Baseline patterns of infection in regions of Benin, Malawi and India seeking to interrupt transmission of soil transmitted helminths (STH) in the DeWorm3 trial

Abstract

Global efforts to control morbidity associated with soil-transmitted helminth infections (STH) have focused largely on the targeted treatment of high-risk groups, including children and pregnant women. However, it is not clear when such programs can be discontinued and there are concerns about the sustainability of current STH control programs. The DeWorm3 project is a large multi-country community cluster randomized trial in Benin, India and Malawi designed to determine the feasibility of interrupting the transmission of STH using community-wide delivery of mass drug administration (MDA) with anthelmintics over multiple rounds. Here, we present baseline data and estimate key epidemiological parameters important in determining the likelihood of transmission interruption in the DeWorm3 trial. A baseline census was conducted in October-December 2017 in India, November-December 2017 in Malawi and in January-February 2018 in Benin. The baseline census enumerated all members of each household and collected demographic data and information on occupation, assets, and access to water, sanitation and hygiene (WASH). Each study site was divided into 40 clusters of at least 1,650 individuals per cluster. Clusters were randomized to receive twice yearly community-wide MDA with albendazole (GSK) targeting eligible individuals of all ages (20 clusters), or to receive the standard-of-care deworming program targeting children provided in each country. In each site, a randomly selected group of 150 individuals per cluster (6,000 total per site) was selected from the baseline census using stratified random sampling, and each individual provided a single stool sample for analysis of STH infection using the Kato-Katz technique. Study site, household and individual characteristics were summarized as appropriate. We estimated key epidemiological parameters including the force of infection and the degree of parasite aggregation within the population. The DeWorm3 sites range in population from 94,969 to 140,932. The population age distribution varied significantly by site, with the highest proportion of infants and young children in Malawi and the highest proportion of adults in India. The baseline age- and cluster-weighted prevalence, as measured by Kato-Katz, varied across sites and by species, Baseline hookworm prevalence in India was 21.4% (95% CI: 20.4-22.4%), while prevalence of Ascaris and Trichuris by Kato-Katz was low (0.1% and 0.3% overall). In Malawi, the overall age- and cluster-weighted STH prevalence was 7.7% (95% CI: 7.1-8.4%) predominantly driven by hookworm infections (7.4%) while Ascaris (0.1%) and Trichuris (0.3%) infections were rare. In Benin, the overall age- and cluster-weighted prevalence was significantly lower (5.6%, 95% CI: 5.1-6.2%) and Ascaris (2.0%, 95% CI: 1.6-2.3%) was more common than in other sites. Ascaris infections were more likely to be moderate- or heavy-intensity (43.7%, unweighted) compared to hookworm (5.0%). The force of infection for hookworm was highest in adults in India and Malawi but appeared relatively stable across age groups in Benin. These data demonstrate the significant variability between the sites in terms of demography, socio-economic status and environmental characteristics. In addition, the baseline prevalence and intensity data from DeWorm3 suggest that each site has unique epidemiologic characteristics that will be critical in determining correlates of achieving STH transmission interruption in the DeWorm3 trial. Trial registration: The trial was registered at ClinicalTrials.gov (NCT03014167).

Fig 1

Maps of study sites in India (A-B), Malawi (C) and Benin (D) with cluster boundaries and GPS locations of all households in the Baseline Census overlaid (ArcGIS).

Fig 2

Population pyramids showing five-year bands of age (where available) and gender breakdown of the Baseline Census populations in India (A), Malawi (B) and Benin (C). These participants were broadly categorized as pre-school age children (PSAC, <5 years of age), school age children (SAC, 5–14 years) and adults (15+). In all figures, red represents the female population and blue represents males.

Fig 3

Age- and cluster-weighted (A) prevalence estimates of infection and (B) prevalence of moderate- or heavy-intensity of infection. Weighted estimates account for the stratified sampling approach by age (stage 1) and cluster (stage 2). Cluster-specific age-weighted prevalences (Pr_cw) were calculated by taking sum of the age-specific prevalences (Pr_PSAC, Pr_SAC or Pr_adult) multiplied by the proportion (Prop) of that age group for each cluster among those 1+ years old (Pr_cw = Pr_PSAC*Prop_PSAC+Pr_SAC*Prop_SAC+Pr_Adult*Prop_Adult). The final age- and cluster-weighted prevalences (Pr_w) were calculated by taking the sum of the cluster-specific age-weighted prevalences multiplied by the proportion of the census population living in each cluster (Pr_w = Pr_c1w*Prop_c1+ Pr_c2w*Prop_c2 … Pr_c40w*Prop_c40)_. Error bars represent weighted Wilson 95% confidence intervals with design effect adjustment.

Fig 4

Fig 4A, C and E record the estimated total hookworm egg count in the human host population by 5-year age categories, projected from the negative binomial probability distribution for egg counts fitted to the sample data for India (A), Malawi (C) and Benin (E). Fig 4B, 4D and 4F record the estimated individual-level probability of heavy hookworm infection by 5-year age categories, calculated from the negative binomial distribution for egg counts fitted to the sample data for India (B), Malawi (D) and Benin (F). All error bars represent 95% credible intervals.

Fig 5

Fig 5A, 5C and 5E record the force of infection for hookworm (the per host rate of acquisition of worms per unit of time (year)) as a function of age, calculated from individual hookworm egg count data for India (A), Malawi (C) and Benin (E). Fig 5B, 5D and 5F show the cluster prevalence of infection plotted against the hookworm mean egg count for individual cluster samples. The curve represents the best fit of a negative binomial probability distribution relating the prevalence of infection to the mean egg count (S1 Text).

Fig 6

Fig 6A records the force of infection for Ascaris (the per host rate of acquisition of worms per unit of time (year)) as a function of age, calculated from individual Ascaris egg count data for Benin. Fig 6B shows the cluster prevalence plotted against the Ascaris mean egg count for individual cluster samples. The curve represents the best fit of a negative binomial probability distribution relating the prevalence of infection and the mean egg count (S1 Text).