Cargando…

Machine learning forecasts for seasonal epidemic peaks: Lessons learnt from an atypical respiratory syncytial virus season

Seasonal peaks in infectious disease incidence put pressures on health services. Therefore, early warning of the timing and magnitude of peak activity during seasonal epidemics can provide information for public health practitioners to take appropriate action. Whilst many infectious diseases have pr...

Descripción completa

Detalles Bibliográficos
Autores principales: Morbey, Roger A., Todkill, Daniel, Watson, Conall, Elliot, Alex J.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10516409/
https://www.ncbi.nlm.nih.gov/pubmed/37738241
http://dx.doi.org/10.1371/journal.pone.0291932
_version_ 1785109121507262464
author Morbey, Roger A.
Todkill, Daniel
Watson, Conall
Elliot, Alex J.
author_facet Morbey, Roger A.
Todkill, Daniel
Watson, Conall
Elliot, Alex J.
author_sort Morbey, Roger A.
collection PubMed
description Seasonal peaks in infectious disease incidence put pressures on health services. Therefore, early warning of the timing and magnitude of peak activity during seasonal epidemics can provide information for public health practitioners to take appropriate action. Whilst many infectious diseases have predictable seasonality, newly emerging diseases and the impact of public health interventions can result in unprecedented seasonal activity. We propose a Machine Learning process for generating short-term forecasts, where models are selected based on their ability to correctly forecast peaks in activity, and can be useful during atypical seasons. We have validated our forecasts using typical and atypical seasonal activity, using respiratory syncytial virus (RSV) activity during 2019–2021 as an example. During the winter of 2020/21 the usual winter peak in RSV activity in England did not occur but was ‘deferred’ until the Spring of 2021. We compare a range of Machine Learning regression models, with alternate models including different independent variables, e.g. with or without seasonality or trend variables. We show that the best-fitting model which minimises daily forecast errors is not the best model for forecasting peaks when the selection criterion is based on peak timing and magnitude. Furthermore, we show that best-fitting models for typical seasons contain different variables to those for atypical seasons. Specifically, including seasonality in models improves performance during typical seasons but worsens it for the atypical seasons.
format Online
Article
Text
id pubmed-10516409
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-105164092023-09-23 Machine learning forecasts for seasonal epidemic peaks: Lessons learnt from an atypical respiratory syncytial virus season Morbey, Roger A. Todkill, Daniel Watson, Conall Elliot, Alex J. PLoS One Research Article Seasonal peaks in infectious disease incidence put pressures on health services. Therefore, early warning of the timing and magnitude of peak activity during seasonal epidemics can provide information for public health practitioners to take appropriate action. Whilst many infectious diseases have predictable seasonality, newly emerging diseases and the impact of public health interventions can result in unprecedented seasonal activity. We propose a Machine Learning process for generating short-term forecasts, where models are selected based on their ability to correctly forecast peaks in activity, and can be useful during atypical seasons. We have validated our forecasts using typical and atypical seasonal activity, using respiratory syncytial virus (RSV) activity during 2019–2021 as an example. During the winter of 2020/21 the usual winter peak in RSV activity in England did not occur but was ‘deferred’ until the Spring of 2021. We compare a range of Machine Learning regression models, with alternate models including different independent variables, e.g. with or without seasonality or trend variables. We show that the best-fitting model which minimises daily forecast errors is not the best model for forecasting peaks when the selection criterion is based on peak timing and magnitude. Furthermore, we show that best-fitting models for typical seasons contain different variables to those for atypical seasons. Specifically, including seasonality in models improves performance during typical seasons but worsens it for the atypical seasons. Public Library of Science 2023-09-22 /pmc/articles/PMC10516409/ /pubmed/37738241 http://dx.doi.org/10.1371/journal.pone.0291932 Text en © 2023 Morbey et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Morbey, Roger A.
Todkill, Daniel
Watson, Conall
Elliot, Alex J.
Machine learning forecasts for seasonal epidemic peaks: Lessons learnt from an atypical respiratory syncytial virus season
title Machine learning forecasts for seasonal epidemic peaks: Lessons learnt from an atypical respiratory syncytial virus season
title_full Machine learning forecasts for seasonal epidemic peaks: Lessons learnt from an atypical respiratory syncytial virus season
title_fullStr Machine learning forecasts for seasonal epidemic peaks: Lessons learnt from an atypical respiratory syncytial virus season
title_full_unstemmed Machine learning forecasts for seasonal epidemic peaks: Lessons learnt from an atypical respiratory syncytial virus season
title_short Machine learning forecasts for seasonal epidemic peaks: Lessons learnt from an atypical respiratory syncytial virus season
title_sort machine learning forecasts for seasonal epidemic peaks: lessons learnt from an atypical respiratory syncytial virus season
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10516409/
https://www.ncbi.nlm.nih.gov/pubmed/37738241
http://dx.doi.org/10.1371/journal.pone.0291932
work_keys_str_mv AT morbeyrogera machinelearningforecastsforseasonalepidemicpeakslessonslearntfromanatypicalrespiratorysyncytialvirusseason
AT todkilldaniel machinelearningforecastsforseasonalepidemicpeakslessonslearntfromanatypicalrespiratorysyncytialvirusseason
AT watsonconall machinelearningforecastsforseasonalepidemicpeakslessonslearntfromanatypicalrespiratorysyncytialvirusseason
AT elliotalexj machinelearningforecastsforseasonalepidemicpeakslessonslearntfromanatypicalrespiratorysyncytialvirusseason