TY  - JOUR
T1  - ANalytical issues regarding rosiglitazone meta-analysis
AU  - Claggett B, Wei L
Y1  - 2011/01/24
N1  - 10.1001/archinternmed.2010.508
JO  - Archives of Internal Medicine
SP  - 179
EP  - 180
VL  - 171
IS  - 2
N2  - 
We read with great interest the recently published article by Nissen and Wolski,1 which updated their previous meta-analysis2 of risk for myocardial infarction and cardiovascular mortality relating to the diabetes drug rosiglitazone. The authors conclude that rosiglitazone statistically significantly increases risk of myocardial infarction relative to comparators by reporting an odds ratio of 1.28, with a 95% confidence interval (CI) of 1.02 to 1.63 and a significant P value of .04, while finding no significant difference in cardiovascular mortality (P = .86 in their current analysis, compared with P = .06 in their previous report).

SN  - 0003-9926
M3  - doi: 10.1001/archinternmed.2010.508
UR  - http://dx.doi.org/10.1001/archinternmed.2010.508
ER  -