Construction of an Attribute-Value Representation for Semi-structured Medical Findings Knowledge Extraction

Data Mining is a process related to analysis, understanding and knowledge extraction from databases. In order to perform this process it is usually necessary to represent the data in the so called attribute-value format. This work proposes an extension of a methodology which supports, through a semi-automatic process, the construction of a table in the attribute-value format from information contained in medical findings which are described in natural language (Portuguese). A case study in which the methodology has been applied to a collection of Upper Digestive Endoscopies’ medical findings is presented. Results show the suitability of our proposal.