A hypothesis-free bridging of disease dynamics and non-pharmaceutical policies

TL;DR

This paper introduces a hybrid, hypothesis-free machine learning approach combining mechanistic disease modeling with data-driven policy analysis to improve COVID-19 case forecasting.

Contribution

It develops a novel hybrid model using a mechanistic ODE and GBM, with an inverse method to estimate transmission rates from policy data, enhancing prediction accuracy.

Findings

Achieved 27% mean absolute percentage error in 35-day forecasts.

Identified key policy variables influencing transmission rates.

More accurate and interpretable than purely mechanistic or data-driven models.

Abstract

Accurate prediction of the number of daily or weekly confirmed cases of COVID-19 is critical to the control of the pandemic. Existing mechanistic models nicely capture the disease dynamics. However, to forecast the future, they require the transmission rate to be known, limiting their prediction power. Typically, a hypothesis is made on the form of the transmission rate with respect to time. Yet the real form is too complex to be mechanistically modeled due to the unknown dynamics of many influential factors. We tackle this problem by using a hypothesis-free machine-learning algorithm to estimate the transmission rate from data on non-pharmaceutical policies, and in turn forecast the confirmed cases using a mechanistic disease model. More specifically, we build a hybrid model consisting of a mechanistic ordinary differential equation (ODE) model and a generalized boosting model (GBM). To calibrate the parameters, we develop an "inverse method" that obtains the transmission rate inversely in time from the other variables in the ODE model and then feed it into the GBM to connect with the policy data. The resulting model forecasted the number of daily confirmed cases up to 35 days in the future in the United States with an averaged mean absolute percentage error of 27%. Being partly data-driven, the method is more accurate than typical mechanistic models and meanwhile more intuitive, and possibly reliable, than purely data-based machine learning models. Moreover, it can identify the most informative predictive variables, which can be helpful in designing improved forecasters as well as informing policymakers.