UM MODELO PARA EXTRAÇÃO, ESTRUTURAÇÃO, INDEXAÇÃO E RECUPERAÇÃO DE CASOS CLÍNICOS PUBLICADOS NA WEB

Currently the range of medical content available on the Web is very wide, mainly clinical cases that serve as the basis for studies and analyzes, however many of these data are without structures and originate from heterogeneous sources, making it difficult to search indexing and data analysis. Thus, this work proposes a metadata model to standardize such contents and serves as a basis for the use of conventional text mining techniques and PLN for their settlement, for future searches, recoveries and maintenance with higher quality.