We introduce the use of a Gated Recurrent Unit (GRU) for influenza prediction at the state- and city-level in the US, and experiment with the inclusion of real-time flu-related Internet search data. We find that a GRU has lower prediction error than current state-of-the-art methods for data-driven influenza prediction at time horizons of over two weeks. In contrast with other machine learning approaches, the inclusion of real-time Internet search data does not improve GRU predictions.
@article{arxiv.1911.02673,
title = {Towards the Use of Neural Networks for Influenza Prediction at Multiple Spatial Resolutions},
author = {Emily L. Aiken and Andre T. Nguyen and Mauricio Santillana},
journal= {arXiv preprint arXiv:1911.02673},
year = {2019}
}
Comments
Machine Learning for Health (ML4H) at NeurIPS 2019 - Extended Abstract; Added Footer