Clinical concept extraction using transformers.

Objective: The goal of this study is to explore transformer-based models (eg, Bidirectional Encoder Representations from Transformers [BERT]) for clinical concept extraction and develop an open-source package with pretrained clinical models to facilitate concept extraction and other downstream natur...

Full description

Bibliographic Details
Published in:Journal of the American Medical Informatics Association Vol. 27; no. 12; pp. 1935 - 1943
Main Authors: Yang, Xi, Bian, Jiang, Hogan, William R, Wu, Yonghui
Format: research Journal Article
Published: Oxford University Press / USA Dec2020
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=147573390&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 147573390
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        10675027
        FZ9
      jtl: Journal of the American Medical Informatics Association
      issn: 10675027
      maglogo: N
    pubinfo:
      dt: Dec2020
      vid: 27
      iid: 12
      pid: 622
      pub: Oxford University Press / USA
    artinfo:
      ui:
        147573390
        147573390
        NLM33120431
        147573390
        10.1093/jamia/ocaa189
        NLM33120431
        147573390
      ppf: 1935
      ppct: 8
      formats:
      tig:
        atl: Clinical concept extraction using transformers.
      aug:
        au:
          Yang, Xi
          Bian, Jiang
          Hogan, William R
          Wu, Yonghui
        affil: Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida , Gainesville, Florida, USA
      sug:
        subj:
          Data Mining Methods
          Software
          Natural Language Processing
          Human
          Data Collection
          Comparative Studies
          Multicenter Studies
          Evaluation Research
          Validation Studies
          Short Portable Mental Status Questionnaire
          Scales
          Questionnaires
      ab: Objective: The goal of this study is to explore transformer-based models (eg, Bidirectional Encoder Representations from Transformers [BERT]) for clinical concept extraction and develop an open-source package with pretrained clinical models to facilitate concept extraction and other downstream natural language processing (NLP) tasks in the medical domain.Methods: We systematically explored 4 widely used transformer-based architectures, including BERT, RoBERTa, ALBERT, and ELECTRA, for extracting various types of clinical concepts using 3 public datasets from the 2010 and 2012 i2b2 challenges and the 2018 n2c2 challenge. We examined general transformer models pretrained using general English corpora as well as clinical transformer models pretrained using a clinical corpus and compared them with a long short-term memory conditional random fields (LSTM-CRFs) mode as a baseline. Furthermore, we integrated the 4 clinical transformer-based models into an open-source package.Results and Conclusion: The RoBERTa-MIMIC model achieved state-of-the-art performance on 3 public clinical concept extraction datasets with F1-scores of 0.8994, 0.8053, and 0.8907, respectively. Compared to the baseline LSTM-CRFs model, RoBERTa-MIMIC remarkably improved the F1-score by approximately 4% and 6% on the 2010 and 2012 i2b2 datasets. This study demonstrated the efficiency of transformer-based models for clinical concept extraction. Our methods and systems can be applied to other clinical tasks. The clinical transformer package with 4 pretrained clinical models is publicly available at https://github.com/uf-hobi-informatics-lab/ClinicalTransformerNER. We believe this package will improve current practice on clinical concept extraction and other tasks in the medical domain.
      pubtype: Academic Journal
      doctype:
        research
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N