Improving disaggregation models of malaria incidence by ensembling non-linear models of prevalence.
Disaggregation regression
Spatial statistics
Stacking
Surveillance data
Journal
Spatial and spatio-temporal epidemiology
ISSN: 1877-5853
Titre abrégé: Spat Spatiotemporal Epidemiol
Pays: Netherlands
ID NLM: 101516571
Informations de publication
Date de publication:
06 2022
06 2022
Historique:
received:
10
01
2020
revised:
13
04
2020
accepted:
18
06
2020
entrez:
12
6
2022
pubmed:
13
6
2022
medline:
15
6
2022
Statut:
ppublish
Résumé
Maps of disease burden are a core tool needed for the control and elimination of malaria. Reliable routine surveillance data of malaria incidence, typically aggregated to administrative units, is becoming more widely available. Disaggregation regression is an important model framework for estimating high resolution risk maps from aggregated data. However, the aggregation of incidence over large, heterogeneous areas means that these data are underpowered for estimating complex, non-linear models. In contrast, prevalence point-surveys are directly linked to local environmental conditions but are not common in many areas of the world. Here, we train multiple non-linear, machine learning models on Plasmodium falciparum prevalence point-surveys. We then ensemble the predictions from these machine learning models with a disaggregation regression model that uses aggregated malaria incidences as response data. We find that using a disaggregation regression model to combine predictions from machine learning models improves model accuracy relative to a baseline model.
Identifiants
pubmed: 35691633
pii: S1877-5845(20)30035-6
doi: 10.1016/j.sste.2020.100357
pmc: PMC9205339
pii:
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
100357Informations de copyright
Copyright © 2020 The Author(s). Published by Elsevier Ltd.. All rights reserved.
Références
Lancet. 2019 Jul 27;394(10195):332-343
pubmed: 31229233
Elife. 2014 Sep 08;3:e04395
pubmed: 25201877
Parasit Vectors. 2011 May 26;4:92
pubmed: 21615906
Nat Commun. 2015 Sep 08;6:8170
pubmed: 26348689
Nature. 2018 Jan 18;553(7688):333-336
pubmed: 29320477
Biostatistics. 2020 Apr 1;21(2):e17-e32
pubmed: 30202860
Nature. 2015 Oct 8;526(7572):207-211
pubmed: 26375008
Stat Med. 2019 Oct 30;38(24):4871-4887
pubmed: 31452235
PLoS One. 2013;8(2):e55882
pubmed: 23418469
PLoS One. 2012;7(2):e31743
pubmed: 22363717
Malar J. 2016 Jan 11;15:20
pubmed: 26754795
Malar J. 2015 Feb 07;14:68
pubmed: 25890035
Malar J. 2007 Feb 16;6:17
pubmed: 17306022
Malar J. 2018 Oct 5;17(1):352
pubmed: 30290815
PLoS Negl Trop Dis. 2016 Aug 05;10(8):e0004915
pubmed: 27494405
Malar J. 2014 May 03;13:171
pubmed: 24886586
Stat Med. 1993 Sep 30;12(18):1703-22
pubmed: 8248663
Malar J. 2007 Sep 25;6:131
pubmed: 17894879
Sci Data. 2015 Sep 01;2:150045
pubmed: 26347245
Stat Methods Med Res. 2012 Oct;21(5):479-507
pubmed: 22544855
PLoS Med. 2011 Dec;8(12):e1001142
pubmed: 22205883
Malar J. 2014 Nov 03;13:421
pubmed: 25366929
J R Soc Interface. 2017 Sep;14(134):
pubmed: 28931634
Lancet. 2019 Jul 27;394(10195):322-331
pubmed: 31229234
Trends Parasitol. 2016 Aug;32(8):635-645
pubmed: 27238200