2022 CDC West Nile virus Forecasting Challenge

This is the data repository for the 2022 CDC West Nile virus Forecasting Challenge. This is an open forecasting challenge to predict West Nile virus (WNV) neuroinvasive disease cases in U.S. counties during the 2022 calendar year.

Participation

To participate in the Challenge, please follow these steps:

  1. Request WNV data by sending a signed Data Use Agreement to vbd-predict@cdc.gov.
  2. Prepare metadata for your model.
  3. Submit the forecast by the deadlines.

For information on submitting forecasts to this project, please see the submission instructions. Participating teams provide their forecasts in a quantile-based format that will be evaluated according to these criteria.

Timeline

  • Project announcement and historical data release: Winter 2022.
  • Initial forecast due: April 30, 2022.
  • Additional forecasts due (optional): May 31, June 30, and July 31, 2022.
  • Additional optional forecast submissions allowed through Oct 31, 2022 (not formally evaluated).

Preliminary visualization

We developed an interactive app to visualize submitted forecasts. The app allows visualization of the median forecasted number of WNV neuroinvasive disease cases per county for 2022 as well as the forecasted probability that the count exceeds the county's 10-year median or maximum. We also provide a county-specific plot of forecasts for all participating teams and comparison models (i.e., median ensemble built from the final submissions (up to July) from teams and a negative binomial historical data model).

Background

West Nile virus (WNV) is the leading cause of arboviral disease in the contiguous United States. An estimated 70–80% of WNV infections are asymptomatic; 20‒30% of infected persons develop an acute systemic febrile illness and <1% of infected persons develop neuroinvasive disease (e.g., meningitis, encephalitis, or myelitis). Among patients with neuroinvasive disease, the case-fatality ratio is approximately 10%. Due to its severity and distinctive clinical features, diagnosis and reporting of neuroinvasive disease is considered more consistent and complete than that of non-neuroinvasive disease.

The first cases of WNV disease in the United States were identified in New York City in 1999; the virus subsequently spread westward, reaching the Pacific coast in 2003. Since then, WNV has caused seasonal summer outbreaks that vary in size and location, with most areas having sporadic disease or intermittent outbreaks. No vaccine or specific treatment of WNV is currently available. Reducing mosquito exposure through vector control and personal protective behaviors are the primary forms of prevention. Predicting where and when WNV transmission will occur could help direct control efforts.

Data license and reuse

We are grateful to the teams who have generated these forecasts and made their forecast data publicly available under different terms and licenses. By default, forecasts are available under the CC-BY 4.0 license, although teams may specify release under a different license in their metadata. You will find the licenses (when provided) within the metadata contained within model-specific folders in the data-forecasts directory. Please consult these licenses before using these data to ensure that you follow the terms under which these data were released.