Forecasting the 2013–2014 Influenza Season Using Wikipedia

Infectious diseases are one of the leading causes of morbidity and mortality around the world; thus, forecasting their impact is crucial for planning an effective response strategy. According to the Centers for Disease Control and Prevention (CDC), seasonal influenza affects 5% to 20% of the U.S. population and causes major economic impacts resulting from hospitalization and absenteeism. Understanding influenza dynamics and forecasting its impact is fundamental for developing prevention and mitigation strategies. We combine modern data assimilation methods with Wikipedia access logs and CDC influenza-like illness (ILI) reports to create a weekly forecast for seasonal influenza. The methods are applied to the 2013-2014 influenza season but are sufficiently general to forecast any disease outbreak, given incidence or case count data. We adjust the initialization and parametrization of a disease model and show that this allows us to determine systematic model bias. In addition, we provide a way to determine where the model diverges from observation and evaluate forecast accuracy. Wikipedia article access logs are shown to be highly correlated with historical ILI records and allow for accurate prediction of ILI data several weeks before it becomes available. The results show that prior to the peak of the flu season, our forecasting method produced 50% and 95% credible intervals for the 2013-2014 ILI observations that contained the actual observations for most weeks in the forecast. However, since our model does not account for re-infection or multiple strains of influenza, the tail of the epidemic is not predicted well after the peak of flu season has passed.Author Summary: We use modern methods for injecting current data into epidemiological models in order to offer a probabilistic evaluation of the future influenza state in the U.S. population. This type of disease forecasting is still in its infancy, but as these methods become more developed it will allow for increasingly robust control measures to react to and prevent large disease outbreaks. While weather forecasting has steadily improved over the last half century and become ubiquitous in modern life, there is surprisingly little work on infectious disease forecasting. Although there has been a great deal of work in modeling disease dynamics, these have seldom been used to generate a probabilistic description of expected future dynamics, given current public health data. Moreover, the mechanism to update expected disease outcomes as new data becomes available is just beginning to receive attention from the public health community. Using CDC influenza-like illness reports and digital monitoring sources, such as observations of Wikipedia article access logs, we are now at a point where forecasting for the influenza season can begin to offer useful information for disease monitoring and mitigation.