Estimating County-Level COVID-19 Exponential Growth Rates Using Generalized Random Forests
This work addresses a practical challenge in public health for policymakers and health officials, but it is incremental as it builds on existing generalized random forest methods.
The paper tackled the problem of balancing accuracy and speed in detecting county-level COVID-19 outbreaks by using generalized random forests to adaptively choose fitting window sizes based on features like social distancing policies. The result showed that this method outperformed non-adaptive window size choices in 7-day ahead case number predictions.
Rapid and accurate detection of community outbreaks is critical to address the threat of resurgent waves of COVID-19. A practical challenge in outbreak detection is balancing accuracy vs. speed. In particular, while estimation accuracy improves with longer fitting windows, speed degrades. This paper presents a machine learning framework to balance this tradeoff using generalized random forests (GRF), and applies it to detect county level COVID-19 outbreaks. This algorithm chooses an adaptive fitting window size for each county based on relevant features affecting the disease spread, such as changes in social distancing policies. Experiment results show that our method outperforms any non-adaptive window size choices in 7-day ahead COVID-19 outbreak case number predictions.