Concept attribute labeling and context-aware named entity recognition in electronic health records

Pomares Quimbaya, Alexandra; González, Rafael A.; Muñoz, Óscar; Garcia-Pena, A.A.; Daza Rodríguez, Julián Camilo; Sierra Múnera, Alejandro; Labbé, Cyril

Mostrar el registro sencillo del registro

dc.rights.licence	Atribución-NoComercial 4.0 Internacional	*
dc.contributor.author	Pomares Quimbaya, Alexandra
dc.contributor.author	González, Rafael A.
dc.contributor.author	Muñoz, Óscar
dc.contributor.author	Garcia-Pena, A.A.
dc.contributor.author	Daza Rodríguez, Julián Camilo
dc.contributor.author	Sierra Múnera, Alejandro
dc.contributor.author	Labbé, Cyril
dc.date.accessioned	2020-05-21T19:23:24Z
dc.date.available	2020-05-21T19:23:24Z
dc.date.created	2018-03
dc.identifier	https://www.igi-global.com/gateway/article/190642	spa
dc.identifier.issn	2160-9551 / 2160-956X (Electrónico)	spa
dc.identifier.uri	http://hdl.handle.net/10554/49379
dc.format	PDF	spa
dc.format.mimetype	application/pdf	spa
dc.language	spa	spa
dc.rights.uri	http://creativecommons.org/licenses/by-nc/4.0/	*
dc.source	International Journal of Reliable and Quality E-Healthcare: Vol. 7 Núm. 1 (2018)	spa
dc.title	Concept attribute labeling and context-aware named entity recognition in electronic health records	spa
dc.type	info:eu-repo/semantics/article
dc.type.hasversion	http://purl.org/coar/version/c_ab4af688f83e57aa
dc.identifier.doi	https://doi.org/10.4018/IJRQEH.2018010101	spa
dc.description.tipoarticulo	Artículo original	spa
dc.description.paginas	1-5	spa
dc.format.soporte	Papel / Electrónico	spa
dc.subject.keyword	Concept Attribute Labeling	spa
dc.subject.keyword	Electronic Health Records	spa
dc.subject.keyword	Named Entity Recognition	spa
dc.subject.keyword	Text Mining	spa
dc.description.abstractenglish	Extracting valuable knowledge from Electronic Health Records (EHR) represents a challenging task due to the presence of both structured and unstructured data, including codified fields, images and test results. Narrative text in particular contains a variety of notes which are diverse in language and detail, as well as being full of ad hoc terminology, including acronyms and jargon, which is especially challenging in non-English EHR, where there is a dearth of annotated corpora or trained case sets. This paper proposes an approach for NER and concept attribute labeling for EHR that takes into consideration the contextual words around the entity of interest to determine its sense. The approach proposes a composition method of three different NER methods, together with the analysis of the context (neighboring words) using an ensemble classification model. This contributes to disambiguate NER, as well as labeling the concept as confirmed, negated, speculative, pending or antecedent. Results show an improvement of the recall and a limited impact on precision for the NER process.	spa
dc.type.local	Artículo de revista	spa
dc.contributor.corporatename	Pontificia Universidad Javeriana. Facultad de Medicina. Instituto de Envejecimiento
dc.contributor.corporatename	Pontificia Universidad Javeriana. Facultad de Medicina. Departamento de Medicina Interna. Grupo de Investigación de Enfermedades Crónicas del Adulto
dc.contributor.corporatename	Pontificia Universidad Javeriana. Facultad de Medicina. Departamento de Medicina Interna. Cardiología
dc.contributor.corporatename	Pontificia Universidad Javeriana. Facultad de Medicina. Departamento de Medicina Interna. Medicina Interna
dc.description.orcid	https://orcid.org/0000-0002-3606-2102
dc.description.orcid	https://orcid.org/0000-0001-5401-0018
dc.contributor.javerianateacher	Garcia-Pena, A.A.
dc.contributor.javerianateacher	Muñoz, Óscar