Staggered NLP-assisted refinement for clinical annotations of chronic disease events

Stephen T. Wu, Chung Il Wi, Sunghwan Sohn, Hongfang D Liu, Young J Juhn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Domain-specific annotations for NLP are often centered on real-world applications of text, and incorrect annotations may be particularly unacceptable. In medical text, the process of manual chart review (of a patient's medical record) is error-prone due to its complexity. We propose a staggered NLP-assisted approach to the refinement of clinical annotations, an interactive process that allows initial human judgments to be verified or falsified by means of comparison with an improving NLP system. We show on our internal Asthma Timelines dataset that this approach improves the quality of the human-produced clinical annotations.

Original languageEnglish (US)
Title of host publicationProceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016
PublisherEuropean Language Resources Association (ELRA)
Pages426-429
Number of pages4
ISBN (Electronic)9782951740891
StatePublished - Jan 1 2016
Event10th International Conference on Language Resources and Evaluation, LREC 2016 - Portoroz, Slovenia
Duration: May 23 2016May 28 2016

Other

Other10th International Conference on Language Resources and Evaluation, LREC 2016
CountrySlovenia
CityPortoroz
Period5/23/165/28/16

Fingerprint

Disease
event
Natural Language Processing
Annotation
Chronic Disease
Asthma
Charts
Real World
Timeline
Medical Texts

Keywords

  • Annotation refinement
  • Clinical text
  • Rule-based NLP
  • Staggered approaches

ASJC Scopus subject areas

  • Linguistics and Language
  • Library and Information Sciences
  • Language and Linguistics
  • Education

Cite this

Wu, S. T., Wi, C. I., Sohn, S., Liu, H. D., & Juhn, Y. J. (2016). Staggered NLP-assisted refinement for clinical annotations of chronic disease events. In Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016 (pp. 426-429). European Language Resources Association (ELRA).

Staggered NLP-assisted refinement for clinical annotations of chronic disease events. / Wu, Stephen T.; Wi, Chung Il; Sohn, Sunghwan; Liu, Hongfang D; Juhn, Young J.

Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016. European Language Resources Association (ELRA), 2016. p. 426-429.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wu, ST, Wi, CI, Sohn, S, Liu, HD & Juhn, YJ 2016, Staggered NLP-assisted refinement for clinical annotations of chronic disease events. in Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016. European Language Resources Association (ELRA), pp. 426-429, 10th International Conference on Language Resources and Evaluation, LREC 2016, Portoroz, Slovenia, 5/23/16.
Wu ST, Wi CI, Sohn S, Liu HD, Juhn YJ. Staggered NLP-assisted refinement for clinical annotations of chronic disease events. In Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016. European Language Resources Association (ELRA). 2016. p. 426-429
Wu, Stephen T. ; Wi, Chung Il ; Sohn, Sunghwan ; Liu, Hongfang D ; Juhn, Young J. / Staggered NLP-assisted refinement for clinical annotations of chronic disease events. Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016. European Language Resources Association (ELRA), 2016. pp. 426-429
@inproceedings{1cf10b3d25da492eb9c3cb73a154e595,
title = "Staggered NLP-assisted refinement for clinical annotations of chronic disease events",
abstract = "Domain-specific annotations for NLP are often centered on real-world applications of text, and incorrect annotations may be particularly unacceptable. In medical text, the process of manual chart review (of a patient's medical record) is error-prone due to its complexity. We propose a staggered NLP-assisted approach to the refinement of clinical annotations, an interactive process that allows initial human judgments to be verified or falsified by means of comparison with an improving NLP system. We show on our internal Asthma Timelines dataset that this approach improves the quality of the human-produced clinical annotations.",
keywords = "Annotation refinement, Clinical text, Rule-based NLP, Staggered approaches",
author = "Wu, {Stephen T.} and Wi, {Chung Il} and Sunghwan Sohn and Liu, {Hongfang D} and Juhn, {Young J}",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
pages = "426--429",
booktitle = "Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016",
publisher = "European Language Resources Association (ELRA)",

}

TY - GEN

T1 - Staggered NLP-assisted refinement for clinical annotations of chronic disease events

AU - Wu, Stephen T.

AU - Wi, Chung Il

AU - Sohn, Sunghwan

AU - Liu, Hongfang D

AU - Juhn, Young J

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Domain-specific annotations for NLP are often centered on real-world applications of text, and incorrect annotations may be particularly unacceptable. In medical text, the process of manual chart review (of a patient's medical record) is error-prone due to its complexity. We propose a staggered NLP-assisted approach to the refinement of clinical annotations, an interactive process that allows initial human judgments to be verified or falsified by means of comparison with an improving NLP system. We show on our internal Asthma Timelines dataset that this approach improves the quality of the human-produced clinical annotations.

AB - Domain-specific annotations for NLP are often centered on real-world applications of text, and incorrect annotations may be particularly unacceptable. In medical text, the process of manual chart review (of a patient's medical record) is error-prone due to its complexity. We propose a staggered NLP-assisted approach to the refinement of clinical annotations, an interactive process that allows initial human judgments to be verified or falsified by means of comparison with an improving NLP system. We show on our internal Asthma Timelines dataset that this approach improves the quality of the human-produced clinical annotations.

KW - Annotation refinement

KW - Clinical text

KW - Rule-based NLP

KW - Staggered approaches

UR - http://www.scopus.com/inward/record.url?scp=85037103977&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037103977&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85037103977

SP - 426

EP - 429

BT - Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016

PB - European Language Resources Association (ELRA)

ER -