Format

Send to

Choose Destination
See comment in PubMed Commons below
J Am Med Inform Assoc. 2017 Apr 17. doi: 10.1093/jamia/ocx039. [Epub ahead of print]

Challenges in adapting existing clinical natural language processing systems to multiple, diverse health care settings.

Author information

1
Kaiser Permanente of Washington Health Research Institute (formerly Group Health Research Institute), Seattle, WA, USA.
2
Division of Gastroenterology, Hepatology, and Nutrition, Department of Medicine and Epidemiology, University of Pittsburgh, Pittsburgh, PA, USA.
3
Division of Gastroenterology, Beth Israel Deaconess Medical Center, Boston, MA, USA.
4
Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA, USA.
5
Department of Health Care Policy, Harvard Medical School, Boston, MA, USA.
6
Division of Gastroenterology and Hepatology, University of North Carolina School of Medicine, Chapel Hill, NC, USA.
7
Division of General Internal Medicine, Beth Israel Deaconess Medical Center, Boston, MA, USA.

Abstract

Objective:

Widespread application of clinical natural language processing (NLP) systems requires taking existing NLP systems and adapting them to diverse and heterogeneous settings. We describe the challenges faced and lessons learned in adapting an existing NLP system for measuring colonoscopy quality.

Materials and Methods:

Colonoscopy and pathology reports from 4 settings during 2013-2015, varying by geographic location, practice type, compensation structure, and electronic health record.

Results:

Though successful, adaptation required considerably more time and effort than anticipated. Typical NLP challenges in assembling corpora, diverse report structures, and idiosyncratic linguistic content were greatly magnified.

Discussion:

Strategies for addressing adaptation challenges include assessing site-specific diversity, setting realistic timelines, leveraging local electronic health record expertise, and undertaking extensive iterative development. More research is needed on how to make it easier to adapt NLP systems to new clinical settings.

Conclusions:

A key challenge in widespread application of NLP is adapting existing systems to new clinical settings.

KEYWORDS:

cancer screening; data collection; electronic health records; information dissemination; natural language processing

PMID:
28419261
DOI:
10.1093/jamia/ocx039
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for Silverchair Information Systems
    Loading ...
    Support Center