Issues relating to confounding and meta-analysis when including non-randomized studies in systematic reviews on the effects of interventions

Background: Confounding caused by selection bias is often a key difference between non-randomized studies (NRS) and randomized controlled trials (RCTs) of interventions. Key methodological issues: In this third paper of the series, we consider issues relating to the inclusion of NRS in systematic reviews on the effects of interventions. We discuss whether potential biases from confounding in NRS can be accounted for, the limitations of current methods for attempting to do so, the different contexts of NRS and RCTs, the problems these issues create for reviewers, and a research agenda for the future. Guidance: Reviewers who are considering whether or not to include NRS in meta-analyses must weigh a number of factors. Including NRS may allow a review to address outcomes or pragmatic implementations of an intervention not studied in RCTs, but it will also increase the workload for the review team, as well as their required technical repertoire. Furthermore, the results of a synthesis involving NRS will likely be more difficult to interpret, and less certain, relative to the results of a synthesis involving only randomized studies. When both randomized and non-randomized evidence are available, we favor a strategy of including NRS and RCTs in the same systematic review but synthesizing their results separately. Conclusion: Including NRS will often make the limitations of the evidence derived from RCTs more apparent, thereby guiding inferences about generalizability, and may help with the design of the next generation of RCTs. Copyright (C) 2012 John Wiley & Sons, Ltd.