Towards the Use of Neural Networks for Influenza Prediction at Multiple Spatial Resolutions
This work addresses influenza forecasting for public health planning, though it is incremental as it applies an existing neural network method to this domain.
The authors tackled influenza prediction at state and city levels using a GRU model, finding it reduced prediction error compared to SOTA methods for forecasts over two weeks, but real-time internet search data did not enhance GRU performance.
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.