PMID- 18487830
OWN - NLM
STAT- MEDLINE
DCOM- 20080930
LR  - 20080519
IS  - 0926-9630 (Print)
IS  - 0926-9630 (Linking)
VI  - 136
DP  - 2008
TI  - Mining for adverse drug events with formal concept analysis.
PG  - 803-8
AB  - The pharmacovigilance databases consist of several case reports involving drugs 
      and adverse events (AEs). Some methods are applied consistently to highlight all 
      signals, i.e. all statistically significant associations between a drug and an 
      AE. These methods are appropriate for verification of more complex relationships 
      involving one or several drug(s) and AE(s) (e.g; syndromes or interactions) but 
      do not address the identification of them. We propose a method for the extraction 
      of these relationships based on Formal Concept Analysis (FCA) associated with 
      disproportionality measures. This method identifies all sets of drugs and AEs 
      which are potential signals, syndromes or interactions. Compared to a previous 
      experience of disproportionality analysis without FCA, the addition of FCA was 
      more efficient for identifying false positives related to concomitant drugs.
FAU - Estacio-Moreno, Alexander
AU  - Estacio-Moreno A
AD  - LORIA, Campus Scientifique, BP 239, 54506 Vandoeuvre, Nancy Cedex, France.
FAU - Toussaint, Yannick
AU  - Toussaint Y
FAU - Bousquet, Cedric
AU  - Bousquet C
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
PL  - Netherlands
TA  - Stud Health Technol Inform
JT  - Studies in health technology and informatics
JID - 9214582
MH  - *Adverse Drug Reaction Reporting Systems
MH  - Algorithms
MH  - Artificial Intelligence
MH  - Drug Interactions
MH  - Humans
MH  - *Information Storage and Retrieval
MH  - Product Surveillance, Postmarketing
EDAT- 2008/05/20 09:00
MHDA- 2008/10/01 09:00
CRDT- 2008/05/20 09:00
PHST- 2008/05/20 09:00 [pubmed]
PHST- 2008/10/01 09:00 [medline]
PHST- 2008/05/20 09:00 [entrez]
PST - ppublish
SO  - Stud Health Technol Inform. 2008;136:803-8.