2017年
MedEx/J: A one-scan simple and fast NLP tool for Japanese clinical texts
Studies in Health Technology and Informatics
- ,
- ,
- 巻
- 245
- 号
- 開始ページ
- 285
- 終了ページ
- 288
- 記述言語
- 英語
- 掲載種別
- 研究論文(国際会議プロシーディングス)
- DOI
- 10.3233/978-1-61499-830-3-285
- 出版者・発行元
- IOS Press
Because of recent replacement of physical documents with electronic medical records (EMR), the importance of information processing in the medical field has increased. In light of this trend, we have been developing MedEx/J, which retrieves important Japanese language information from medical reports. MedEx/J executes two tasks simultaneously: (1) term extraction, and (2) positive and negative event classification. We designate this approach as a one-scan approach, providing simplicity of systems and reasonable accuracy. MedEx/J performance on the two tasks is described herein:(1) term extraction (F β-1 = 0.87) and (2) positive-negative classification (F β-1 = 0.63). This paper also presents discussion and explains remaining issues in the medical natural language processing field.
- リンク情報
-
- DOI
- https://doi.org/10.3233/978-1-61499-830-3-285
- DBLP
- https://dblp.uni-trier.de/rec/conf/medinfo/AramakiYW17
- PubMed
- https://www.ncbi.nlm.nih.gov/pubmed/29295100
- URL
- http://dblp.uni-trier.de/db/conf/medinfo/medinfo2017.html#conf/medinfo/AramakiYW17
- Scopus
- https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85040523516&origin=inward
- Scopus Citedby
- https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85040523516&origin=inward
- ID情報
-
- DOI : 10.3233/978-1-61499-830-3-285
- ISSN : 1879-8365
- ISSN : 0926-9630
- eISSN : 1879-8365
- DBLP ID : conf/medinfo/AramakiYW17
- PubMed ID : 29295100
- SCOPUS ID : 85040523516