ASSOCIAÇÃO ENTRE VARIÁVEIS SOCIOECONÔMICAS E A OCORRÊNCIA DE DENGUE NO ESTADO DE GOIÁS: UMA ANÁLISE A PARTIR DE ALGORITMOS DE MACHINE LEARNING

• Autor(a) principal: Gioia, Thamy Barbara
• Data de Publicação: 2022
• Outros Autores: Barros, Juliana Ramalho
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Hygeia (Uberlândia)
• Texto Completo: https://seer.ufu.br/index.php/hygeia/article/view/64263
• topic: Determinantes Sociais; Random Forest; XGBoost; KNN

Dengue is considered one of the diseases with the most significant rates in Brazil. The increasing rates directly affect public health services, so that evaluating the environmental and social conditions in areas with high rates of the disease can assist in the development of diagnoses and health actions. In this sense, the objective of this study was to identify the most important socioeconomic variables for the prediction of dengue prevalence rates in municipalities of the state of Goiás. The evaluation was performed based on 38 socioeconomic variables obtained from the database of Instituto Brasileiro de Geografia e Estatística - IBGE, Fundação João Pinheiro - FJP and from the calculation of dengue prevalence rates based on data available in Sistema de Informação de Agravos de Notificação - SINAN for the periods 2001-2009 and 2010-2018. Modeling was performed from the evaluation of three machine learning algorithms: Random Forest, XGBoost and KNN. The results indicated that the most important variables showed an inverse relationship to the conditions of low income, illiteracy and deficiency in basic sanitation services.