Estimation of malaria parasite reservoir coverage using reactive case detection and active community fever screening from census data with rapid diagnostic tests in southern Zambia: a re-sampling approach

Abstract

Background and methods: In areas where malaria transmission has been suppressed by vector control interventions many malaria control and elimination programmes are actively seeking new interventions to further reduce malaria prevalence, incidence and transmission. Malaria infection prevalence and incidence has been shown to cluster geographically, especially at lower transmission levels, and as such a reactive strategy is frequently used, by which index cases presenting to a passive surveillance system are used to target small areas for testing and treatment, reactive case detection (RCD), or focal drug administration (fDA). This study utilizes geo-located data from a census with parasitological testing with rapid diagnostic tests (RDTs) and treatment-seeking data collection conducted in southern Zambia to estimate the coverage of RCD or fDA in terms of the population and parasite reservoir as well as the operational requirements of such strategies, using a re-sampling algorithm developed exclusively for this purpose. This re-sampling algorithm allows for the specification of several parameters, such that different operational variants of these reactive strategies can be examined, including varying the search radius, screening for fever, or presumptive treatment (fDA).

Results: Results indicate that RCD, fDA and active fever screening followed by RCD, even with search radii over several hundered meters will only yield limited coverage of the RDT positive parasite reservoir during a short period. Long-term use of these strategies may increase this proportion. Reactive strategies detect a higher proportion of the reservoir of infections than random searches, but this effect appears to be greater in areas of low, but not moderate malaria prevalence in southern Zambia.

Discussion: Increases in the sensitivity of RDTs could also affect these results. The number of individuals and households that need to be searched increase rapidly, but approximately linearly with search radius.

Conclusions: Reactive strategies in southern Zambia yield improved identification of the parasite reservoir when targeted to areas with prevalence less than 10%. The operational requirements of delivering reactive strategies routinely are likely to prevent their uptake until prevalence falls far below this level.

Keywords: Active community fever screening; Case detection; Fever screening; Malaria; Reactive case detection; Resampling.

Fig. 1

Study area map. Map of study area showing households

Fig. 2

Schematic diagram of the reactive case detection re-sampling algorithm. Lowest level shows classification of individuals by measured infection status and identification by the system. False positives and false negatives are those whose parasite status in the original census data were expected to be misidentified by the reactive system

Fig. 3

Single simulation schematic result. Index cases shown in blue, searched areas shown with orange circles, households shown in gray, malaria infected individuals shown in red

Fig. 4

Reservoir detected vs. search radius and treatment seeking probability. a Proportion of reservoir detected vs. search radius. Treatment seeking is not simulated and is based on the data. b Proportion of reservoir detected vs. treatment seeking probability. Treatment seeking behavior is simulated amongst those reporting fever. Red line population aggregate, solid gray lines catchment areas with prevalence below the median (92/1000), dashed gray lines catchment areas with prevalence above the median (92/1000), blue line average over catchment areas. Field test sensitivity = 0.95, field test specificity = 0.80, P (treatment seeker is tested) = 0.90, P (RCD-selected household is covered) = 0.90, P (individual within RCD-selected household is covered) = 0.90

Fig. 5

Proportion of reservoir detected vs. prevalence

Fig. 6

Reservoir detected vs. proportion of population tested by treatment seeking probability. a Proportion of reservoir detected vs. proportion of population tested with treatment seeking probability of 0.80; b proportion of reservoir detected vs. proportion of population tested with treatment seeking probability of 0.20; red line population aggregate, solid grey lines catchment areas with prevalence below the median (92/1000), dashed grey lines catchment areas with prevalence above the median (92/1000), blue line average over catchment areas. Search radius varied from 1–1500 m, field test sensitivity = 0.95, field test specificity = 0.80, P (treatment seeker is tested) = 0.90, P (RCD-selected household is covered) = 0.90, P (individual within RCD-selected household is covered) = 0.90

Fig. 7

Proportion of reservoir detected vs. field test sensitivity. Red line population aggregate, solid grey lines catchment areas with prevalence below the median (92/1000), dashed grey lines catchment areas with prevalence above the median (92/1000), blue line average over catchment areas. Treatment seeking behavior sourced from data, search radius = 100m; field test specificity = 0.80; P (treatment seeker is tested) = 0.90; P (RCD-selected household is covered) = 0.90; P (individual within RCD-selected household is covered) = 0.90