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.
@article{osti_1806600,
author = {Lee, Kookjin and Ray, Jaideep and Safta, Cosmin and Chen, ed., Chi-Hua},
title = {The predictive skill of convolutional neural networks models for disease forecasting},
annote = {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.},
doi = {10.1371/journal.pone.0254319},
url = {https://www.osti.gov/biblio/1806600},
journal = {PLoS ONE},
issn = {ISSN 1932-6203},
number = {7},
volume = {16},
place = {United States},
publisher = {Public Library of Science (PLoS)},
year = {2021},
month = {07}}
SIGIR '18: The 41st International ACM SIGIR conference on research and development in Information Retrieval, The 41st International ACM SIGIR Conference on Research & Development in Information Retrievalhttps://doi.org/10.1145/3209978.3210077