In:
PLOS Computational Biology, Public Library of Science (PLoS), Vol. 17, No. 3 ( 2021-3-29), p. e1008837-
Kurzfassung:
Predictions of COVID-19 case growth and mortality are critical to the decisions of political leaders, businesses, and individuals grappling with the pandemic. This predictive task is challenging due to the novelty of the virus, limited data, and dynamic political and societal responses. We embed a Bayesian time series model and a random forest algorithm within an epidemiological compartmental model for empirically grounded COVID-19 predictions. The Bayesian case model fits a location-specific curve to the velocity (first derivative) of the log transformed cumulative case count, borrowing strength across geographic locations and incorporating prior information to obtain a posterior distribution for case trajectories. The compartmental model uses this distribution and predicts deaths using a random forest algorithm trained on COVID-19 data and population-level characteristics, yielding daily projections and interval estimates for cases and deaths in U.S. states. We evaluated the model by training it on progressively longer periods of the pandemic and computing its predictive accuracy over 21-day forecasts. The substantial variation in predicted trajectories and associated uncertainty between states is illustrated by comparing three unique locations: New York, Colorado, and West Virginia. The sophistication and accuracy of this COVID-19 model offer reliable predictions and uncertainty estimates for the current trajectory of the pandemic in the U.S. and provide a platform for future predictions as shifting political and societal responses alter its course.
Materialart:
Online-Ressource
ISSN:
1553-7358
DOI:
10.1371/journal.pcbi.1008837
DOI:
10.1371/journal.pcbi.1008837.g001
DOI:
10.1371/journal.pcbi.1008837.g002
DOI:
10.1371/journal.pcbi.1008837.g003
DOI:
10.1371/journal.pcbi.1008837.g004
DOI:
10.1371/journal.pcbi.1008837.g005
DOI:
10.1371/journal.pcbi.1008837.s001
DOI:
10.1371/journal.pcbi.1008837.s002
DOI:
10.1371/journal.pcbi.1008837.s003
DOI:
10.1371/journal.pcbi.1008837.s004
DOI:
10.1371/journal.pcbi.1008837.s005
DOI:
10.1371/journal.pcbi.1008837.s006
DOI:
10.1371/journal.pcbi.1008837.s007
DOI:
10.1371/journal.pcbi.1008837.r001
DOI:
10.1371/journal.pcbi.1008837.r002
DOI:
10.1371/journal.pcbi.1008837.r003
DOI:
10.1371/journal.pcbi.1008837.r004
DOI:
10.1371/journal.pcbi.1008837.r005
DOI:
10.1371/journal.pcbi.1008837.r006
Sprache:
Englisch
Verlag:
Public Library of Science (PLoS)
Publikationsdatum:
2021
ZDB Id:
2193340-6
