Chronic Illness Diagnosis Helper: proposal of a tool to aid the diagnosis of chronic diseases through the historical analysis of symptomatic reports

• Autor(a) principal: Bastos, Michael Lopes
• Data de Publicação: 2020
• Outros Autores: Lins, Anthony José da Cunha Carneiro
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Revista de Engenharia e Pesquisa Aplicada
• Texto Completo: http://revistas.poli.br/index.php/repa/article/view/1354

According to data from the World Health Organization (WHO), the noncommunicable chronic diseases (NCD) are responsible for around 71% of deaths in all world. Thus, over the years some methods have been taken to try to reduce this index. Concerning to use of Technologies in this process, there are some initiatives in the context of Machine Learning (ML) that trying to find ways from diagnosis aid to support in certain types of treatments. Thus, this project has a goal to show a tool based on a machine learning model to health professionals to diagnosis NCD using symptomatic data derivates from base “Chronic illness” from the Kaggle platform. As the best result from this process, was choose a learning model based an ensemble technics, when the best accurate arrived at ≈ 71,63 % for some 20 pathologies, being this model used as bases to the application Chronic Illness Diagnosis Helper (CIDH), developed with an initial Prove of Concept.