An Ensemble -sub-epidemic Modeling Framework for Short-term Forecasting Epidemic Trajectories: Application to the COVID-19 Pandemic in the USA

Overview

Journal medRxiv

Date 2022 Jul 7

PMID 35794886

Authors

Gerardo Chowell

Sushma Dahal

Amna Tariq

Kimberlyn Roosa

James M Hyman

Ruiyan Luo

Affiliations

Soon will be listed here.

Abstract

Summary: The COVID-19 pandemic has highlighted the urgent need to develop reliable tools to forecast the trajectory of epidemics and pandemics in near real-time. We describe and apply an ensemble -sub-epidemic modeling framework for forecasting the trajectory of epidemics and pandemics. We systematically assess its calibration and short-term forecasting performance in weekly 10-30 days ahead forecasts for the COVID-19 pandemic in the USA from late April 2020 to late February 2022 and compare its performance with two different statistical ARIMA models. This framework demonstrated reliable forecasting performance and substantially outcompeted the ARIMA models. The forecasting performance was consistently best for the ensemble sub-epidemic models incorporating a higher number of top-ranking sub-epidemic models. The ensemble model incorporating the top four ranking sub-epidemic models consistently yielded the best performance, particularly in terms of the coverage rate of the 95% prediction interval and the weighted interval score. This framework can be applied to forecast other growth processes found in nature and society including the spread of information through social media.

References

Yamana T, Kandula S, Shaman J . Superensemble forecasts of dengue outbreaks. J R Soc Interface. 2016; 13(123). PMC: 5095208. DOI: 10.1098/rsif.2016.0410. View

Roosa K, Tariq A, Yan P, Hyman J, Chowell G . Multi-model forecasts of the ongoing Ebola epidemic in the Democratic Republic of Congo, March-October 2019. J R Soc Interface. 2020; 17(169):20200447. PMC: 7482568. DOI: 10.1098/rsif.2020.0447. View

Ray E, Reich N . Prediction of infectious disease epidemics via weighted density ensembles. PLoS Comput Biol. 2018; 14(2):e1005910. PMC: 5834190. DOI: 10.1371/journal.pcbi.1005910. View

Johansson M, Apfeldorf K, Dobson S, Devita J, Buczak A, Baugher B . An open challenge to advance probabilistic forecasting for dengue epidemics. Proc Natl Acad Sci U S A. 2019; 116(48):24268-24274. PMC: 6883829. DOI: 10.1073/pnas.1909865116. View

Funk S, Camacho A, Kucharski A, Lowe R, Eggo R, Edmunds W . Assessing the performance of real-time epidemic forecasts: A case study of Ebola in the Western Area region of Sierra Leone, 2014-15. PLoS Comput Biol. 2019; 15(2):e1006785. PMC: 6386417. DOI: 10.1371/journal.pcbi.1006785. View

Taylor K, Taylor J . Interval forecasts of weekly incident and cumulative COVID-19 mortality in the United States: A comparison of combining methods. PLoS One. 2022; 17(3):e0266096. PMC: 8963571. DOI: 10.1371/journal.pone.0266096. View

Chowell G, Luo R, Sun K, Roosa K, Tariq A, Viboud C . Real-time forecasting of epidemic trajectories using computational dynamic ensembles. Epidemics. 2019; 30:100379. DOI: 10.1016/j.epidem.2019.100379. View

Chowell G, Luo R . Ensemble bootstrap methodology for forecasting dynamic growth processes using differential equations: application to epidemic outbreaks. BMC Med Res Methodol. 2021; 21(1):34. PMC: 7882252. DOI: 10.1186/s12874-021-01226-9. View

Watson G, Xiong D, Zhang L, Zoller J, Shamshoian J, Sundin P . Pandemic velocity: Forecasting COVID-19 in the US with a machine learning & Bayesian time series compartmental model. PLoS Comput Biol. 2021; 17(3):e1008837. PMC: 8031749. DOI: 10.1371/journal.pcbi.1008837. View

10.

Roosa K, Lee Y, Luo R, Kirpich A, Rothenberg R, Hyman J . Real-time forecasts of the COVID-19 epidemic in China from February 5th to February 24th, 2020. Infect Dis Model. 2020; 5:256-263. PMC: 7033348. DOI: 10.1016/j.idm.2020.02.002. View

11.

Chowell G, Hincapie-Palacio D, Ospina J, Pell B, Tariq A, Dahal S . Using Phenomenological Models to Characterize Transmissibility and Forecast Patterns and Final Burden of Zika Epidemics. PLoS Curr. 2016; 8. PMC: 4922743. DOI: 10.1371/currents.outbreaks.f14b2217c902f453d9320a43a35b9583. View

12.

Bracher J, Ray E, Gneiting T, Reich N . Evaluating epidemic forecasts in an interval format. PLoS Comput Biol. 2021; 17(2):e1008618. PMC: 7880475. DOI: 10.1371/journal.pcbi.1008618. View

13.

Zhang S, Ponce J, Zhang Z, Lin G, Karniadakis G . An integrated framework for building trustworthy data-driven epidemiological models: Application to the COVID-19 outbreak in New York City. PLoS Comput Biol. 2021; 17(9):e1009334. PMC: 8452065. DOI: 10.1371/journal.pcbi.1009334. View

14.

McGowan C, Biggerstaff M, Johansson M, Apfeldorf K, Ben-Nun M, Brooks L . Collaborative efforts to forecast seasonal influenza in the United States, 2015-2016. Sci Rep. 2019; 9(1):683. PMC: 6346105. DOI: 10.1038/s41598-018-36361-9. View

15.

Roy S, Bhunia G, Shit P . Spatial prediction of COVID-19 epidemic using ARIMA techniques in India. Model Earth Syst Environ. 2020; 7(2):1385-1391. PMC: 7363688. DOI: 10.1007/s40808-020-00890-y. View

16.

Farcomeni A, Maruotti A, Divino F, Jona-Lasinio G, Lovison G . An ensemble approach to short-term forecast of COVID-19 intensive care occupancy in Italian regions. Biom J. 2020; 63(3):503-513. PMC: 7753356. DOI: 10.1002/bimj.202000189. View

17.

Rguibi M, Moussa N, Madani A, Aaroud A, Zine-Dine K . Forecasting Covid-19 Transmission with ARIMA and LSTM Techniques in Morocco. SN Comput Sci. 2022; 3(2):133. PMC: 8758931. DOI: 10.1007/s42979-022-01019-x. View

18.

Reich N, Brooks L, Fox S, Kandula S, McGowan C, Moore E . A collaborative multiyear, multimodel assessment of seasonal influenza forecasting in the United States. Proc Natl Acad Sci U S A. 2019; 116(8):3146-3154. PMC: 6386665. DOI: 10.1073/pnas.1812594116. View

19.

Novaes de Amorim A, Deardon R, Saini V . A stacked ensemble method for forecasting influenza-like illness visit volumes at emergency departments. PLoS One. 2021; 16(3):e0241725. PMC: 7984626. DOI: 10.1371/journal.pone.0241725. View

20.

Hwang E . Prediction intervals of the COVID-19 cases by HAR models with growth rates and vaccination rates in top eight affected countries: Bootstrap improvement. Chaos Solitons Fractals. 2022; 155:111789. PMC: 8720534. DOI: 10.1016/j.chaos.2021.111789. View