JMIR Publications

ABSTRACT

Background:

Disease surveillance systems capable of producing accurate real-time and short-term forecasts can help public health officials design timely public health interventions to mitigate the effects of disease outbreaks in affected populations. In France, existing clinically-based disease surveillance systems produce Gastroenteritis activity information that lags real-time by one to three weeks. This temporal data gap prevents public health officials from having a timely epidemiological characterization of this disease at any point in time, and thus leads to the design of interventions that do not take into consideration the most recent changes in dynamics.

Objective:

Our main goal is to evaluate the feasibility of using Internet search query trends and hospital data to predict gastroenteritis incidence rates in near real time, at the national and regional scales and for longer-term forecasts.

Methods:

We present two machine learning approaches that produce real-time estimates, short-term forecasts, and long-term forecasts of acute gastroenteritis activity at different spatial resolutions in France. Both approaches leverage disparate data sources that include: disease-related Internet search activity, electronic health records data, and historical disease activity.

Results:

Our results suggest that all data sources contribute to improving Gastroenteritis surveillance for longer-term forecasts with a prominent predictive power of historical data due to the strong seasonal dynamics of this disease.

Conclusions:

The methods we developed could help reduce the impact of the acute gastroenteritis peak by making it possible to anticipate increased activity by up to 10 weeks.