Navegando por Autor "Lemos, Victor Luan de Lima"

Agora exibindo 1 - 1 de 1
  • Imagem de Miniatura
    Item
    Aplicação de modelagem computacional e inteligência artificial na classificação do risco de surtos de doenças infecciosas na cidade de Maceió, Alagoas
    (INSTITUTO FEDERAL DE ALAGOAS - Ifal, 2026-02-20) Oliveira, Samila Raphaela de; Silva, Cledja Karina Rolim da; http://lattes.cnpq.br/1770216488772332; Souza, Társis Marinho de; http://lattes.cnpq.br/9808563385937929; Souza, Társis Marinho de; http://lattes.cnpq.br/9808563385937929; Silva, Cledja Karina Rolim da; http://lattes.cnpq.br/1770216488772332; Santos, Edvonaldo Horácio dos; http://lattes.cnpq.br/8960641809330500; Silva, Leonardo Soares e; http://lattes.cnpq.br/4856480961305199
    Infectious diseases have historically represented a significant threat to populations worldwide and remain a relevant and priority challenge for public health, reinforcing the need for innovative strategies focused on prevention, surveillance, and control. In Brazil, despite the existence of national epidemiological surveillance systems, the occurrence of outbreaks and the reemergence of infectious diseases reveal limitations and vulnerabilities in the capacity to anticipate and respond to epidemic events. In this context, the early identification of risk patterns is essential to support timely public health actions. Within this scenario, models based on artificial intelligence have gained prominence due to their ability to identify complex patterns and support public health planning. These approaches have demonstrated performance comparable to or superior to traditional statistical methods, becoming essential tools for epidemic monitoring and control. Therefore, this study aims to analyze and compare computational models and machine learning algorithms applied to the classification of the risk of infectious disease outbreaks, using data from the Notifiable Diseases Information System (SINAN). The study seeks to contribute to the advancement of computational modeling in public health and to the strengthening of evidence-based strategies in epidemiological surveillance.