooled subgroup estimates and error bars are defined as the 95% confidence interval