Forecasts of Flu Hospitalizations
Updated June 21, 2022
The June 20th flu forecast summary is the last of the 2021-2022 season. Flu forecasting summaries for the 2022-2023 season will begin again in fall 2022.
Reported and forecasted new influenza hospitalizations as of June 20, 2022.
Interpretation of National Forecasts of New Hospitalizations
- This week’s ensemble predicts that the number of new weekly confirmed influenza hospital admissions will likely decrease nationally, with 400 to 2,400 new confirmed influenza hospital admissions likely reported in the week ending July 16, 2022.
- This week, 15 modeling groups contributed one or more forecasts that were eligible for inclusion in the new hospitalization ensemble forecasts for at least one jurisdiction. Contributing teams are listed below.
- Ensemble forecasts combine diverse independent team forecasts into one forecast. They have been among the most reliable forecasts in performance for previous influenza and COVID-19 forecasts, but even the ensemble forecasts may not reliably predict rapid changes in the trends.
- The figure shows the number of new confirmed influenza hospital admissions reported in the United States each week from September 26 through June 18 and forecasted new influenza hospital admissions per week over the next 4 weeks, through July 16. Effective February 2, 2022, hospitals are required to report laboratory-confirmed influenza hospitalizations to HHS Protect daily. Prior to this update, reporting influenza hospitalizations was optional (noted as grey in the above figure). See COVID-19 Guidance for Hospital Reporting and FAQs for additional details on this guidance.
State-level forecasts show the predicted number of new influenza hospital admissions per week for the next 4 weeks by state. Each state forecast figure uses a different scale due to differences in the number of new influenza hospital admissions per week between states and only forecasts included in the ensemble are shown. Plots of the state-level ensemble forecasts and the underlying data can be downloaded below.
Additional forecast data and information about submitting forecasts are available at https://github.com/cdcepi/Flusight-forecast-data.
Carnegie Mellon Delphi Group (Model: CMU-TimeSeries)
Columbia University (Model: CU-ensemble)
Georgia Institute of Technology (Model: GT-FluFNP)
Guidehouse FluSight Team (Model: GH-Flusight)
IEM Health (Model: IEM_Health-FluProject)
Los Alamos National Lab and Northern Arizona University (Model: LosAlamos_NAU-CModel_Flu)
MOBS Lab at Northeastern (Model: MOBS-GLEAM_FLUH)
Predictive Science Inc (Model: PSI-DICE)
Signature Science (Model: SigSci-CREG)
Signature Science (Model: SigSci-TSENS)
Srivastava Group (Model: SGroup-RandomForest)
Srivastava Group (Model: SGroup-SIkJalpha)
University of Massachusetts-Amherst (Model: ARIMA)
University of Massachusetts-Amherst (Model: UMass-trends_ensemble)
University of Texas FluCast (Model: UT_FluCast-Voltaire)
University of Virginia, Biocomplexity Institute (Model: UVAFluX-Ensemble)
Virginia Tech, Sanghani Center for Artificial Intelligence and Data Analytics (Model: VTSanghani-ExogModel)