This paper describes an agent-based model framework developed to forecast the 2014-15 Ebola epidemic, which was subsequently used in the Ebola forecasting challenge. Producing timely and reliable forecasts for an epidemic of an emerging infectious disease is a challenge. Epidemiologists and policy makers have to deal with poor data quality, limited understanding of the disease dynamics, a rapidly changing social environment and the uncertainty around the effects of various interventions in place.
In this setting, detailed computational models provide a comprehensive framework for integrating diverse data sources into a well-defined model of disease dynamics and social behavior, potentially leading to better understanding and actions. The authors describe the various components of their model, the calibration process and summarize the forecast performance across different scenarios. They conclude by highlighting how such a data-driven approach can be refined and adapted for future epidemics.
Venkatramanan S, Lewis B, Chen J et al. Using Data-Driven Agent-Based Models for Forecasting Emerging Infectious Diseases. Epidemics 2017. https://doi.org/10.1016/j.epidem.2017.02.010