Parasite associations predict infection risk: incorporating co-infections in predictive models for neglected tropical diseases

Abstract

Background: Schistosomiasis and infection by soil-transmitted helminths are some of the world's most prevalent neglected tropical diseases. Infection by more than one parasite (co-infection) is common and can contribute to clinical morbidity in children. Geostatistical analyses of parasite infection data are key for developing mass drug administration strategies, yet most methods ignore co-infections when estimating risk. Infection status for multiple parasites can act as a useful proxy for data-poor individual-level or environmental risk factors while avoiding regression dilution bias. Conditional random fields (CRF) is a multivariate graphical network method that opens new doors in parasite risk mapping by (i) predicting co-infections with high accuracy; (ii) isolating associations among parasites; and (iii) quantifying how these associations change across landscapes. Methods: We built a spatial CRF to estimate infection risks for Ascaris lumbricoides, Trichuris trichiura, hookworms (Ancylostoma duodenale and Necator americanus) and Schistosoma mansoni using data from a national survey of Rwandan schoolchildren. We used an ensemble learning approach to generate spatial predictions by simulating from the CRF's posterior distribution with a multivariate boosted regression tree that captured non-linear relationships between predictors and covariance in infection risks. This CRF ensemble was compared against single parasite gradient boosted machines to assess each model's performance and prediction uncertainty. Results: Parasite co-infections were common, with 19.57% of children infected with at least two parasites. The CRF ensemble achieved higher predictive power than single-parasite models by improving estimates of co-infection prevalence at the individual level and classifying schools into World Health Organization treatment categories with greater accuracy. The CRF uncovered important environmental and demographic predictors of parasite infection probabilities. Yet even after capturing demographic and environmental risk factors, the presences or absences of other parasites were strong predictors of individual-level infection risk. Spatial predictions delineated high-risk regions in need of anthelminthic treatment interventions, including areas with higher than expected co-infection prevalence. Conclusions: Monitoring studies routinely screen for multiple parasites, yet statistical models generally ignore this multivariate data when assessing risk factors and designing treatment guidelines. Multivariate approaches can be instrumental in the global effort to reduce and eventually eliminate neglected helminth infections in developing countries.

Species associations in arthropod ectoparasite infracommunities are spatially and temporally variable and affected by environmental factors

“…This suggests that environmental factors may enhance or suppress the occurrence and/or strength of both positive and negative interspecific interactions (Kraft et al, 2015). Environmental effects on species interactions are well known and have been found in various free-living (Brooker et al, 2008;Dhondt, 2010;Milazzo et al, 2012) and parasitic (Brooker & Clements, 2009;Brooker et al, 2012;Krasnov et al, 2019;Clark et al, 2020) taxa. The most likely reasons behind this are ectoparasite species' either similar or differential environmental preferences and ranges of environmental tolerance.…”

“…If an edge between a pair of species in the resultant graph is absent, then these species are conditionally independent of each other. The presence of an edge suggests that the two species are conditionally associated, while the possible effects of all other species are controlled for (Clark et al, 2020). The application of MRF in community ecology has been strengthened by introducing the possibility of incorporating covariates (conditional random fields, CRF; Sutton & McCallum, 2011), with the aim of assessing variation in the occurrence probabilities across environmental gradients (Clark et al, 2018).…”

“…The MRF approach has been successfully applied to investigate pathogenic parasite co-infection patterns and their spatial variation (Clark et al, 2018(Clark et al, , 2020Fountain-Jones et al, 2020; see also Brian & Aldridge, 2021 for recent application of the MRF to parasite communities in freshwater mussels). Here, we applied a Markov random fields (MRF) modelling approach to understand whether and how species associations in ectoparasite (flea and gamasid mite) infracommunities, harboured by small mammals in Western Siberia, vary along environmental gradients across space and time.…”

Retrospective analysis and time series forecasting with automated machine learning of ascariasis, enterobiasis and cystic echinococcosis in Romania

“…Time series forecasting is mainly performed for infectious diseases, such as influenza [50][51][52][53][54][55]; hand, foot and mouth disease [56][57][58][59] and tuberculosis [60][61][62]. There is little forecasting of parasitic NTD in the current literature [63]. In addition, most time series analyses have employed only a few predictive models [49].…”

Soil-Transmitted Helminth Vaccines: Are We Getting Closer?

“…Coinfections with two or multiple STHs are extremely common in sub-Saharan Africa and elsewhere in the developing countries ( 1 , 81 ). The three STHs hookworm, Ascaris and Trichuris also share highly conserved antigens that are likely to have very similar biological functions ( 46 ).…”