Querying the national drug file reference terminology (NDFRT) to assign drugs to decision support categories

Linas Simonaitis, Gunther Schadow

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

1 Citation (Scopus)

Abstract

Introduction: The accurate categorization of drugs is a prerequisite for decision support rules. The manual process of creating drug classes can be laborious and error-prone. Methods: All 142 drug classes currently used at Regenstrief Institute for drug interaction alerts were extracted. These drug classes were replicated as fully-defined concepts in our local instance of the NDFRT knowledge base. The performance of these two strategies (manual classification vs. NDFRT-based queries) was compared, and the sensitivity and specificity of each was calculated. Results: Compared to existing manual classifications, NDFRT-based queries made a greater number of correct class-drug assignments: 1528 vs. 1266. NDFRT queries have greater sensitivity (74.9% vs. 62.1%) to classify drugs. However, they have less specificity (85.6% vs. 99.8%). Conclusion: The NDFRT knowledge base shows promise for use in an automated strategy to improve the creation and update of drug classes. The chief disadvantage of our NDFRT-based approach was a greater number of false positive assignments due to the inclusion of non-systemic doseforms.

Original languageEnglish
Title of host publicationStudies in Health Technology and Informatics
Pages1095-1099
Number of pages5
Volume160
EditionPART 1
DOIs
StatePublished - 2010
Event13th World Congress on Medical and Health Informatics, Medinfo 2010 - Cape Town, South Africa
Duration: Sep 12 2010Sep 15 2010

Other

Other13th World Congress on Medical and Health Informatics, Medinfo 2010
CountrySouth Africa
CityCape Town
Period9/12/109/15/10

Fingerprint

Terminology
Pharmaceutical Preparations
Drug interactions
Knowledge Bases
Drug Interactions

Keywords

  • Computer-assisted drug therapy
  • Drug classification
  • Knowledge bases
  • National Drug File Reference Terminology

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Simonaitis, L., & Schadow, G. (2010). Querying the national drug file reference terminology (NDFRT) to assign drugs to decision support categories. In Studies in Health Technology and Informatics (PART 1 ed., Vol. 160, pp. 1095-1099) https://doi.org/10.3233/978-1-60750-588-4-1095

Querying the national drug file reference terminology (NDFRT) to assign drugs to decision support categories. / Simonaitis, Linas; Schadow, Gunther.

Studies in Health Technology and Informatics. Vol. 160 PART 1. ed. 2010. p. 1095-1099.

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

Simonaitis, L & Schadow, G 2010, Querying the national drug file reference terminology (NDFRT) to assign drugs to decision support categories. in Studies in Health Technology and Informatics. PART 1 edn, vol. 160, pp. 1095-1099, 13th World Congress on Medical and Health Informatics, Medinfo 2010, Cape Town, South Africa, 9/12/10. https://doi.org/10.3233/978-1-60750-588-4-1095
Simonaitis, Linas ; Schadow, Gunther. / Querying the national drug file reference terminology (NDFRT) to assign drugs to decision support categories. Studies in Health Technology and Informatics. Vol. 160 PART 1. ed. 2010. pp. 1095-1099
@inproceedings{6da757fe424746f49f0b8caa62645237,
title = "Querying the national drug file reference terminology (NDFRT) to assign drugs to decision support categories",
abstract = "Introduction: The accurate categorization of drugs is a prerequisite for decision support rules. The manual process of creating drug classes can be laborious and error-prone. Methods: All 142 drug classes currently used at Regenstrief Institute for drug interaction alerts were extracted. These drug classes were replicated as fully-defined concepts in our local instance of the NDFRT knowledge base. The performance of these two strategies (manual classification vs. NDFRT-based queries) was compared, and the sensitivity and specificity of each was calculated. Results: Compared to existing manual classifications, NDFRT-based queries made a greater number of correct class-drug assignments: 1528 vs. 1266. NDFRT queries have greater sensitivity (74.9{\%} vs. 62.1{\%}) to classify drugs. However, they have less specificity (85.6{\%} vs. 99.8{\%}). Conclusion: The NDFRT knowledge base shows promise for use in an automated strategy to improve the creation and update of drug classes. The chief disadvantage of our NDFRT-based approach was a greater number of false positive assignments due to the inclusion of non-systemic doseforms.",
keywords = "Computer-assisted drug therapy, Drug classification, Knowledge bases, National Drug File Reference Terminology",
author = "Linas Simonaitis and Gunther Schadow",
year = "2010",
doi = "10.3233/978-1-60750-588-4-1095",
language = "English",
isbn = "9781607505877",
volume = "160",
pages = "1095--1099",
booktitle = "Studies in Health Technology and Informatics",
edition = "PART 1",

}

TY - GEN

T1 - Querying the national drug file reference terminology (NDFRT) to assign drugs to decision support categories

AU - Simonaitis, Linas

AU - Schadow, Gunther

PY - 2010

Y1 - 2010

N2 - Introduction: The accurate categorization of drugs is a prerequisite for decision support rules. The manual process of creating drug classes can be laborious and error-prone. Methods: All 142 drug classes currently used at Regenstrief Institute for drug interaction alerts were extracted. These drug classes were replicated as fully-defined concepts in our local instance of the NDFRT knowledge base. The performance of these two strategies (manual classification vs. NDFRT-based queries) was compared, and the sensitivity and specificity of each was calculated. Results: Compared to existing manual classifications, NDFRT-based queries made a greater number of correct class-drug assignments: 1528 vs. 1266. NDFRT queries have greater sensitivity (74.9% vs. 62.1%) to classify drugs. However, they have less specificity (85.6% vs. 99.8%). Conclusion: The NDFRT knowledge base shows promise for use in an automated strategy to improve the creation and update of drug classes. The chief disadvantage of our NDFRT-based approach was a greater number of false positive assignments due to the inclusion of non-systemic doseforms.

AB - Introduction: The accurate categorization of drugs is a prerequisite for decision support rules. The manual process of creating drug classes can be laborious and error-prone. Methods: All 142 drug classes currently used at Regenstrief Institute for drug interaction alerts were extracted. These drug classes were replicated as fully-defined concepts in our local instance of the NDFRT knowledge base. The performance of these two strategies (manual classification vs. NDFRT-based queries) was compared, and the sensitivity and specificity of each was calculated. Results: Compared to existing manual classifications, NDFRT-based queries made a greater number of correct class-drug assignments: 1528 vs. 1266. NDFRT queries have greater sensitivity (74.9% vs. 62.1%) to classify drugs. However, they have less specificity (85.6% vs. 99.8%). Conclusion: The NDFRT knowledge base shows promise for use in an automated strategy to improve the creation and update of drug classes. The chief disadvantage of our NDFRT-based approach was a greater number of false positive assignments due to the inclusion of non-systemic doseforms.

KW - Computer-assisted drug therapy

KW - Drug classification

KW - Knowledge bases

KW - National Drug File Reference Terminology

UR - http://www.scopus.com/inward/record.url?scp=78649509578&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649509578&partnerID=8YFLogxK

U2 - 10.3233/978-1-60750-588-4-1095

DO - 10.3233/978-1-60750-588-4-1095

M3 - Conference contribution

C2 - 20841853

AN - SCOPUS:78649509578

SN - 9781607505877

VL - 160

SP - 1095

EP - 1099

BT - Studies in Health Technology and Informatics

ER -