Hot spot or not: a comparison of spatial statistical methods to predict prospective malaria infections

Abstract

Background: Within affected communities, Plasmodium falciparum infections may be skewed in distribution such that single or small clusters of households consistently harbour a disproportionate number of infected individuals throughout the year. Identifying these hotspots of malaria transmission would permit targeting of interventions and a more rapid reduction in malaria burden across the whole community. This study set out to compare different statistical methods of hotspot detection (SaTScan, kernel smoothing, weighted local prevalence) using different indicators (PCR positivity, AMA-1 and MSP-1 antibodies) for prediction of infection the following year.

Methods: Two full surveys of four villages in Mwanza, Tanzania were completed over consecutive years, 2010-2011. In both surveys, infection was assessed using nested polymerase chain reaction (nPCR). In addition in 2010, serologic markers (AMA-1 and MSP-119 antibodies) of exposure were assessed. Baseline clustering of infection and serological markers were assessed using three geospatial methods: spatial scan statistics, kernel analysis and weighted local prevalence analysis. Methods were compared in their ability to predict infection in the second year of the study using random effects logistic regression models, and comparisons of the area under the receiver operating curve (AUC) for each model. Sensitivity analysis was conducted to explore the effect of varying radius size for the kernel and weighted local prevalence methods and maximum population size for the spatial scan statistic.

Results: Guided by AUC values, the kernel method and spatial scan statistics appeared to be more predictive of infection in the following year. Hotspots of PCR-detected infection and seropositivity to AMA-1 were predictive of subsequent infection. For the kernel method, a 1 km window was optimal. Similarly, allowing hotspots to contain up to 50% of the population was a better predictor of infection in the second year using spatial scan statistics than smaller maximum population sizes.

Conclusions: Clusters of AMA-1 seroprevalence or parasite prevalence that are predictive of infection a year later can be identified using geospatial models. Kernel smoothing using a 1 km window and spatial scan statistics both provided accurate prediction of future infection.

Figure 1

Location of study site within Tanzania (inset map) and clustering of malaria infection using different methods. (A) derived from SaTScan (coldspot significantly lower infection, hotspot significantly greater infection), (B) derived from Kernel and (C) derived from Weighted Local Prevalence.

Figure 2

Clustering of sero-positivity to AMA-1 in 2010 using SaTScan and kernel Method. Clustering of sero-positivity to AMA-1 in 2010 using (A) SaTScan and (B) kernel with a 1 km radius.