Medical domain document classification via extraction of taxonomy concepts from MeSH ontology

Abstract

This paper is a result of a task that was presented to attendants of Keyword Search in Big Linked Data summer school, that was organized by Vienna University of Technology, under the Keystone COST action in the summer of 2017. It presents a specific approach to the classification via creation of minimal document surrogates based on the US National medical library’s MeSH ontology, which is derived from the Medical Subject Headings thesaurus. In a series of previously classified medically related text, which are the bases for the task, all of the significant terms are located and replaced with taxonomical references from the MeSH ontology. Extracted references are used for the classification within the ontology using a rather simple algorithm and the results are evaluated in compresence to previous manual classification of the same documents.