Forecasts of Flu Hospital Admissions

Interpretation of forecasts of new hospital admissions

• Ensemble forecasts combine forecasts from all submitted models into one forecast. These forecasts have been among the most accurate for previous influenza forecasting efforts but may not reliably predict rapid changes in disease trends. This week, 34 modeling groups contributed 42 forecasts that were eligible for inclusion in the ensemble forecasts for at least one jurisdiction. Contributing teams are listed below.
• The interactive figure shows the number of new laboratory-confirmed influenza hospital admissions reported in the United States each week from October 2025 through October 17, 2026 reported as of October 21, 2026, and forecasted new influenza hospital admissions per week for this week and the next two weeks, through November 7, 2026. The colored areas on the graph show prediction intervals, which indicate the bounds of uncertainty around the forecast estimates.

National and state forecasts

• The forecasted hospital admission rates (for both median and prediction intervals) use Census Vintage 2024 population estimates as a population denominator for the state. We note that the denominator for rates may not capture the exact catchment populations of the hospitals in each state, but rates provide a rough adjustment for population size, allowing comparison across states with different population sizes.
• Hospitals are required to report weekly laboratory-confirmed influenza hospitalizations to the National Healthcare Safety Network (NHSN). See Guidance for Hospital Reporting and FAQs for additional details on this guidance. Historical data from NHSN are not shown from April 27-October 31, 2024, due to the pause in mandatory reporting.
• The following jurisdictions had <80% of hospitals reporting for the most recent week: Alaska, Arkansas, California, District of Columbia, Georgia, Hawaii, Idaho, Illinois, Iowa, Kansas, Kentucky, Louisiana, Maine, Maryland, Minnesota, Mississippi, Missouri, Montana, Nebraska, Nevada, New Mexico, North Dakota, Ohio, Oklahoma, Oregon, Puerto Rico, Rhode Island, Texas, US, Vermont, Virginia and Wyoming. Lower reporting rates could impact forecast validity. Percent of hospitals reporting is calculated based on the number of active hospitals reporting complete data to NHSN for a given reporting week.
• Forecast submissions are collected and stored in the FluSight GitHub repository, which also contains more detailed information about the forecast data and submission process.

Additional materials

Contributing teams and models

Atlantic Coast Center for Infectious Disease Dynamics and Analytics (Model: ACCIDDA-Chromantis)

bayvaxbio (Model: bayvaxbio-CountCast)

Branching Process Collective at Northeastern University (Model: NU-EMBERS)

BYFlu (Model: BYFlu-STMGGP)

California Department of Public Health (Model: CADPH-FluCAT_Ensemble)

Carnegie Mellon Delphi Group (Model: CMU-TimeSeries)

Center for Forecasting and Outbreak Analytics (CDC/CFA) (Model: CFA-PyRenew_E)

CEPH Lab at Indiana University (Model: CEPH-Rtrend_fluH)

Columbia University (Model: CU-ensemble)

Columbia University (Model: CU-STS_Residual)

Complex Intelligence Lab (Model: Xi_lab-GLEAM_AI)

Complex Intelligence Lab (Model: Xi_lab-GLEAM_AI_hybrid)

Cornell_JHU (Model: Cornell_JHU-SCARCHhierarSIR)

CPHMR, Clemson University (Model: DMAPRIME-QR)

CPHMR, Clemson University (Model: DMAPRIME-HYB)

docxology (Model: docxology-panelqr)

Epistorm: Center for Advanced Epidemic Analytics and Predictive Modeling Technology (Model: Epistorm-Ensemble_Flu)

Gatech-ISYE-TS (Model: Gatech-ensemble_prob)

Gatech-ISYE-TS (Model: Gatech-ensemble_stat)

Georgia Tech VIP Responsible AI - Influencers (Model: GT_Influencers-ensemble)

HallAI (Model: HallAI-FluTrend)

LUcompUncertLab (Model: LUcompUncertLab-puca)

MIGHTE (Model: MIGHTE-Base)

MIGHTE (Model: MIGHTE-Nsemble)

MOBS Lab at Northeastern University and ISI Foundation (Model: NEU_ISI-FluBcast)

MOBS Lab at Northeastern University (Model: MOBS-EpyStrain_Flu)

MOBS Lab at Northeastern University (Model: MOBS-GLEAM_NCB_FLUH)

NAU (Model: NAU-FourCAT)

Northeastern University (Model: NU-FLARE)

Northern Arizona University and Los Alamos National Lab (Model: NAU_PyBNF-GroundHogCGR)

Northern Arizona University and Los Alamos National Lab (Model: NAU_PyBNF-OracleSIHRS)

Northern Arizona University (Model: NAU-epymorph)

One Health Trust and Johns Hopkins University (Model: OHT_JHU-nbxd)

Predictive Science Inc. (Model: PSI-PROF)

Predictive Science Inc. (Model: PSI-PROF_MOA)

Sentinel (Model: Sentinel-Ens)

UGA Center for the Ecology of Infectious Diseases (CEID) (Model: UGA_CEID-auto_AVG_LB)

UGA_flucast (Model: UGA_flucast-INFLAenza)

UMass-Amherst (Model: UMass-flusion)

University of Michigan, Computer Science and Engineering (Model: UM-DeepOutbreak)

UVAFluX (Model: UVAFluX-Ensemble)

VTSanghani (Model: VTSanghani-PRIME)