Predictive analysis across spatial scales links zoonotic malaria to deforestation

Patrick M. Brock, Kimberly M. Fornace, Matthew J. Grigg, Nicholas M. Anstey, Timothy William, Jon Cox, Chris J. Drakeley, Heather M. Ferguson, Rowland R. Kao

Research output: Contribution to journalArticleResearchpeer-review

Abstract

The complex transmission ecologies of vector-borne and zoonotic diseases pose challenges to their control, especially in changing landscapes. Human incidence of zoonotic malaria (Plasmodium knowlesi) is associated with deforestation although mechanisms are unknown. Here, a novel application of a method for predicting disease occurrence that combines machine learning and statistics is used to identify the key spatial scales that define the relationship between zoonotic malaria cases and environmental change. Using data from satellite imagery, a case - control study, and a cross-sectional survey, predictive models of household-level occurrence of P. knowlesi were fitted with 16 variables summarized at 11 spatial scales simultaneously. The method identified a strong and well-defined peak of predictive influence of the proportion of cleared land within 1 km of households on P. knowlesi occurrence. Aspect (1 and 2 km), slope (0.5 km) and canopy regrowth (0.5 km) were important at small scales. By contrast, fragmentation of deforested areas influenced P. knowlesi occurrence probability most strongly at large scales (4 and 5 km). The identification of these spatial scales narrows the field of plausible mechanisms that connect land use change and P. knowlesi, allowing for the refinement of disease occurrence predictions and the design of spatially-targeted interventions.

Original languageEnglish
Article number20182351
Pages (from-to)1-9
Number of pages9
JournalProceedings of the Royal Society B: Biological Sciences
Volume286
Issue number1894
DOIs
Publication statusPublished - 16 Jan 2019

Fingerprint

Plasmodium knowlesi
Deforestation
Spatial Analysis
malaria
Conservation of Natural Resources
Zoonoses
deforestation
spatial analysis
Malaria
disease occurrence
Satellite imagery
Ecology
regrowth
households
Land use
Satellite Imagery
satellite imagery
land use change
Learning systems
environmental change

Cite this

Brock, Patrick M. ; Fornace, Kimberly M. ; Grigg, Matthew J. ; Anstey, Nicholas M. ; William, Timothy ; Cox, Jon ; Drakeley, Chris J. ; Ferguson, Heather M. ; Kao, Rowland R. / Predictive analysis across spatial scales links zoonotic malaria to deforestation. In: Proceedings of the Royal Society B: Biological Sciences. 2019 ; Vol. 286, No. 1894. pp. 1-9.
@article{8e7c55b98a5e49658174697582e21639,
title = "Predictive analysis across spatial scales links zoonotic malaria to deforestation",
abstract = "The complex transmission ecologies of vector-borne and zoonotic diseases pose challenges to their control, especially in changing landscapes. Human incidence of zoonotic malaria (Plasmodium knowlesi) is associated with deforestation although mechanisms are unknown. Here, a novel application of a method for predicting disease occurrence that combines machine learning and statistics is used to identify the key spatial scales that define the relationship between zoonotic malaria cases and environmental change. Using data from satellite imagery, a case - control study, and a cross-sectional survey, predictive models of household-level occurrence of P. knowlesi were fitted with 16 variables summarized at 11 spatial scales simultaneously. The method identified a strong and well-defined peak of predictive influence of the proportion of cleared land within 1 km of households on P. knowlesi occurrence. Aspect (1 and 2 km), slope (0.5 km) and canopy regrowth (0.5 km) were important at small scales. By contrast, fragmentation of deforested areas influenced P. knowlesi occurrence probability most strongly at large scales (4 and 5 km). The identification of these spatial scales narrows the field of plausible mechanisms that connect land use change and P. knowlesi, allowing for the refinement of disease occurrence predictions and the design of spatially-targeted interventions.",
keywords = "Boosted regression trees, Disease ecology, Disease occurrence prediction, Malaria, Plasmodium knowlesi, Zoonoses",
author = "Brock, {Patrick M.} and Fornace, {Kimberly M.} and Grigg, {Matthew J.} and Anstey, {Nicholas M.} and Timothy William and Jon Cox and Drakeley, {Chris J.} and Ferguson, {Heather M.} and Kao, {Rowland R.}",
year = "2019",
month = "1",
day = "16",
doi = "10.1098/rspb.2018.2351",
language = "English",
volume = "286",
pages = "1--9",
journal = "Proceedings of the Royal Society of London: Biological Sciences",
issn = "0962-8452",
publisher = "Royal Society",
number = "1894",

}

Brock, PM, Fornace, KM, Grigg, MJ, Anstey, NM, William, T, Cox, J, Drakeley, CJ, Ferguson, HM & Kao, RR 2019, 'Predictive analysis across spatial scales links zoonotic malaria to deforestation', Proceedings of the Royal Society B: Biological Sciences, vol. 286, no. 1894, 20182351, pp. 1-9. https://doi.org/10.1098/rspb.2018.2351

Predictive analysis across spatial scales links zoonotic malaria to deforestation. / Brock, Patrick M.; Fornace, Kimberly M.; Grigg, Matthew J.; Anstey, Nicholas M.; William, Timothy; Cox, Jon; Drakeley, Chris J.; Ferguson, Heather M.; Kao, Rowland R.

In: Proceedings of the Royal Society B: Biological Sciences, Vol. 286, No. 1894, 20182351, 16.01.2019, p. 1-9.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Predictive analysis across spatial scales links zoonotic malaria to deforestation

AU - Brock, Patrick M.

AU - Fornace, Kimberly M.

AU - Grigg, Matthew J.

AU - Anstey, Nicholas M.

AU - William, Timothy

AU - Cox, Jon

AU - Drakeley, Chris J.

AU - Ferguson, Heather M.

AU - Kao, Rowland R.

PY - 2019/1/16

Y1 - 2019/1/16

N2 - The complex transmission ecologies of vector-borne and zoonotic diseases pose challenges to their control, especially in changing landscapes. Human incidence of zoonotic malaria (Plasmodium knowlesi) is associated with deforestation although mechanisms are unknown. Here, a novel application of a method for predicting disease occurrence that combines machine learning and statistics is used to identify the key spatial scales that define the relationship between zoonotic malaria cases and environmental change. Using data from satellite imagery, a case - control study, and a cross-sectional survey, predictive models of household-level occurrence of P. knowlesi were fitted with 16 variables summarized at 11 spatial scales simultaneously. The method identified a strong and well-defined peak of predictive influence of the proportion of cleared land within 1 km of households on P. knowlesi occurrence. Aspect (1 and 2 km), slope (0.5 km) and canopy regrowth (0.5 km) were important at small scales. By contrast, fragmentation of deforested areas influenced P. knowlesi occurrence probability most strongly at large scales (4 and 5 km). The identification of these spatial scales narrows the field of plausible mechanisms that connect land use change and P. knowlesi, allowing for the refinement of disease occurrence predictions and the design of spatially-targeted interventions.

AB - The complex transmission ecologies of vector-borne and zoonotic diseases pose challenges to their control, especially in changing landscapes. Human incidence of zoonotic malaria (Plasmodium knowlesi) is associated with deforestation although mechanisms are unknown. Here, a novel application of a method for predicting disease occurrence that combines machine learning and statistics is used to identify the key spatial scales that define the relationship between zoonotic malaria cases and environmental change. Using data from satellite imagery, a case - control study, and a cross-sectional survey, predictive models of household-level occurrence of P. knowlesi were fitted with 16 variables summarized at 11 spatial scales simultaneously. The method identified a strong and well-defined peak of predictive influence of the proportion of cleared land within 1 km of households on P. knowlesi occurrence. Aspect (1 and 2 km), slope (0.5 km) and canopy regrowth (0.5 km) were important at small scales. By contrast, fragmentation of deforested areas influenced P. knowlesi occurrence probability most strongly at large scales (4 and 5 km). The identification of these spatial scales narrows the field of plausible mechanisms that connect land use change and P. knowlesi, allowing for the refinement of disease occurrence predictions and the design of spatially-targeted interventions.

KW - Boosted regression trees

KW - Disease ecology

KW - Disease occurrence prediction

KW - Malaria

KW - Plasmodium knowlesi

KW - Zoonoses

UR - http://www.scopus.com/inward/record.url?scp=85061297890&partnerID=8YFLogxK

U2 - 10.1098/rspb.2018.2351

DO - 10.1098/rspb.2018.2351

M3 - Article

VL - 286

SP - 1

EP - 9

JO - Proceedings of the Royal Society of London: Biological Sciences

JF - Proceedings of the Royal Society of London: Biological Sciences

SN - 0962-8452

IS - 1894

M1 - 20182351

ER -