rss
J Am Med Inform Assoc doi:10.1136/amiajnl-2011-000150
  • Research and applications

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

  1. Xiaodan Zhu
  1. Institute for Information Technology, National Research Council, Ottawa, Ontario, Canada
  1. Correspondence to Dr Berry de Bruijn, Institute for Information Technology, National Research Council, Canada, 1200 Montreal Road, Building M50, Ottawa, ON, K1A OR6, Canada; berry.debruijn{at}nrc-cnrc.gc.ca
  • Received 11 January 2011
  • Accepted 13 April 2011
  • Published Online First 12 May 2011

Abstract

Objective As clinical text mining continues to mature, its potential as an enabling technology for innovations in patient care and clinical research is becoming a reality. A critical part of that process is rigid benchmark testing of natural language processing methods on realistic clinical narrative. In this paper, the authors describe the design and performance of three state-of-the-art text-mining applications from the National Research Council of Canada on evaluations within the 2010 i2b2 challenge.

Design The three systems perform three key steps in clinical information extraction: (1) extraction of medical problems, tests, and treatments, from discharge summaries and progress notes; (2) classification of assertions made on the medical problems; (3) classification of relations between medical concepts. Machine learning systems performed these tasks using large-dimensional bags of features, as derived from both the text itself and from external sources: UMLS, cTAKES, and Medline.

Measurements Performance was measured per subtask, using micro-averaged F-scores, as calculated by comparing system annotations with ground-truth annotations on a test set.

Results The systems ranked high among all submitted systems in the competition, with the following F-scores: concept extraction 0.8523 (ranked first); assertion detection 0.9362 (ranked first); relationship detection 0.7313 (ranked second).

Conclusion For all tasks, we found that the introduction of a wide range of features was crucial to success. Importantly, our choice of machine learning algorithms allowed us to be versatile in our feature design, and to introduce a large number of features without overfitting and without encountering computing-resource bottlenecks.

Footnotes

  • Funding The 2010 i2b2/VA challenge and the workshop were funded in part by the grant number U54-LM008748 on Informatics for Integrating Biology to the Bedside from National Library of Medicine, and facilities of the VA Salt Lake City Health Care System with funding support from the Consortium for Healthcare Informatics Research (CHIR), VA HSR HIR 08-374, and the VA Informatics and Computing Infrastructure (VINCI), VA HSR HIR 08-204. MedQuist co-sponsored the 2010 i2b2/VA challenge meeting at AMIA.

  • Competing interests None.

  • Provenance and peer review Not commissioned; externally peer reviewed

Related Article

Free Sample

This recent issue is free to all users to allow everyone the opportunity to see the full scope and typical content of JAMIA.
View free sample issue >>

Access policy for JAMIA

All content published in JAMIA is deposited with PubMed Central by the publisher with a 12 month embargo. Authors/funders may pay an Open Access fee of $2,000 to make the article free on the JAMIA website and PMC immediately on publication.

All content older than 12 months is freely available on this website.

AMIA members can log in with their JAMIA user name (email address) and password or via the AMIA website.

Navigate This Article