The Lancet says don’t panic, and wait for a randomized study due out in 2009.

WSJ’s The Numbers Guy explains meta-analysis studies.

Read more for continuing Avandia coverage here at Kevin, M.D.

Update –
Dr. Wes:
“I only know that if I had submitted a meta-analysis to the New England Journal of Medicine regarding any other drug, it likely would have been summarily rejected due to methological flaws inherent to such studies. While the study certainly raises important questions, it still leaves open the possibility that there might be one or more confounding variables to explain the cardiovascular risks with this drug reported.”

Marc Siegel:
“But drug safety and cost/benefit analyses mean looking at more than just a weakly observed mathematically determined association. These shadows will be found in many more places the harder we look for them. And great drugs will be unfairly targeted and destroyed.”

Derek Lowe:
“A meta-analysis is a much different beast, since you’re trying to fit a large number of different trials, run in different ways for different reasons, into the same framework. Not everyone trusts them, even when the analysis is performed by someone as competent as Nissen . . .”