Spatial-Temporal Convolutional Network for Spread Prediction of COVID-19
This work addresses the problem of predicting COVID-19 patient numbers for public health officials and healthcare systems, enabling better resource allocation and response planning.
This paper proposes a spatial-temporal convolutional neural network to predict future COVID-19 symptom severity per region based on past reported symptoms. The model aims to approximate future patient numbers to enable faster response, such as hospital preparation or local lockdowns.
In this work we present a spatial-temporal convolutional neural network for predicting future COVID-19 related symptoms severity among a population, per region, given its past reported symptoms. This can help approximate the number of future Covid-19 patients in each region, thus enabling a faster response, e.g., preparing the local hospital or declaring a local lockdown where necessary. Our model is based on a national symptom survey distributed in Israel and can predict symptoms severity for different regions daily. The model includes two main parts - (1) learned region-based survey responders profiles used for aggregating questionnaires data into features (2) Spatial-Temporal 3D convolutional neural network which uses the above features to predict symptoms progression.