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


Journal

PloS one
ISSN: 1932-6203
Titre abrégé: PLoS One
Pays: United States
ID NLM: 101285081

Informations de publication

Date de publication:
2023
Historique:
received: 12 01 2023
accepted: 10 09 2023
medline: 25 9 2023
pubmed: 22 9 2023
entrez: 22 9 2023
Statut: epublish

Résumé

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.

Identifiants

pubmed: 37738241
doi: 10.1371/journal.pone.0291932
pii: PONE-D-22-35171
pmc: PMC10516409
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

e0291932

Informations de copyright

Copyright: © 2023 Morbey et al. 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 credited.

Déclaration de conflit d'intérêts

The authors have declared that no competing interests exist.

Références

Sci Rep. 2019 Jan 24;9(1):683
pubmed: 30679458
Commun Dis Intell (2018). 2019 Mar 15;43:
pubmed: 30879285
PLoS One. 2020 Feb 10;15(2):e0228804
pubmed: 32040541
Proc Natl Acad Sci U S A. 2019 Feb 19;116(8):3146-3154
pubmed: 30647115
Epidemiol Infect. 2018 Aug;146(11):1389-1396
pubmed: 29972108
JMIR Public Health Surveill. 2020 Mar 4;6(1):e14627
pubmed: 32130197
EBioMedicine. 2019 Sep;47:284-292
pubmed: 31477561
Epidemiol Infect. 2019 Jan;147:e101
pubmed: 30869042
Epidemics. 2019 Sep;28:100341
pubmed: 31047830
Influenza Other Respir Viruses. 2015 Sep;9(5):234-46
pubmed: 26031655
J Infect. 2019 Jun;78(6):468-475
pubmed: 30817978
Epidemiol Infect. 2017 Jul;145(9):1922-1932
pubmed: 28413995
BMC Health Serv Res. 2022 Jan 2;22(1):17
pubmed: 34974842
Epidemiol Infect. 2007 Jan;135(1):159-62
pubmed: 16753078
Lancet Infect Dis. 2023 Jan;23(1):56-66
pubmed: 36063828
Osong Public Health Res Perspect. 2022 Jun;13(3):203-211
pubmed: 35820669
JMIR Public Health Surveill. 2019 Jul 23;5(3):e11780
pubmed: 31339102
Infect Dis Model. 2017 Jan 10;2(1):56-70
pubmed: 29928729
J Korean Med Sci. 2022 Jul 18;37(28):e215
pubmed: 35851860
BMJ Open. 2016 Jun 02;6(6):e009337
pubmed: 27256085

Auteurs

Roger A Morbey (RA)

Real-Time Syndromic Surveillance Team, Field Services, Health Protection Operations, UK Health Security Agency, Birmingham, United Kingdom.

Daniel Todkill (D)

Real-Time Syndromic Surveillance Team, Field Services, Health Protection Operations, UK Health Security Agency, Birmingham, United Kingdom.

Conall Watson (C)

Immunisation and Vaccine Preventable Diseases Division, UK Health Security Agency, London, United Kingdom.

Alex J Elliot (AJ)

Real-Time Syndromic Surveillance Team, Field Services, Health Protection Operations, UK Health Security Agency, Birmingham, United Kingdom.

Articles similaires

Exploring blood-brain barrier passage using atomic weighted vector and machine learning.

Yoan Martínez-López, Paulina Phoobane, Yanaima Jauriga et al.
1.00
Blood-Brain Barrier Machine Learning Humans Support Vector Machine Software

Total elbow arthroplasty in England.

Zaid Hamoodi, Adrian Sayers, Michael R Whitehouse et al.
1.00
Humans England Female Male Arthroplasty, Replacement, Elbow

Understanding the role of machine learning in predicting progression of osteoarthritis.

Simone Castagno, Benjamin Gompels, Estelle Strangmark et al.
1.00
Humans Disease Progression Machine Learning Osteoarthritis

Classifications MeSH