Automating concept identification in the electronic medical record: an experiment in extracting dosage information.

D. A. Evans; N. D. Brownlow; W. R. Hersh; E. M. Campbell

Automating concept identification in the electronic medical record: an experiment in extracting dosage information.

D. A. Evans, N. D. Brownlow, W. R. Hersh, E. M. Campbell

Research output: Contribution to journal › Article › peer-review

Abstract

We discuss the development and evaluation of an automated procedure for extracting drug-dosage information from clinical narratives. The process was developed rapidly using existing technology and resources, including categories of terms from UMLS96. Evaluations over a large training and smaller test set of medical records demonstrate an approximately 80% rate of exact and partial matches' on target phrases, with few false positives and a modest rate of false negatives. The results suggest a strategy for automating general concept identification in electronic medical records.

Original language	English (US)
Pages (from-to)	388-392
Number of pages	5
Journal	Proceedings : a conference of the American Medical Informatics Association / ... AMIA Annual Fall Symposium. AMIA Fall Symposium
State	Published - 1996
Externally published	Yes

ASJC Scopus subject areas

General Medicine

Cite this

Automating concept identification in the electronic medical record: an experiment in extracting dosage information. / Evans, D. A.; Brownlow, N. D.; Hersh, W. R. et al.
In: Proceedings : a conference of the American Medical Informatics Association / ... AMIA Annual Fall Symposium. AMIA Fall Symposium, 1996, p. 388-392.

Research output: Contribution to journal › Article › peer-review

@article{990b519705e04293bbafd65e0fbc7efe,

title = "Automating concept identification in the electronic medical record: an experiment in extracting dosage information.",

abstract = "We discuss the development and evaluation of an automated procedure for extracting drug-dosage information from clinical narratives. The process was developed rapidly using existing technology and resources, including categories of terms from UMLS96. Evaluations over a large training and smaller test set of medical records demonstrate an approximately 80% rate of exact and partial matches' on target phrases, with few false positives and a modest rate of false negatives. The results suggest a strategy for automating general concept identification in electronic medical records.",

author = "Evans, {D. A.} and Brownlow, {N. D.} and Hersh, {W. R.} and Campbell, {E. M.}",

note = "Copyright: This record is sourced from MEDLINE{\textregistered}/PubMed{\textregistered}, a database of the U.S. National Library of Medicine",

year = "1996",

language = "English (US)",

pages = "388--392",

journal = "Proceedings : a conference of the American Medical Informatics Association / ... AMIA Annual Fall Symposium. AMIA Fall Symposium",

issn = "1091-8280",

publisher = "Hanley and Belfus Inc.",

}

TY - JOUR

T1 - Automating concept identification in the electronic medical record

T2 - an experiment in extracting dosage information.

AU - Evans, D. A.

AU - Brownlow, N. D.

AU - Hersh, W. R.

AU - Campbell, E. M.

N1 - Copyright: This record is sourced from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

PY - 1996

Y1 - 1996

N2 - We discuss the development and evaluation of an automated procedure for extracting drug-dosage information from clinical narratives. The process was developed rapidly using existing technology and resources, including categories of terms from UMLS96. Evaluations over a large training and smaller test set of medical records demonstrate an approximately 80% rate of exact and partial matches' on target phrases, with few false positives and a modest rate of false negatives. The results suggest a strategy for automating general concept identification in electronic medical records.

AB - We discuss the development and evaluation of an automated procedure for extracting drug-dosage information from clinical narratives. The process was developed rapidly using existing technology and resources, including categories of terms from UMLS96. Evaluations over a large training and smaller test set of medical records demonstrate an approximately 80% rate of exact and partial matches' on target phrases, with few false positives and a modest rate of false negatives. The results suggest a strategy for automating general concept identification in electronic medical records.

UR - http://www.scopus.com/inward/record.url?scp=0030346928&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030346928&partnerID=8YFLogxK

M3 - Article

C2 - 8947694

AN - SCOPUS:0030346928

SN - 1091-8280

SP - 388

EP - 392

JO - Proceedings : a conference of the American Medical Informatics Association / ... AMIA Annual Fall Symposium. AMIA Fall Symposium

JF - Proceedings : a conference of the American Medical Informatics Association / ... AMIA Annual Fall Symposium. AMIA Fall Symposium

ER -

Automating concept identification in the electronic medical record: an experiment in extracting dosage information.

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this