Interpretable Sequence Learning for COVID-19 Forecasting

TL;DR

This paper introduces an interpretable machine learning model integrated with compartmental disease modeling to forecast COVID-19 progression, providing accurate and explainable predictions at various geographic levels.

Contribution

It presents a novel explainable modeling approach combining machine learning with epidemiological compartments, enhancing forecast accuracy and interpretability for COVID-19.

Findings

Outperforms state-of-the-art models in forecasting accuracy.

Provides meaningful explanatory insights into disease progression.

Effective at multiple geographic resolutions, including states and counties.

Abstract

We propose a novel approach that integrates machine learning into compartmental disease modeling to predict the progression of COVID-19. Our model is explainable by design as it explicitly shows how different compartments evolve and it uses interpretable encoders to incorporate covariates and improve performance. Explainability is valuable to ensure that the model's forecasts are credible to epidemiologists and to instill confidence in end-users such as policy makers and healthcare institutions. Our model can be applied at different geographic resolutions, and here we demonstrate it for states and counties in the United States. We show that our model provides more accurate forecasts, in metrics averaged across the entire US, than state-of-the-art alternatives, and that it provides qualitatively meaningful explanatory insights. Lastly, we analyze the performance of our model for different subgroups based on the subgroup distributions within the counties.