Most overviews of Cochrane reviews neglected potential biases from dual authorship

Abstract

Objective: Some authors of Cochrane overviews have also (co-)authored one or more of the underlying reviews. We examined the extent of dual (co-)authorship in Cochrane overviews, how it is dealt with, and whether the issue is raised in protocols.

Study design: The Cochrane Library was searched for overviews and protocols for overviews in September 2015. Data on dual (co-)authorship were extracted for each review into standard spreadsheets by one author and checked for accuracy by a second.

Results: Twenty overviews and 25 protocols were identified. The overviews included a median of 10 reviews (interquartile range [IQR]: 6-18.5). In 18/20 overviews (90%), at least one of the included reviews was affected by dual (co-)authorship. A median of 5 (IQR, 2.5-7) reviews per overview was affected by dual (co-)authorship. In 8/18 (44%) overviews with dual (co-)authorship, quality assessment was conducted independently. In 7/25 (28%) protocols, dual (co-)authorship was mentioned.

Conclusion: Potential biases arising from dual (co-)authorship are often neglected in Cochrane overviews. We argue that authors of Cochrane overviews and Review Groups should pay more attention to the issue, to avoid bias and preserve the good reputation that Cochrane overviews will typically deserve.

Keywords: Conflict of interest; Overview; Systematic review.