PMID- 19941924
OWN - NLM
STAT- MEDLINE
DCOM- 20100603
LR  - 20131121
IS  - 1096-0295 (Electronic)
IS  - 0273-2300 (Linking)
VI  - 56
IP  - 3
DP  - 2010 Apr
TI  - Prediction of drug-related cardiac adverse effects in humans--B: use of QSAR 
      programs for early detection of drug-induced cardiac toxicities.
PG  - 276-89
LID - 10.1016/j.yrtph.2009.11.005 [doi]
AB  - This report describes the use of three quantitative structure-activity 
      relationship (QSAR) programs to predict drug-related cardiac adverse effects 
      (AEs), BioEpisteme, MC4PC, and Leadscope Predictive Data Miner. QSAR models were 
      constructed for 9 cardiac AE clusters affecting Purkinje nerve fibers 
      (arrhythmia, bradycardia, conduction disorder, electrocardiogram, palpitations, 
      QT prolongation, rate rhythm composite, tachycardia, and Torsades de pointes) and 
      5 clusters affecting the heart muscle (coronary artery disorders, heart failure, 
      myocardial disorders, myocardial infarction, and valve disorders). The models 
      were based on a database of post-marketing AEs linked to 1632 chemical 
      structures, and identical training data sets were configured for three QSAR 
      programs. Model performance was optimized and shown to be affected by the ratio 
      of the number of active to inactive drugs. Results revealed that the three 
      programs were complementary and predictive performances using any single 
      positive, consensus two positives, or consensus three positives were as follows, 
      respectively: 70.7%, 91.7%, and 98.0% specificity; 74.7%, 47.2%, and 21.0% 
      sensitivity; and 138.2, 206.3, and 144.2 chi(2). In addition, a prospective study 
      using AE data from the U.S. Food and Drug Administration's (FDA's) MedWatch 
      Program showed 82.4% specificity and 94.3% sensitivity. Furthermore, an external 
      validation study of 18 drugs with serious cardiotoxicity not considered in the 
      models had 88.9% sensitivity.
CI  - Published by Elsevier Inc.
FAU - Frid, Anna A
AU  - Frid AA
AD  - GlobalNet Services, 11820 Parklawn Drive, Rockville, MD 20852, USA.
FAU - Matthews, Edwin J
AU  - Matthews EJ
LA  - eng
PT  - Journal Article
DEP - 20091124
PL  - Netherlands
TA  - Regul Toxicol Pharmacol
JT  - Regulatory toxicology and pharmacology : RTP
JID - 8214983
RN  - 0 (Pharmaceutical Preparations)
SB  - IM
MH  - Adverse Drug Reaction Reporting Systems
MH  - Cardiovascular Diseases/chemically induced/*epidemiology
MH  - Cluster Analysis
MH  - Computer Simulation
MH  - Databases, Factual
MH  - Drug Labeling
MH  - *Drug-Related Side Effects and Adverse Reactions/classification/*epidemiology
MH  - Forecasting
MH  - Heart/*drug effects
MH  - Humans
MH  - Pharmaceutical Preparations/classification
MH  - Product Surveillance, Postmarketing
MH  - Purkinje Fibers/drug effects
MH  - *Quantitative Structure-Activity Relationship
MH  - Software
MH  - United States/epidemiology
MH  - United States Food and Drug Administration
EDAT- 2009/11/28 06:00
MHDA- 2010/06/04 06:00
CRDT- 2009/11/28 06:00
PHST- 2009/06/08 00:00 [received]
PHST- 2009/09/29 00:00 [revised]
PHST- 2009/11/06 00:00 [accepted]
PHST- 2009/11/28 06:00 [entrez]
PHST- 2009/11/28 06:00 [pubmed]
PHST- 2010/06/04 06:00 [medline]
AID - S0273-2300(09)00227-X [pii]
AID - 10.1016/j.yrtph.2009.11.005 [doi]
PST - ppublish
SO  - Regul Toxicol Pharmacol. 2010 Apr;56(3):276-89. doi: 10.1016/j.yrtph.2009.11.005. 
      Epub 2009 Nov 24.