Cargando…

A Bayesian Ensemble Approach for Epidemiological Projections

Mathematical models are powerful tools for epidemiology and can be used to compare control actions. However, different models and model parameterizations may provide different prediction of outcomes. In other fields of research, ensemble modeling has been used to combine multiple projections. We exp...

Descripción completa

Detalles Bibliográficos
Autores principales: Lindström, Tom, Tildesley, Michael, Webb, Colleen
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2015
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4415763/
https://www.ncbi.nlm.nih.gov/pubmed/25927892
http://dx.doi.org/10.1371/journal.pcbi.1004187
_version_ 1782369120479608832
author Lindström, Tom
Tildesley, Michael
Webb, Colleen
author_facet Lindström, Tom
Tildesley, Michael
Webb, Colleen
author_sort Lindström, Tom
collection PubMed
description Mathematical models are powerful tools for epidemiology and can be used to compare control actions. However, different models and model parameterizations may provide different prediction of outcomes. In other fields of research, ensemble modeling has been used to combine multiple projections. We explore the possibility of applying such methods to epidemiology by adapting Bayesian techniques developed for climate forecasting. We exemplify the implementation with single model ensembles based on different parameterizations of the Warwick model run for the 2001 United Kingdom foot and mouth disease outbreak and compare the efficacy of different control actions. This allows us to investigate the effect that discrepancy among projections based on different modeling assumptions has on the ensemble prediction. A sensitivity analysis showed that the choice of prior can have a pronounced effect on the posterior estimates of quantities of interest, in particular for ensembles with large discrepancy among projections. However, by using a hierarchical extension of the method we show that prior sensitivity can be circumvented. We further extend the method to include a priori beliefs about different modeling assumptions and demonstrate that the effect of this can have different consequences depending on the discrepancy among projections. We propose that the method is a promising analytical tool for ensemble modeling of disease outbreaks.
format Online
Article
Text
id pubmed-4415763
institution National Center for Biotechnology Information
language English
publishDate 2015
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-44157632015-05-07 A Bayesian Ensemble Approach for Epidemiological Projections Lindström, Tom Tildesley, Michael Webb, Colleen PLoS Comput Biol Research Article Mathematical models are powerful tools for epidemiology and can be used to compare control actions. However, different models and model parameterizations may provide different prediction of outcomes. In other fields of research, ensemble modeling has been used to combine multiple projections. We explore the possibility of applying such methods to epidemiology by adapting Bayesian techniques developed for climate forecasting. We exemplify the implementation with single model ensembles based on different parameterizations of the Warwick model run for the 2001 United Kingdom foot and mouth disease outbreak and compare the efficacy of different control actions. This allows us to investigate the effect that discrepancy among projections based on different modeling assumptions has on the ensemble prediction. A sensitivity analysis showed that the choice of prior can have a pronounced effect on the posterior estimates of quantities of interest, in particular for ensembles with large discrepancy among projections. However, by using a hierarchical extension of the method we show that prior sensitivity can be circumvented. We further extend the method to include a priori beliefs about different modeling assumptions and demonstrate that the effect of this can have different consequences depending on the discrepancy among projections. We propose that the method is a promising analytical tool for ensemble modeling of disease outbreaks. Public Library of Science 2015-04-30 /pmc/articles/PMC4415763/ /pubmed/25927892 http://dx.doi.org/10.1371/journal.pcbi.1004187 Text en © 2015 Lindström et al http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly credited.
spellingShingle Research Article
Lindström, Tom
Tildesley, Michael
Webb, Colleen
A Bayesian Ensemble Approach for Epidemiological Projections
title A Bayesian Ensemble Approach for Epidemiological Projections
title_full A Bayesian Ensemble Approach for Epidemiological Projections
title_fullStr A Bayesian Ensemble Approach for Epidemiological Projections
title_full_unstemmed A Bayesian Ensemble Approach for Epidemiological Projections
title_short A Bayesian Ensemble Approach for Epidemiological Projections
title_sort bayesian ensemble approach for epidemiological projections
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4415763/
https://www.ncbi.nlm.nih.gov/pubmed/25927892
http://dx.doi.org/10.1371/journal.pcbi.1004187
work_keys_str_mv AT lindstromtom abayesianensembleapproachforepidemiologicalprojections
AT tildesleymichael abayesianensembleapproachforepidemiologicalprojections
AT webbcolleen abayesianensembleapproachforepidemiologicalprojections
AT lindstromtom bayesianensembleapproachforepidemiologicalprojections
AT tildesleymichael bayesianensembleapproachforepidemiologicalprojections
AT webbcolleen bayesianensembleapproachforepidemiologicalprojections