Análise epidemiológica : algoritmos de aprendizado de máquina para classificação de doenças
Tipo
TCC
Data de publicação
2019-06
Periódico
Citações (Scopus)
Autores
Morelli, Antônio Victor Ribeiro
Silva, Luciano
Silva, Luciano
Orientador
Silva, Luciano
Título da Revista
ISSN da Revista
Título de Volume
Membros da banca
Programa
Resumo
O objetivo deste estudo foi identificar doenças através de um classificador com aprendizagem supervisionada, buscando a alta acurácia do mesmo, de forma que ele fosse capaz de classificar doenças com base nos sintomas apresentados pelos pacientes. Buscando esse fim, foram utilizadas informações epidemiológicas de algumas doenças bem conhecidas e foi criado um banco de dados com pacientes, seus respectivos sintomas e as doenças que lhes foram atribuídas no diagnóstico. Posteriormente, foi aplicado um modelo de aprendizado de máquina supervisionado SVM (support-vector machine) nesse banco de pacientes com a finalidade de classificar, com alta acurácia, as doenças com base nos sintomas apresentados.
The aim of this study was to identify diseases through a classifier with supervised learning, seeking its high accuracy, so it would be able to classify diseases based on the symptoms of the patients. For this purpose, epidemiological information of some well-known diseases was used, and a database with patients was created, including their respective symptoms and the diseases that were assigned to them in the diagnosis. Subsequently, a SVM supervised machine learning model (support-vector machine) was applied to the patient database in order to classify, with high accuracy, the diseases based on the presented symptoms found in the patients database.
The aim of this study was to identify diseases through a classifier with supervised learning, seeking its high accuracy, so it would be able to classify diseases based on the symptoms of the patients. For this purpose, epidemiological information of some well-known diseases was used, and a database with patients was created, including their respective symptoms and the diseases that were assigned to them in the diagnosis. Subsequently, a SVM supervised machine learning model (support-vector machine) was applied to the patient database in order to classify, with high accuracy, the diseases based on the presented symptoms found in the patients database.
Descrição
Palavras-chave
SVM , aprendizado de máquina , epidemiologia , aprendizado supervisionado , SVM , machine learning , epidemiology , supervised learning