Using remote sensing environmental data to forecast malaria incidence at a rural district hospital in Western Kenya

Maquins Odhiambo Sewe, Yesim Tozan, Clas Ahlm, Joacim Rocklöv

Research output: Contribution to journalArticle

Abstract

Malaria surveillance data provide opportunity to develop forecasting models. Seasonal variability in environmental factors correlate with malaria transmission, thus the identification of transmission patterns is useful in developing prediction models. However, with changing seasonal transmission patterns, either due to interventions or shifting weather seasons, traditional modelling approaches may not yield adequate predictive skill. Two statistical models,a general additive model (GAM) and GAMBOOST model with boosted regression were contrasted by assessing their predictive accuracy in forecasting malaria admissions at lead times of one to three months. Monthly admission data for children under five years with confirmed malaria at the Siaya district hospital in Western Kenya for the period 2003 to 2013 were used together with satellite derived data on rainfall, average temperature and evapotranspiration(ET). There was a total of 8,476 confirmed malaria admissions. The peak of malaria season changed and malaria admissions reduced overtime. The GAMBOOST model at 1-month lead time had the highest predictive skill during both the training and test periods and thus can be utilized in a malaria early warning system.

Original languageEnglish (US)
Article number2589
JournalScientific Reports
Volume7
Issue number1
DOIs
StatePublished - Dec 1 2017

Fingerprint

malaria
remote sensing
early warning system
environmental data
hospital
forecast
evapotranspiration
environmental factor
weather
rainfall
prediction
modeling

ASJC Scopus subject areas

  • General

Cite this

Using remote sensing environmental data to forecast malaria incidence at a rural district hospital in Western Kenya. / Sewe, Maquins Odhiambo; Tozan, Yesim; Ahlm, Clas; Rocklöv, Joacim.

In: Scientific Reports, Vol. 7, No. 1, 2589, 01.12.2017.

Research output: Contribution to journalArticle

@article{30f0af9c66ea401199d819291db74581,
title = "Using remote sensing environmental data to forecast malaria incidence at a rural district hospital in Western Kenya",
abstract = "Malaria surveillance data provide opportunity to develop forecasting models. Seasonal variability in environmental factors correlate with malaria transmission, thus the identification of transmission patterns is useful in developing prediction models. However, with changing seasonal transmission patterns, either due to interventions or shifting weather seasons, traditional modelling approaches may not yield adequate predictive skill. Two statistical models,a general additive model (GAM) and GAMBOOST model with boosted regression were contrasted by assessing their predictive accuracy in forecasting malaria admissions at lead times of one to three months. Monthly admission data for children under five years with confirmed malaria at the Siaya district hospital in Western Kenya for the period 2003 to 2013 were used together with satellite derived data on rainfall, average temperature and evapotranspiration(ET). There was a total of 8,476 confirmed malaria admissions. The peak of malaria season changed and malaria admissions reduced overtime. The GAMBOOST model at 1-month lead time had the highest predictive skill during both the training and test periods and thus can be utilized in a malaria early warning system.",
author = "Sewe, {Maquins Odhiambo} and Yesim Tozan and Clas Ahlm and Joacim Rockl{\"o}v",
year = "2017",
month = "12",
day = "1",
doi = "10.1038/s41598-017-02560-z",
language = "English (US)",
volume = "7",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Using remote sensing environmental data to forecast malaria incidence at a rural district hospital in Western Kenya

AU - Sewe, Maquins Odhiambo

AU - Tozan, Yesim

AU - Ahlm, Clas

AU - Rocklöv, Joacim

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Malaria surveillance data provide opportunity to develop forecasting models. Seasonal variability in environmental factors correlate with malaria transmission, thus the identification of transmission patterns is useful in developing prediction models. However, with changing seasonal transmission patterns, either due to interventions or shifting weather seasons, traditional modelling approaches may not yield adequate predictive skill. Two statistical models,a general additive model (GAM) and GAMBOOST model with boosted regression were contrasted by assessing their predictive accuracy in forecasting malaria admissions at lead times of one to three months. Monthly admission data for children under five years with confirmed malaria at the Siaya district hospital in Western Kenya for the period 2003 to 2013 were used together with satellite derived data on rainfall, average temperature and evapotranspiration(ET). There was a total of 8,476 confirmed malaria admissions. The peak of malaria season changed and malaria admissions reduced overtime. The GAMBOOST model at 1-month lead time had the highest predictive skill during both the training and test periods and thus can be utilized in a malaria early warning system.

AB - Malaria surveillance data provide opportunity to develop forecasting models. Seasonal variability in environmental factors correlate with malaria transmission, thus the identification of transmission patterns is useful in developing prediction models. However, with changing seasonal transmission patterns, either due to interventions or shifting weather seasons, traditional modelling approaches may not yield adequate predictive skill. Two statistical models,a general additive model (GAM) and GAMBOOST model with boosted regression were contrasted by assessing their predictive accuracy in forecasting malaria admissions at lead times of one to three months. Monthly admission data for children under five years with confirmed malaria at the Siaya district hospital in Western Kenya for the period 2003 to 2013 were used together with satellite derived data on rainfall, average temperature and evapotranspiration(ET). There was a total of 8,476 confirmed malaria admissions. The peak of malaria season changed and malaria admissions reduced overtime. The GAMBOOST model at 1-month lead time had the highest predictive skill during both the training and test periods and thus can be utilized in a malaria early warning system.

UR - http://www.scopus.com/inward/record.url?scp=85020235413&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020235413&partnerID=8YFLogxK

U2 - 10.1038/s41598-017-02560-z

DO - 10.1038/s41598-017-02560-z

M3 - Article

C2 - 28572680

AN - SCOPUS:85020235413

VL - 7

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 2589

ER -