Feasibility of very short-term forecast models for COVID-19 hospital-based surveillance

INTRODUCTION: We evaluated the performance of Bayesian vector autoregressive (BVAR) and Holt’s models to forecast the weekly COVID-19 reported cases in six units of a large hospital. METHODS: Cases reported from epidemiologic weeks (EW) 12-37 were selected as the training period, and from EW 38-41 a...

Descripción completa

Detalles Bibliográficos
Autores principales: Martinez, Edson Zangiacomi, Passos, Afonso Dinis Costa, Cinto, Antônio Fernando, Escarso, Andreia Cássia, Monteiro, Rosane Aparecida, Silva, Jorgete Maria e, Bellissimo-Rodrigues, Fernando, Aragon, Davi Casale
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Sociedade Brasileira de Medicina Tropical - SBMT 2021
Materias:
Short Communication
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7891562/
https://www.ncbi.nlm.nih.gov/pubmed/33605383
http://dx.doi.org/10.1590/0037-8682-0762-2020
_version_ 1783652723853361152
author Martinez, Edson Zangiacomi
Passos, Afonso Dinis Costa
Cinto, Antônio Fernando
Escarso, Andreia Cássia
Monteiro, Rosane Aparecida
Silva, Jorgete Maria e
Bellissimo-Rodrigues, Fernando
Aragon, Davi Casale
author_facet Martinez, Edson Zangiacomi
Passos, Afonso Dinis Costa
Cinto, Antônio Fernando
Escarso, Andreia Cássia
Monteiro, Rosane Aparecida
Silva, Jorgete Maria e
Bellissimo-Rodrigues, Fernando
Aragon, Davi Casale
author_sort Martinez, Edson Zangiacomi
collection PubMed
description INTRODUCTION: We evaluated the performance of Bayesian vector autoregressive (BVAR) and Holt’s models to forecast the weekly COVID-19 reported cases in six units of a large hospital. METHODS: Cases reported from epidemiologic weeks (EW) 12-37 were selected as the training period, and from EW 38-41 as the test period. RESULTS: The models performed well in forecasting cases within one or two weeks following the end of the time-series, but forecasts for a more distant period were inaccurate. CONCLUSIONS: Both models offered reasonable performance in very short-term forecasts for confirmed cases of COVID-19.
format Online
Article
Text
id pubmed-7891562
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Sociedade Brasileira de Medicina Tropical - SBMT
record_format MEDLINE/PubMed
spelling pubmed-78915622021-02-19 Feasibility of very short-term forecast models for COVID-19 hospital-based surveillance Martinez, Edson Zangiacomi Passos, Afonso Dinis Costa Cinto, Antônio Fernando Escarso, Andreia Cássia Monteiro, Rosane Aparecida Silva, Jorgete Maria e Bellissimo-Rodrigues, Fernando Aragon, Davi Casale Rev Soc Bras Med Trop Short Communication INTRODUCTION: We evaluated the performance of Bayesian vector autoregressive (BVAR) and Holt’s models to forecast the weekly COVID-19 reported cases in six units of a large hospital. METHODS: Cases reported from epidemiologic weeks (EW) 12-37 were selected as the training period, and from EW 38-41 as the test period. RESULTS: The models performed well in forecasting cases within one or two weeks following the end of the time-series, but forecasts for a more distant period were inaccurate. CONCLUSIONS: Both models offered reasonable performance in very short-term forecasts for confirmed cases of COVID-19. Sociedade Brasileira de Medicina Tropical - SBMT 2021-02-10 /pmc/articles/PMC7891562/ /pubmed/33605383 http://dx.doi.org/10.1590/0037-8682-0762-2020 Text en https://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License
spellingShingle Short Communication
Martinez, Edson Zangiacomi
Passos, Afonso Dinis Costa
Cinto, Antônio Fernando
Escarso, Andreia Cássia
Monteiro, Rosane Aparecida
Silva, Jorgete Maria e
Bellissimo-Rodrigues, Fernando
Aragon, Davi Casale
Feasibility of very short-term forecast models for COVID-19 hospital-based surveillance
title Feasibility of very short-term forecast models for COVID-19 hospital-based surveillance
title_full Feasibility of very short-term forecast models for COVID-19 hospital-based surveillance
title_fullStr Feasibility of very short-term forecast models for COVID-19 hospital-based surveillance
title_full_unstemmed Feasibility of very short-term forecast models for COVID-19 hospital-based surveillance
title_short Feasibility of very short-term forecast models for COVID-19 hospital-based surveillance
title_sort feasibility of very short-term forecast models for covid-19 hospital-based surveillance
topic Short Communication
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7891562/
https://www.ncbi.nlm.nih.gov/pubmed/33605383
http://dx.doi.org/10.1590/0037-8682-0762-2020
work_keys_str_mv AT martinezedsonzangiacomi feasibilityofveryshorttermforecastmodelsforcovid19hospitalbasedsurveillance
AT passosafonsodiniscosta feasibilityofveryshorttermforecastmodelsforcovid19hospitalbasedsurveillance
AT cintoantoniofernando feasibilityofveryshorttermforecastmodelsforcovid19hospitalbasedsurveillance
AT escarsoandreiacassia feasibilityofveryshorttermforecastmodelsforcovid19hospitalbasedsurveillance
AT monteirorosaneaparecida feasibilityofveryshorttermforecastmodelsforcovid19hospitalbasedsurveillance
AT silvajorgetemariae feasibilityofveryshorttermforecastmodelsforcovid19hospitalbasedsurveillance
AT bellissimorodriguesfernando feasibilityofveryshorttermforecastmodelsforcovid19hospitalbasedsurveillance
AT aragondavicasale feasibilityofveryshorttermforecastmodelsforcovid19hospitalbasedsurveillance

Ejemplares similares