The predictive skill of convolutional neural networks models for disease forecasting.

In this paper we investigate the utility of one-dimensional convolutional neural network (CNN) models in epidemiological forecasting. Deep learning models, in particular variants of recurrent neural networks (RNNs) have been studied for ILI (Influenza-Like Illness) forecasting, and have achieved a h...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Kookjin Lee, Jaideep Ray, Cosmin Safta
Formato: article
Lenguaje:EN
Publicado: Public Library of Science (PLoS) 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/9a39ca67b96c4b9d9f34bda94007bbe8
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:9a39ca67b96c4b9d9f34bda94007bbe8
record_format dspace
spelling oai:doaj.org-article:9a39ca67b96c4b9d9f34bda94007bbe82021-12-02T20:09:18ZThe predictive skill of convolutional neural networks models for disease forecasting.1932-620310.1371/journal.pone.0254319https://doaj.org/article/9a39ca67b96c4b9d9f34bda94007bbe82021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0254319https://doaj.org/toc/1932-6203In this paper we investigate the utility of one-dimensional convolutional neural network (CNN) models in epidemiological forecasting. Deep learning models, in particular variants of recurrent neural networks (RNNs) have been studied for ILI (Influenza-Like Illness) forecasting, and have achieved a higher forecasting skill compared to conventional models such as ARIMA. In this study, we adapt two neural networks that employ one-dimensional temporal convolutional layers as a primary building block-temporal convolutional networks and simple neural attentive meta-learners-for epidemiological forecasting. We then test them with influenza data from the US collected over 2010-2019. We find that epidemiological forecasting with CNNs is feasible, and their forecasting skill is comparable to, and at times, superior to, plain RNNs. Thus CNNs and RNNs bring the power of nonlinear transformations to purely data-driven epidemiological models, a capability that heretofore has been limited to more elaborate mechanistic/compartmental disease models.Kookjin LeeJaideep RayCosmin SaftaPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 7, p e0254319 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Kookjin Lee
Jaideep Ray
Cosmin Safta
The predictive skill of convolutional neural networks models for disease forecasting.
description In this paper we investigate the utility of one-dimensional convolutional neural network (CNN) models in epidemiological forecasting. Deep learning models, in particular variants of recurrent neural networks (RNNs) have been studied for ILI (Influenza-Like Illness) forecasting, and have achieved a higher forecasting skill compared to conventional models such as ARIMA. In this study, we adapt two neural networks that employ one-dimensional temporal convolutional layers as a primary building block-temporal convolutional networks and simple neural attentive meta-learners-for epidemiological forecasting. We then test them with influenza data from the US collected over 2010-2019. We find that epidemiological forecasting with CNNs is feasible, and their forecasting skill is comparable to, and at times, superior to, plain RNNs. Thus CNNs and RNNs bring the power of nonlinear transformations to purely data-driven epidemiological models, a capability that heretofore has been limited to more elaborate mechanistic/compartmental disease models.
format article
author Kookjin Lee
Jaideep Ray
Cosmin Safta
author_facet Kookjin Lee
Jaideep Ray
Cosmin Safta
author_sort Kookjin Lee
title The predictive skill of convolutional neural networks models for disease forecasting.
title_short The predictive skill of convolutional neural networks models for disease forecasting.
title_full The predictive skill of convolutional neural networks models for disease forecasting.
title_fullStr The predictive skill of convolutional neural networks models for disease forecasting.
title_full_unstemmed The predictive skill of convolutional neural networks models for disease forecasting.
title_sort predictive skill of convolutional neural networks models for disease forecasting.
publisher Public Library of Science (PLoS)
publishDate 2021
url https://doaj.org/article/9a39ca67b96c4b9d9f34bda94007bbe8
work_keys_str_mv AT kookjinlee thepredictiveskillofconvolutionalneuralnetworksmodelsfordiseaseforecasting
AT jaideepray thepredictiveskillofconvolutionalneuralnetworksmodelsfordiseaseforecasting
AT cosminsafta thepredictiveskillofconvolutionalneuralnetworksmodelsfordiseaseforecasting
AT kookjinlee predictiveskillofconvolutionalneuralnetworksmodelsfordiseaseforecasting
AT jaideepray predictiveskillofconvolutionalneuralnetworksmodelsfordiseaseforecasting
AT cosminsafta predictiveskillofconvolutionalneuralnetworksmodelsfordiseaseforecasting
_version_ 1718375079653408768