RSV Ensemble Forecasts

What to know

  • The RSVHub ensemble predicts that for the week ending April 18, 2026, the weekly percentage of new emergency department (ED) visits due to RSV in the United States will be 0.25% (95% prediction interval: 0.15%-0.42%). The median forecast suggests a decrease from 0.32%, which was reported for the week ending April 4, 2026 (the most recent week of reporting).
  • The ensemble also predicts that the number of new laboratory-confirmed RSV hospital admissions in the United States during the week ending April 18, 2026 will be approximately 1,500 (770 - 3,200). The median forecast suggests a decrease compared to the 2,800 admissions so far reported for the week ending April 4, 2026. Of note, these forecasts are based on NHSN hospital admissions data. NHSN reported hospital admissions may differ from the data reported by RSV-NET.
NULL

National and state forecasts

Note

Model ensembles can perform better when they average out errors from individual models. However, individual models can still outperform the ensemble, especially when the number of ensembled models is low.

Ensemble models are only displayed when at least two models are included.

Select forecast location, date, and models below. Modeling based on forecasts submitted by . Click and drag to change the forecast date to see how previous forecasts performed against reported data.

Historical data
Forecast median prediction interval Name

Select Models

Click on models to see and compare forecasts

Export this chart (PDF) Download data (CSV)

Interpretation of forecasts

  • Overview: Forecasted percent of ED visits and new hospital admissions due to RSV. This week, 2 modeling groups contributed 2 forecasts of ED visits and 5 modeling groups contributed 5 forecasts of hospital admissions that were eligible for inclusion in the ensemble forecasts for at least one jurisdiction. Contributing teams are listed below. Of note, the hospital admissions forecasts are based on NHSN hospital admissions data. NHSN reported hospital admissions may differ from the data reported by RSV-NET.
  • What are ensemble models?: Ensemble forecasts combine forecasts from all submitted models into one forecast. These forecasts have been among the most accurate for previous RSV forecasting efforts but may not reliably predict rapid changes in disease trends.
  • What does the figure show?: The figure shows the percentage of RSV emergency department visits each week reported from October 1, 2022 through April 4, 2026, number of new laboratory-confirmed RSV hospital admissions reported in the United States each week from August 8, 2020 through April 4, 2026, and forecasted new RSV emergency department visits and hospital admissions per week for this week and the next 2 weeks through April 25, 2026. The colored areas on the graph show prediction intervals, which indicate the bounds of uncertainty around the forecast estimates.

How and why are the forecasts different?

In April 2026, we started publishing weekly forecast ensembles with both percentage of new emergency department (ED) visits due to RSV and RSV hospital admission counts. Emergency department visit forecasts represent RSV as a proportion of ED visits, aggregated by week and jurisdiction.

Individuals may seek care in an emergency room before being hospitalized; as such, hospital admission rates tend to lag ED visit percentages due to RSV by 1-2 weeks. Because of this, ED visit forecasts may differ from hospital admission forecasts and can provide a more timely indication of disease trends by week and jurisdiction.

  • How do we calculate the rates/percentages? The forecasted percentages of ED visits due to RSV are calculated by dividing the number of visits with a discharge diagnosis of RSV in a one-week period (the numerator) by the total number of ED visits in the same period (denominator) at the relevant jurisdictional level. The forecasted hospital admission rates (for both median and prediction intervals) use Census Vintage 2023 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.
  • The following jurisdictions had <80% of hospitals reporting for the most recent week:. Alabama, Alaska, Arkansas, California, Colorado, District of Columbia, Florida, Georgia, Hawaii, Idaho, Illinois, Iowa, Kansas, Kentucky, Louisiana, Maryland, Michigan, Mississippi, Missouri, Montana, Nebraska, Nevada, New Mexico, New York, Oklahoma, Oregon, Puerto Rico, South Dakota, Texas, United States, Vermont, Virginia, and Wyoming.
    • Percent of hospitals reporting is calculated based on the number of active facilities reporting complete data to NHSN for a given reporting week.
  • More Information: Forecast submissions are collected and stored in the RSV Forecast Hub GitHub repository, which also contains more detailed information about the forecast data and submission process.
    • A data dictionary for the downloadable CSV is also available in a public GitHub depository.

Contributing teams and models

Individual model websites are linked where available.

Print
Content Source:
Center for Forecasting and Outbreak Analytics