Literature DB >> 33029619

The impact of learning Unified Medical Language System knowledge embeddings in relation extraction from biomedical texts.

Maxwell A Weinzierl1, Ramon Maldonado1, Sanda M Harabagiu1.   

Abstract

OBJECTIVE: We explored how knowledge embeddings (KEs) learned from the Unified Medical Language System (UMLS) Metathesaurus impact the quality of relation extraction on 2 diverse sets of biomedical texts.
MATERIALS AND METHODS: Two forms of KEs were learned for concepts and relation types from the UMLS Metathesaurus, namely lexicalized knowledge embeddings (LKEs) and unlexicalized KEs. A knowledge embedding encoder (KEE) enabled learning either LKEs or unlexicalized KEs as well as neural models capable of producing LKEs for mentions of biomedical concepts in texts and relation types that are not encoded in the UMLS Metathesaurus. This allowed us to design the relation extraction with knowledge embeddings (REKE) system, which incorporates either LKEs or unlexicalized KEs produced for relation types of interest and their arguments.
RESULTS: The incorporation of either LKEs or unlexicalized KE in REKE advances the state of the art in relation extraction on 2 relation extraction datasets: the 2010 i2b2/VA dataset and the 2013 Drug-Drug Interaction Extraction Challenge corpus. Moreover, the impact of LKEs is superior, achieving F1 scores of 78.2 and 82.0, respectively. DISCUSSION: REKE not only highlights the importance of incorporating knowledge encoded in the UMLS Metathesaurus in a novel way, through 2 possible forms of KEs, but it also showcases the subtleties of incorporating KEs in relation extraction systems.
CONCLUSIONS: Incorporating LKEs informed by the UMLS Metathesaurus in a relation extraction system operating on biomedical texts shows significant promise. We present the REKE system, which establishes new state-of-the-art results for relation extraction on 2 datasets when using LKEs.
© The Author(s) 2020. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  deep learning; information extraction; medical informatics; unified medical language system

Mesh:

Year:  2020        PMID: 33029619      PMCID: PMC7647370          DOI: 10.1093/jamia/ocaa205

Source DB:  PubMed          Journal:  J Am Med Inform Assoc        ISSN: 1067-5027            Impact factor:   4.497


  13 in total

1.  Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program.

Authors:  A R Aronson
Journal:  Proc AMIA Symp       Date:  2001

2.  The Unified Medical Language System (UMLS): integrating biomedical terminology.

Authors:  Olivier Bodenreider
Journal:  Nucleic Acids Res       Date:  2004-01-01       Impact factor: 16.971

3.  Bridging semantics and syntax with graph algorithms-state-of-the-art of extracting biomedical relations.

Authors:  Yuan Luo; Özlem Uzuner; Peter Szolovits
Journal:  Brief Bioinform       Date:  2016-02-05       Impact factor: 11.622

4.  MedEx: a medication information extraction system for clinical narratives.

Authors:  Hua Xu; Shane P Stenner; Son Doan; Kevin B Johnson; Lemuel R Waitman; Joshua C Denny
Journal:  J Am Med Inform Assoc       Date:  2010 Jan-Feb       Impact factor: 4.497

5.  2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text.

Authors:  Özlem Uzuner; Brett R South; Shuying Shen; Scott L DuVall
Journal:  J Am Med Inform Assoc       Date:  2011-06-16       Impact factor: 4.497

6.  Automatic extraction of relations between medical concepts in clinical texts.

Authors:  Bryan Rink; Sanda Harabagiu; Kirk Roberts
Journal:  J Am Med Inform Assoc       Date:  2011 Sep-Oct       Impact factor: 4.497

7.  Classifying medical relations in clinical text via convolutional neural networks.

Authors:  Bin He; Yi Guan; Rui Dai
Journal:  Artif Intell Med       Date:  2018-05-18       Impact factor: 5.326

8.  Segment convolutional neural networks (Seg-CNNs) for classifying relations in clinical notes.

Authors:  Yuan Luo; Yu Cheng; Özlem Uzuner; Peter Szolovits; Justin Starren
Journal:  J Am Med Inform Assoc       Date:  2018-01-01       Impact factor: 4.497

9.  Machine-learned solutions for three stages of clinical information extraction: the state of the art at i2b2 2010.

Authors:  Berry de Bruijn; Colin Cherry; Svetlana Kiritchenko; Joel Martin; Xiaodan Zhu
Journal:  J Am Med Inform Assoc       Date:  2011-05-12       Impact factor: 4.497

10.  Drug-drug interaction extraction via hierarchical RNNs on sequence and shortest dependency paths.

Authors:  Yijia Zhang; Wei Zheng; Hongfei Lin; Jian Wang; Zhihao Yang; Michel Dumontier
Journal:  Bioinformatics       Date:  2018-03-01       Impact factor: 6.937

View more
  2 in total

1.  The UMLS knowledge sources at 30: indispensable to current research and applications in biomedical informatics.

Authors:  Betsy L Humphreys; Guilherme Del Fiol; Hua Xu
Journal:  J Am Med Inform Assoc       Date:  2020-10-01       Impact factor: 4.497

2.  Discovering microbe-disease associations from the literature using a hierarchical long short-term memory network and an ensemble parser model.

Authors:  Yesol Park; Joohong Lee; Heesang Moon; Yong Suk Choi; Mina Rho
Journal:  Sci Rep       Date:  2021-02-24       Impact factor: 4.379

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.