Cargando…
Optimal multi-source forecasting of seasonal influenza
Forecasting the emergence and spread of influenza viruses is an important public health challenge. Timely and accurate estimates of influenza prevalence, particularly of severe cases requiring hospitalization, can improve control measures to reduce transmission and mortality. Here, we extend a previ...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6138397/ https://www.ncbi.nlm.nih.gov/pubmed/30180212 http://dx.doi.org/10.1371/journal.pcbi.1006236 |
_version_ | 1783355339028037632 |
---|---|
author | Ertem, Zeynep Raymond, Dorrie Meyers, Lauren Ancel |
author_facet | Ertem, Zeynep Raymond, Dorrie Meyers, Lauren Ancel |
author_sort | Ertem, Zeynep |
collection | PubMed |
description | Forecasting the emergence and spread of influenza viruses is an important public health challenge. Timely and accurate estimates of influenza prevalence, particularly of severe cases requiring hospitalization, can improve control measures to reduce transmission and mortality. Here, we extend a previously published machine learning method for influenza forecasting to integrate multiple diverse data sources, including traditional surveillance data, electronic health records, internet search traffic, and social media activity. Our hierarchical framework uses multi-linear regression to combine forecasts from multiple data sources and greedy optimization with forward selection to sequentially choose the most predictive combinations of data sources. We show that the systematic integration of complementary data sources can substantially improve forecast accuracy over single data sources. When forecasting the Center for Disease Control and Prevention (CDC) influenza-like-illness reports (ILINet) from week 48 through week 20, the optimal combination of predictors includes public health surveillance data and commercially available electronic medical records, but neither search engine nor social media data. |
format | Online Article Text |
id | pubmed-6138397 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2018 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-61383972018-09-27 Optimal multi-source forecasting of seasonal influenza Ertem, Zeynep Raymond, Dorrie Meyers, Lauren Ancel PLoS Comput Biol Research Article Forecasting the emergence and spread of influenza viruses is an important public health challenge. Timely and accurate estimates of influenza prevalence, particularly of severe cases requiring hospitalization, can improve control measures to reduce transmission and mortality. Here, we extend a previously published machine learning method for influenza forecasting to integrate multiple diverse data sources, including traditional surveillance data, electronic health records, internet search traffic, and social media activity. Our hierarchical framework uses multi-linear regression to combine forecasts from multiple data sources and greedy optimization with forward selection to sequentially choose the most predictive combinations of data sources. We show that the systematic integration of complementary data sources can substantially improve forecast accuracy over single data sources. When forecasting the Center for Disease Control and Prevention (CDC) influenza-like-illness reports (ILINet) from week 48 through week 20, the optimal combination of predictors includes public health surveillance data and commercially available electronic medical records, but neither search engine nor social media data. Public Library of Science 2018-09-04 /pmc/articles/PMC6138397/ /pubmed/30180212 http://dx.doi.org/10.1371/journal.pcbi.1006236 Text en © 2018 Ertem 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 (http://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 Ertem, Zeynep Raymond, Dorrie Meyers, Lauren Ancel Optimal multi-source forecasting of seasonal influenza |
title | Optimal multi-source forecasting of seasonal influenza |
title_full | Optimal multi-source forecasting of seasonal influenza |
title_fullStr | Optimal multi-source forecasting of seasonal influenza |
title_full_unstemmed | Optimal multi-source forecasting of seasonal influenza |
title_short | Optimal multi-source forecasting of seasonal influenza |
title_sort | optimal multi-source forecasting of seasonal influenza |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6138397/ https://www.ncbi.nlm.nih.gov/pubmed/30180212 http://dx.doi.org/10.1371/journal.pcbi.1006236 |
work_keys_str_mv | AT ertemzeynep optimalmultisourceforecastingofseasonalinfluenza AT raymonddorrie optimalmultisourceforecastingofseasonalinfluenza AT meyerslaurenancel optimalmultisourceforecastingofseasonalinfluenza |