Influenza forecasting for the French regions by using EHR, web and climatic data sources with an ensemble approach ARGONet

Effective and timely disease surveillance systems have the potential to help public health officials design interventions to mitigate the effects of disease outbreaks. Currently, healthcare-based disease monitoring systems in France offer influenza activity information that lags real-time by 1 to 3 weeks. This temporal data gap introduces uncertainty that prevents public health officials from having a timely perspective on the population-level disease activity. Here, we present a machine-learning modeling approach that produces real-time estimates and short-term forecasts of influenza activity for the 12 continental regions of France by leveraging multiple disparate data sources that include, Google search activity, real-time and local weather information, flu-related Twitter micro-blogs, electronic health records data, and historical disease activity synchronicities across regions. Our results show that all data sources contribute to improving influenza surveillance and that machine-learning ensembles that combine all data sources lead to accurate and timely predictions. Author summary The role of public health is to protect the health of populations by providing the right intervention to the right population at the right time. In France and all around the world, Influenza is a major public health problem. Traditional surveillance systems produce estimates of influenza-like illness (ILI) incidence rates, but with one-to three-week delay. Accurate real-time monitoring systems of influenza outbreaks could be useful for public health decisions. By combining different data sources and different statistical models, we propose an accurate and timely forecasting platform to track the flu in France at a spatial resolution that, to our knowledge, has not been explored before.