Factors associated with the performance and cost-effectiveness of using lymphatic filariasis transmission assessment surveys for monitoring soil-transmitted helminths: a case study in Kenya

Abstract

Transmission assessment surveys (TAS) for lymphatic filariasis have been proposed as a platform to assess the impact of mass drug administration (MDA) on soil-transmitted helminths (STHs). This study used computer simulation and field data from pre- and post-MDA settings across Kenya to evaluate the performance and cost-effectiveness of the TAS design for STH assessment compared with alternative survey designs. Variations in the TAS design and different sample sizes and diagnostic methods were also evaluated. The district-level TAS design correctly classified more districts compared with standard STH designs in pre-MDA settings. Aggregating districts into larger evaluation units in a TAS design decreased performance, whereas age group sampled and sample size had minimal impact. The low diagnostic sensitivity of Kato-Katz and mini-FLOTAC methods was found to increase misclassification. We recommend using a district-level TAS among children 8-10 years of age to assess STH but suggest that key consideration is given to evaluation unit size.

Figure 1.

Baseline prevalence of soil-transmitted helminths (STHs) in coastal and western regions of Kenya in 2012. Schools surveyed in post-mass drug administration (MDA) follow-up are shown with a solid outline. District boundaries correspond to “old districts” from 2004 used as lymphatic filariasis (LF) implementation units.

Figure 2

Infection prevalence: 1) by age group and semivariograms; 2) of (a) Hookworm, (b) Ascaris lumbricoides, and (c) Trichuris trichiura pre- mass drug administration (MDA) (light) and post-MDA (dark). The lower sill (point at which the semivariogram plateaus, indicating maximum value where there is still spatial structure) to nugget (minimum value at which spatial structure is present) ratio indicates less spatial structure following MDA, although these data are based on only 60 schools.

Figure 3.

District prevalence estimates versus true prevalence estimates across all 1,000 realizations for different sampling strategies. (A) and (C) represent results using districts as evaluation unit (EU) in a pre-mass drug administration (MDA) (A) and post-MDA (C) setting, whereas (B) and (D) represent results using aggregated districts as EU in a pre-MDA (B) and post-MDA (D) setting. Light blue points represent a standard survey method of 50 children from five schools per district, orange points a TAS method using 8–10 year olds, dark blue points a transmission assessment survey (TAS) method using 6–7 year olds and gray points the WHO recommended approach using ecological zones as EUs. Dashed lines represent perfect correspondence.

Figure 4.

The proportion of districts correctly classified according to the true district prevalence in a pre-mass drug administration (MDA) (A) and post-MDA (B) settings. Light blue lines represent a transmission assessment survey (TAS) design using 8–10 year olds, orange represents a TAS design using 6–7 year olds and dark blue represents a standard soil-transmitted helminth (STH) design of 50 randomly selected children from five schools per district. Red lines represent an aggregated TAS design in 8–10 year olds and grey lines represent a design using five schools per ecological zone. Only categories with > 50 simulations were included to reduce random error.

Figure 5.

Boxplots illustrating the relationship between the area of a transmission assessment survey (TAS) evaluation unit (EU), divided into quintiles, and performance of a TAS survey design that samples 308 children aged 8–10 years, in terms of the proportion of districts correctly classified in pre- (A) and post-mass drug administration (MDA) (B) contexts. Plots include the results from district-level and aggregated EUs. As performance was strongly associated with soil-transmitted helminth (STH) prevalence in pre-MDA settings, but not post-MDA settings, boxplots in (A) display the residual variation in performance by EU area, after adjusting for true prevalence.

Figure 6.

Smoothed estimates of the proportion of times each district was correctly classified in a given true prevalence class in pre-mass drug administration (MDA) (A) and post-MDA (B) settings using a district-level transmission assessment survey (TAS) design in children aged 8–10 years. Polygons correspond to the upper and lower sensitivity estimates for Kato-Katz (blue) and mini-FLOTAC (pink) using a total sample size of 100 or 500. The grey line represents the proportion of districts correctly classified using TAS decision rules, based on the midpoint sensitivity estimate for Kato-Katz and a sample size of 308. Only categories with > 50 simulations were included to reduce random error.