Medical Knowledge Resources for Text-Mining of Health Records in Czech, Polish, and Slovak

Investor logo

Warning

This publication doesn't include Faculty of Arts. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

ANETTA Krištof

Year of publication 2022
Type Article in Proceedings
Conference Proceedings of the Sixteenth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2022
MU Faculty or unit

Faculty of Informatics

Citation
Web
Keywords EHR; electronic health records; healthcare text; UMLS; ICD10; SNOMED CT; MedDRA; MeSH; NLP; natural language processing; Slavic languages; Polish; Czech; Slovak
Description Knowledge extraction from medical text in small languages like Czech, Polish or Slovak is challenging due to the insufficiency of languagespecific medical resources (pretrained models, ontologies, dictionaries). This paper is a survey of noteworthy options for researchers targeting these languages, divided into two sections. First, since the UMLS Metathesaurus for English is by far the most extensive and detailed medical knowledge resource in Western medicine, appreciable results can be achieved by machine-translating the mined text to English – therefore, the relevant English components of UMLS are introduced. Second come the languagespecific resources for each language, detailing the publishing institutions, current website locations, contents, and file formats. The contribution of this paper is in collecting and pre-screening widely disparate sources needed for successful medical knowledge extraction in Central European Slavic languages.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.