Epidemic Prediction Initiative

Moving forecasting from research to decisions

The Epidemic Prediction Initiative (EPI) aims to improve the science and usability of epidemic forecasts by facilitating open forecasting projects with specific public health objectives.

Timely interventions like vaccinations can prevent or control the adverse impacts of epidemics on human health. However, prediction of epidemics is challenging. For example, the incidence of dengue – a vector-borne disease affecting approximately 100 million people per year – can increase 3-5 fold during an epidemic, yet no clear indicator of the intensity or timing of an epidemic exists until it is already underway. Influenza and other globally important diseases present similar challenges. Advances in forecasting for these diseases and others are continually occurring, yet research gaps limit forecasting model development, evaluation of forecasts, and adoption by decision-makers. The Epidemic Prediction Initiative was launched in 2014 to improve the science and usability of forecasts by addressing these challenges.

Beginning in January 2016, EPI published influenza forecasts from participating teams in real-time on a dedicated EPI website. This was the first time that infectious disease forecasts from multiple groups were published jointly in real-time, facilitating forecast comparison and evaluation by public health officials. EPI also initiated and maintains an open online repository of code and data related to epidemics. This activity aims to standardize data formats and support forecasting research. EPI has also worked across CDC, among other federal government agencies, with local and international public health officials, and in the academic community to better understand how to improve forecast accuracy and how forecasts can be used in public health decision making.

FluSight Hospitalization Forecasting

Weekly forecasts of influenza hospitalizations for the US and US states

COVID-19 Forecasting

Weekly forecasts of COVID-19 cases (2020-2021) and deaths (2020-2023) and daily forecasts of COVID-19 hospitalizations (2020-present) for the US, US states, and US counties (cases only)

Aedes Forecasting 2019-2020

Monthly forecasts of Aedes aegypti and Aedes albopictus for a subset of US counties

WNV Forecasting 2020, 2022, and 2023

Annual forecasts of neuroinvasive WNV disease cases for all counties in the contiguous US (2020, 2022) and monthly forecasts of neuroinvasive WNV disease cases for all states in the contiguous US (2023)

State FluSight 2019-2020

Weekly and seasonal forecasts of influenza-like-illness for US states

DoD Influenza Forecasting 2019-2020

Weekly and seasonal forecasts of influenza-like-illness for 28 US Military Treatment Facilities

Influenza Hospitalizations 2018–2019

Weekly and seasonal forecasts of laboratory confirmed influenza hospitalizations by age group for FluSurv-NET

FluSight 2015-2020

Weekly and seasonal forecasts of influenza-like-illness for the US and the 10 Department of Health and Human Services regions in the US

Dengue Forecasting Project 2015

Retrospective seasonal forecasts of dengue incidence in Iquitos, Peru and San Juan, Puerto Rico