Your browser doesn't support javascript.
loading
Named Entity Recognition in Prehospital Trauma Care.
Silverman, Greg M; Lindemann, Elizabeth A; Rajamani, Geetanjali; Finzel, Raymond L; McEwan, Reed; Knoll, Benjamin C; Pakhomov, Serguei; Melton, Genevieve B; Tignanelli, Christopher J.
Afiliação
  • Silverman GM; Academic Health Center - Information Systems, University of Minnesota, Minneapolis, Minnesota, USA.
  • Lindemann EA; Institute for Health Informatics, University of Minnesota, Minneapolis, Minnesota, USA.
  • Rajamani G; Department of Surgery, University of Minnesota, Minneapolis, Minnesota, USA.
  • Finzel RL; Stanford University, Stanford, CA, USA.
  • McEwan R; College of Pharmacy, University of Minnesota, Minneapolis, Minnesota, USA.
  • Knoll BC; Academic Health Center - Information Systems, University of Minnesota, Minneapolis, Minnesota, USA.
  • Pakhomov S; Institute for Health Informatics, University of Minnesota, Minneapolis, Minnesota, USA.
  • Melton GB; College of Pharmacy, University of Minnesota, Minneapolis, Minnesota, USA.
  • Tignanelli CJ; Institute for Health Informatics, University of Minnesota, Minneapolis, Minnesota, USA.
Stud Health Technol Inform ; 264: 1586-1587, 2019 Aug 21.
Article em En | MEDLINE | ID: mdl-31438244
ABSTRACT
Natural language processing (NLP) methods would improve outcomes in the area of prehospital Emergency Medical Services (EMS) data collection and abstraction. This study evaluated off-the-shelf solutions for automating labelling of clinically relevant data from EMS reports. A qualitative approach for choosing the best possible ensemble of pretrained NLP systems was developed and validated along with a feature using word embeddings to test phrase synonymy. The ensemble showed increased performance over individual systems.
Assuntos
Palavras-chave
Texto completo
Imprimir
XML
PubMed Links
Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Serviços Médicos de Emergência Tipo de estudo: Qualitative_research Idioma: En Ano de publicação: 2019 Tipo de documento: Article
Texto completo
Imprimir
XML
PubMed Links
Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Serviços Médicos de Emergência Tipo de estudo: Qualitative_research Idioma: En Ano de publicação: 2019 Tipo de documento: Article