Publications

BibTex format

@article{Clark:2020:10.1186/s13071-020-04016-2,
author = {Clark, NJ and Owada, K and Ruberanziza, E and Ortu, G and Umulisa, I and Bayisenge, U and Mbonigaba, JB and Mucaca, JB and Lancaster, W and Fenwick, A and Magalhaes, RJS and Mbituyumuremyi, A},
doi = {10.1186/s13071-020-04016-2},
journal = {Parasites and Vectors},
pages = {1--16},
title = {Parasite associations predict infection risk: incorporating co-infections in predictive models for neglected tropical diseases},
url = {http://dx.doi.org/10.1186/s13071-020-04016-2},
volume = {13},
year = {2020}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - BackgroundSchistosomiasis 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.MethodsWe 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.ResultsParasite 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 probab
AU  - Clark,NJ
AU  - Owada,K
AU  - Ruberanziza,E
AU  - Ortu,G
AU  - Umulisa,I
AU  - Bayisenge,U
AU  - Mbonigaba,JB
AU  - Mucaca,JB
AU  - Lancaster,W
AU  - Fenwick,A
AU  - Magalhaes,RJS
AU  - Mbituyumuremyi,A
DO  - 10.1186/s13071-020-04016-2
EP  - 16
PY  - 2020///
SN  - 1756-3305
SP  - 1
TI  - Parasite associations predict infection risk: incorporating co-infections in predictive models for neglected tropical diseases
T2  - Parasites and Vectors
UR  - http://dx.doi.org/10.1186/s13071-020-04016-2
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000521104100001&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://parasitesandvectors.biomedcentral.com/articles/10.1186/s13071-020-04016-2
UR  - http://hdl.handle.net/10044/1/82702
VL  - 13
ER  -

Download

Professor Alan Fenwick OBE

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)