PMID- 21546507
OWN - NLM
STAT- MEDLINE
DCOM- 20120120
LR  - 20211020
IS  - 1527-974X (Electronic)
IS  - 1067-5027 (Print)
IS  - 1067-5027 (Linking)
VI  - 18
IP  - 5
DP  - 2011 Sep-Oct
TI  - Using information mining of the medical literature to improve drug safety.
PG  - 668-74
LID - 10.1136/amiajnl-2011-000096 [doi]
AB  - OBJECTIVE: Prescription drugs can be associated with adverse effects (AEs) that 
      are unrecognized despite evidence in the medical literature, as shown by 
      rofecoxib's late recall in 2004. We assessed whether applying information mining 
      to PubMed could reveal major drug-AE associations if articles testing whether 
      drugs cause AEs are over-represented in the literature. DESIGN: MEDLINE citations 
      published between 1949 and September 2009 were retrieved if they mentioned one of 
      38 drugs and one of 55 AEs. A statistical document classifier (using MeSH index 
      terms) was constructed to remove irrelevant articles unlikely to test whether a 
      drug caused an AE. The remaining relevant articles were analyzed using a 
      disproportionality analysis that identified drug-AE associations (signals of 
      disproportionate reporting) using step-up procedures developed to control the 
      familywise type I error rate. MEASUREMENTS: Sensitivity and positive predictive 
      value (PPV) for empirical drug-AE associations as judged against drug-AE 
      associations subject to FDA warnings. RESULTS: In testing, the statistical 
      document classifier identified relevant articles with 81% sensitivity and 87% 
      PPV. Using data filtered by the statistical document classifier, base-case models 
      showed 64.9% sensitivity and 42.4% PPV for detecting FDA warnings. Base-case 
      models discovered 54% of all detected FDA warnings using literature published 
      before warnings. For example, the rofecoxib-heart disease association was evident 
      using literature published before 2002. Analyses incorporating literature 
      mentioning AEs common to the drug class of interest yielded 71.4% sensitivity and 
      40.7% PPV. CONCLUSIONS: Results from large-scale literature retrieval and 
      analysis (literature mining) compared favorably with and could complement current 
      drug safety methods.
FAU - Shetty, Kanaka D
AU  - Shetty KD
AD  - RAND Corporation, Santa Monica, California 90401, USA.
FAU - Dalal, Siddhartha R
AU  - Dalal SR
LA  - eng
PT  - Evaluation Study
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20110505
PL  - England
TA  - J Am Med Inform Assoc
JT  - Journal of the American Medical Informatics Association : JAMIA
JID - 9430800
SB  - IM
MH  - *Data Mining
MH  - Humans
MH  - Medical Subject Headings
MH  - *Natural Language Processing
MH  - Product Surveillance, Postmarketing/*methods
MH  - *PubMed
MH  - Sensitivity and Specificity
MH  - United States
PMC - PMC3168306
COIS- Competing interests: None.
EDAT- 2011/05/07 06:00
MHDA- 2012/01/21 06:00
PMCR- 2012/09/01
CRDT- 2011/05/07 06:00
PHST- 2011/05/07 06:00 [entrez]
PHST- 2011/05/07 06:00 [pubmed]
PHST- 2012/01/21 06:00 [medline]
PHST- 2012/09/01 00:00 [pmc-release]
AID - amiajnl-2011-000096 [pii]
AID - 10.1136/amiajnl-2011-000096 [doi]
PST - ppublish
SO  - J Am Med Inform Assoc. 2011 Sep-Oct;18(5):668-74. doi: 
      10.1136/amiajnl-2011-000096. Epub 2011 May 5.