Towards a machine learning-based approach to forecasting Dengue virus outbreaks in Colombian cities. A case-study: Medellín, Antioquia

摘要

The geographical conditions of Colombia favor the re-emergence and propagation of infectious tropical diseases.Among them, the Dengue virus is highly endemic throughout the country, thereby locating this arbovirus as oneof the major pathologies of the public health system. Therefore, there is a global challenge to generate novelstrategies to predict and control dengue virus transmission. In particular, during the Colombian 2016 Dengueoutbreak, more than 17 thousand Dengue cases were reported by the health authorities of Medellín, Antioquia.In this paper, we present a machine learning approach for the early detection of dengue outbreaks in the city ofMedellin. We use an artificial neural network as the core of the machine learning algorithm, with environmental,meteorological and epidemiological data from the National Institute of Health -SIVIGILA- and the Aburrá ValleyEarly Warning System -SIATA-. Our objective is to identify possible Dengue outbreaks, i.e. to create an earlywarning system, to provide a preventive timeline to the health authorities to design contingency plans and tomitigate the impact of dengue on the population of Medellin. Our results indicate that a artificial neural networkforecasting for time series shows a trend for the correct prediction of dengue cases up to the first four weeks with adeterioration in precision as the forecast is pushed for additional ten to twenty weeks.