Gecko: A time-series model for COVID-19 hospital admission forecasting
Mark J. Panaggio,
Kaitlin Rainwater-Lovett,
Paul J. Nicholas,
Mike Fang,
Hyunseung Bang,
Jeffrey Freeman,
Elisha Peterson,
Samuel Imbriale
Affiliations
Mark J. Panaggio
Johns Hopkins University Applied Physics Laboratory, 11100 Johns Hopkins Road, Laurel, MD 20723, United States of America; Corresponding author.
Kaitlin Rainwater-Lovett
Johns Hopkins University Applied Physics Laboratory, 11100 Johns Hopkins Road, Laurel, MD 20723, United States of America
Paul J. Nicholas
Johns Hopkins University Applied Physics Laboratory, 11100 Johns Hopkins Road, Laurel, MD 20723, United States of America
Mike Fang
Johns Hopkins University Applied Physics Laboratory, 11100 Johns Hopkins Road, Laurel, MD 20723, United States of America
Hyunseung Bang
Johns Hopkins University Applied Physics Laboratory, 11100 Johns Hopkins Road, Laurel, MD 20723, United States of America
Jeffrey Freeman
Johns Hopkins University Applied Physics Laboratory, 11100 Johns Hopkins Road, Laurel, MD 20723, United States of America
Elisha Peterson
Johns Hopkins University Applied Physics Laboratory, 11100 Johns Hopkins Road, Laurel, MD 20723, United States of America
Samuel Imbriale
Office of the Assistant Secretary for Preparedness and Response, U.S. Department of Health and Human Services, Washington, DC, United States of America
During the COVID-19 pandemic, concerns about hospital capacity in the United States led to a demand for models that forecast COVID-19 hospital admissions. These short-term forecasts were needed to support planning efforts by providing decision-makers with insight about future demands for health care capacity and resources. We present a SARIMA time-series model called Gecko developed for this purpose. We evaluate its historical performance using metrics such as mean absolute error, predictive interval coverage, and weighted interval scores, and compare to alternative hospital admission forecasting models. We find that Gecko outperformed baseline approaches and was among the most accurate models for forecasting hospital admissions at the state and national levels from January–May 2021. This work suggests that simple statistical methods can provide a viable alternative to traditional epidemic models for short-term forecasting.
