Cargando…

Deep Spatiotemporal Model for COVID-19 Forecasting

COVID-19 has caused millions of infections and deaths over the last 2 years. Machine learning models have been proposed as an alternative to conventional epidemiologic models in an effort to optimize short- and medium-term forecasts that will help health authorities to optimize the use of policies a...

Descripción completa

Detalles Bibliográficos
Autores principales: Muñoz-Organero, Mario, Queipo-Álvarez, Paula
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9101138/
https://www.ncbi.nlm.nih.gov/pubmed/35591208
http://dx.doi.org/10.3390/s22093519
_version_ 1784707012456611840
author Muñoz-Organero, Mario
Queipo-Álvarez, Paula
author_facet Muñoz-Organero, Mario
Queipo-Álvarez, Paula
author_sort Muñoz-Organero, Mario
collection PubMed
description COVID-19 has caused millions of infections and deaths over the last 2 years. Machine learning models have been proposed as an alternative to conventional epidemiologic models in an effort to optimize short- and medium-term forecasts that will help health authorities to optimize the use of policies and resources to tackle the spread of the SARS-CoV-2 virus. Although previous machine learning models based on time pattern analysis for COVID-19 sensed data have shown promising results, the spread of the virus has both spatial and temporal components. This manuscript proposes a new deep learning model that combines a time pattern extraction based on the use of a Long-Short Term Memory (LSTM) Recurrent Neural Network (RNN) over a preceding spatial analysis based on a Convolutional Neural Network (CNN) applied to a sequence of COVID-19 incidence images. The model has been validated with data from the 286 health primary care centers in the Comunidad de Madrid (Madrid region, Spain). The results show improved scores in terms of both root mean square error (RMSE) and explained variance (EV) when compared with previous models that have mainly focused on the temporal patterns and dependencies.
format Online
Article
Text
id pubmed-9101138
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-91011382022-05-14 Deep Spatiotemporal Model for COVID-19 Forecasting Muñoz-Organero, Mario Queipo-Álvarez, Paula Sensors (Basel) Article COVID-19 has caused millions of infections and deaths over the last 2 years. Machine learning models have been proposed as an alternative to conventional epidemiologic models in an effort to optimize short- and medium-term forecasts that will help health authorities to optimize the use of policies and resources to tackle the spread of the SARS-CoV-2 virus. Although previous machine learning models based on time pattern analysis for COVID-19 sensed data have shown promising results, the spread of the virus has both spatial and temporal components. This manuscript proposes a new deep learning model that combines a time pattern extraction based on the use of a Long-Short Term Memory (LSTM) Recurrent Neural Network (RNN) over a preceding spatial analysis based on a Convolutional Neural Network (CNN) applied to a sequence of COVID-19 incidence images. The model has been validated with data from the 286 health primary care centers in the Comunidad de Madrid (Madrid region, Spain). The results show improved scores in terms of both root mean square error (RMSE) and explained variance (EV) when compared with previous models that have mainly focused on the temporal patterns and dependencies. MDPI 2022-05-05 /pmc/articles/PMC9101138/ /pubmed/35591208 http://dx.doi.org/10.3390/s22093519 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Muñoz-Organero, Mario
Queipo-Álvarez, Paula
Deep Spatiotemporal Model for COVID-19 Forecasting
title Deep Spatiotemporal Model for COVID-19 Forecasting
title_full Deep Spatiotemporal Model for COVID-19 Forecasting
title_fullStr Deep Spatiotemporal Model for COVID-19 Forecasting
title_full_unstemmed Deep Spatiotemporal Model for COVID-19 Forecasting
title_short Deep Spatiotemporal Model for COVID-19 Forecasting
title_sort deep spatiotemporal model for covid-19 forecasting
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9101138/
https://www.ncbi.nlm.nih.gov/pubmed/35591208
http://dx.doi.org/10.3390/s22093519
work_keys_str_mv AT munozorganeromario deepspatiotemporalmodelforcovid19forecasting
AT queipoalvarezpaula deepspatiotemporalmodelforcovid19forecasting