Knowledge discovery and dengue forecasting applied in a four-year dataset collected at Natal, RN – Brazil

Dengue, a disease recognized as a health problem, causes significant impacts on health and affects millions of people each year worldwide. A suitable method for dengue vector surveillance is to count eggs the mosquitoes Aedes aegypti have laid in spatially distributed ovitraps. In view of this approach, this study uses a database collected in 397 ovitraps distributed across the municipality of Natal, RN – Brazil. The number of eggs in each ovitrap was counted weekly, over four years (2016 - 2019), and simultaneously analyzed with the incidence of dengue. Our results confirm that dengue incidence seems to be related to socioeconomic status in Natal. Using a deep learning model, we then predict the incidence of new dengue cases based on data obtained from the previous week of dengue or the number of eggs present in the ovitraps. The analysis shows that ovitrap data allows earlier detection (four to six weeks) when compared to dengue cases themselves (one week). Furthermore, the results confirm that quantifying Aedes aegypti eggs may be valuable for planning actions and public health interventions.