Online Program

A Predictive Internet-Based Model for COVID-19 Hospitalization Census (309687)

Andrew McWilliams, Atrium Health 
Geoff Rose, Atrium Health 
Thao Tran, Atrium Health 
*Philip Turk, Atrium Health 

Keywords: COVID, modeling, forecasting, epidemiology, surveillance

The COVID-19 pandemic has strained hospital resources and necessitated the need for predictive models to forecast patient care demands in order to allow for adequate staffing and resource allocation. Recently, other studies have looked at associations between Google Trends data and the number of COVID-19 cases. Expanding on this approach, we propose a vector error correction model (VECM) for the number of COVID-19 patients in a healthcare system (Census) that incorporates Google search term activity and healthcare chatbot scores. The VECM provided a good fit to Census and very good forecasting performance as assessed by hypothesis tests and mean absolute percentage prediction error. We demonstrate the VECM can potentially be a valuable component to a COVID-19 surveillance program in a healthcare system.

This talk is a tribute to Jim Harner. Our numerous late-night conversations provided intellectual fodder for ideas. He provided me a valuable professional opportunity to gain experience and would have wanted this research to make a difference in the battle against COVID-19.