Parallel prediction of dengue cases with different risks in Mexico using an artificial neural network model considering meteorological data.

In 2022, Mexico registered an increase in dengue cases compared to the previous year. On the other hand, the amount of precipitation reported annually was slightly less than the previous year. Similarly, the minimum-mean-maximum temperatures recorded annually were below the previous year. In the literature, it is possible to find studies focused on the spread of dengue only for some specific regions of Mexico. However, given the increase in the number of cases during 2022 in regions not considered by previously published works, this study covers cases reported in all states of the country. On the other hand, determining a relationship between the dynamics of dengue cases and climatic factors through a computational model can provide relevant information on the transmission of the virus. A multiple-learning computational approach was developed to simulate the number of the different risks of dengue cases according to the classification reported per epidemiological week by considering climatic factors in Mexico. For the development of the model, the data were obtained from the reports published in the Epidemiological Panorama of Dengue in Mexico and in the National Meteorological Service. The classification of non-severe dengue, dengue with warning signs, and severe dengue were modeled in parallel through an artificial neural network model. Five variables were considered to train the model: the monthly average of the minimum, mean, and maximum temperatures, the precipitation, and the number of the epidemiological week. The selection of variables in this work is focused on the spread of the different risks of dengue once the mosquito begins transmitting the virus. Therefore, temperature and precipitation were chosen as climatic factors due to the close relationship between the density of adult mosquitoes and the incidence of the disease. The Levenberg-Marquardt algorithm was applied to fit the coefficients during the learning process. In the results, the ANN model simulated the classification of the different risks of dengue with the following precisions (R): 0.9684, 0.9721, and 0.8001 for non-severe dengue, with alarm signs and severe, respectively. Applying a correlation matrix and a sensitivity analysis of the ANN model coefficients, both the average minimum temperature and precipitation were relevant to predict the number of dengue cases. Finally, the information discovered in this work can support the decision-making of the Ministry of Health to avoid a syndemic between the increase in dengue cases and other seasonal diseases.