Automated detection of off-label drug use

Kenneth Jung, Paea LePendu, William S. Chen, Srinivasan V. Iyer, Benjamin Readhead, Joel T. Dudley, Nigam H. Shah

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

Off-label drug use, defined as use of a drug in a manner that deviates from its approved use defined by the drug's FDA label, is problematic because such uses have not been evaluated for safety and efficacy. Studies estimate that 21% of prescriptions are off-label, and only 27% of those have evidence of safety and efficacy. We describe a data-mining approach for systematically identifying off-label usages using features derived from free text clinical notes and features extracted from two databases on known usage (Medi-Span and DrugBank). We trained a highly accurate predictive model that detects novel off-label uses among 1,602 unique drugs and 1,472 unique indications. We validated 403 predicted uses across independent data sources. Finally, we prioritize well-supported novel usages for further investigation on the basis of drug safety and cost.

Original languageEnglish (US)
Article numbere89324
JournalPLoS One
Volume9
Issue number2
DOIs
StatePublished - Feb 19 2014
Externally publishedYes

Fingerprint

Off-Label Use
Labels
drugs
Safety
Pharmaceutical Preparations
Drug Costs
Data Mining
Information Storage and Retrieval
Prescriptions
Databases
Data mining
Costs

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Jung, K., LePendu, P., Chen, W. S., Iyer, S. V., Readhead, B., Dudley, J. T., & Shah, N. H. (2014). Automated detection of off-label drug use. PLoS One, 9(2), [e89324]. https://doi.org/10.1371/journal.pone.0089324

Automated detection of off-label drug use. / Jung, Kenneth; LePendu, Paea; Chen, William S.; Iyer, Srinivasan V.; Readhead, Benjamin; Dudley, Joel T.; Shah, Nigam H.

In: PLoS One, Vol. 9, No. 2, e89324, 19.02.2014.

Research output: Contribution to journalArticle

Jung, K, LePendu, P, Chen, WS, Iyer, SV, Readhead, B, Dudley, JT & Shah, NH 2014, 'Automated detection of off-label drug use', PLoS One, vol. 9, no. 2, e89324. https://doi.org/10.1371/journal.pone.0089324
Jung K, LePendu P, Chen WS, Iyer SV, Readhead B, Dudley JT et al. Automated detection of off-label drug use. PLoS One. 2014 Feb 19;9(2). e89324. https://doi.org/10.1371/journal.pone.0089324
Jung, Kenneth ; LePendu, Paea ; Chen, William S. ; Iyer, Srinivasan V. ; Readhead, Benjamin ; Dudley, Joel T. ; Shah, Nigam H. / Automated detection of off-label drug use. In: PLoS One. 2014 ; Vol. 9, No. 2.
@article{9a4e4b31fc38491e956fa344d3cb2e94,
title = "Automated detection of off-label drug use",
abstract = "Off-label drug use, defined as use of a drug in a manner that deviates from its approved use defined by the drug's FDA label, is problematic because such uses have not been evaluated for safety and efficacy. Studies estimate that 21{\%} of prescriptions are off-label, and only 27{\%} of those have evidence of safety and efficacy. We describe a data-mining approach for systematically identifying off-label usages using features derived from free text clinical notes and features extracted from two databases on known usage (Medi-Span and DrugBank). We trained a highly accurate predictive model that detects novel off-label uses among 1,602 unique drugs and 1,472 unique indications. We validated 403 predicted uses across independent data sources. Finally, we prioritize well-supported novel usages for further investigation on the basis of drug safety and cost.",
author = "Kenneth Jung and Paea LePendu and Chen, {William S.} and Iyer, {Srinivasan V.} and Benjamin Readhead and Dudley, {Joel T.} and Shah, {Nigam H.}",
year = "2014",
month = "2",
day = "19",
doi = "10.1371/journal.pone.0089324",
language = "English (US)",
volume = "9",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "2",

}

TY - JOUR

T1 - Automated detection of off-label drug use

AU - Jung, Kenneth

AU - LePendu, Paea

AU - Chen, William S.

AU - Iyer, Srinivasan V.

AU - Readhead, Benjamin

AU - Dudley, Joel T.

AU - Shah, Nigam H.

PY - 2014/2/19

Y1 - 2014/2/19

N2 - Off-label drug use, defined as use of a drug in a manner that deviates from its approved use defined by the drug's FDA label, is problematic because such uses have not been evaluated for safety and efficacy. Studies estimate that 21% of prescriptions are off-label, and only 27% of those have evidence of safety and efficacy. We describe a data-mining approach for systematically identifying off-label usages using features derived from free text clinical notes and features extracted from two databases on known usage (Medi-Span and DrugBank). We trained a highly accurate predictive model that detects novel off-label uses among 1,602 unique drugs and 1,472 unique indications. We validated 403 predicted uses across independent data sources. Finally, we prioritize well-supported novel usages for further investigation on the basis of drug safety and cost.

AB - Off-label drug use, defined as use of a drug in a manner that deviates from its approved use defined by the drug's FDA label, is problematic because such uses have not been evaluated for safety and efficacy. Studies estimate that 21% of prescriptions are off-label, and only 27% of those have evidence of safety and efficacy. We describe a data-mining approach for systematically identifying off-label usages using features derived from free text clinical notes and features extracted from two databases on known usage (Medi-Span and DrugBank). We trained a highly accurate predictive model that detects novel off-label uses among 1,602 unique drugs and 1,472 unique indications. We validated 403 predicted uses across independent data sources. Finally, we prioritize well-supported novel usages for further investigation on the basis of drug safety and cost.

UR - http://www.scopus.com/inward/record.url?scp=84895862716&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84895862716&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0089324

DO - 10.1371/journal.pone.0089324

M3 - Article

VL - 9

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 2

M1 - e89324

ER -