Abstract
BackgroundMeta-analyses of randomized controlled trials (RCTs) have been considered as the highest level of evidence in the pyramid of the evidence-based medicine. However, the causal interpretation of such results is seldom studied.MethodsWe systematically searched for methodologies pertaining to the implementation of a causally explicit framework for meta-analysis of randomized controlled trials and discussed the interpretation and scientific relevance of such causal estimands. We performed a systematic search in four databases to identify relevant methodologies, supplemented with hand-search. We included methodologies that described causality under counterfactuals and potential outcomes framework.ResultsWe only identified three efforts explicitly describing a causal framework on meta-analysis of RCTs. Two approaches required individual participant data, while for the last one, only summary data were required. All three approaches presented a sufficient framework under which a meta-analytical estimate is identifiable and estimable. However, several conceptual limitations remain, mainly in regard to the data generation process under which the selected RCTs rise.ConclusionsWe undertook a review of methodologies on causal inference methods in meta-analyses. Although all identified methodologies provide valid causal estimates, there are limitations in the assumptions regarding the data generation process and sampling of the potential RCTs to be included in the meta-analysis which pose challenges to the interpretation and scientific relevance of the identified causal effects. Despite both causal inference and meta-analysis being extensively studied in the literature, limited effort exists of combining those two frameworks.
Highlights
Meta-analyses of randomized controlled trials (RCTs) have been considered as the highest level of evidence in the pyramid of the evidence-based medicine
Causal inference for meta-analysis using IPD data from independent RCTs Sobel et al [6] described a framework where causal estimates can be derived from a meta-analysis of RCTs when individual participant data (IPD) are available
Had we had a random sample of trials, this sample would allow for the covariate distribution of the superpopulation to be consistent with the covariate distribution of a naturally existing population. This is rarely the case, as conducting a trial is largely a function of very specific motives and aims [13, 14], and one may argue that a random sample of trials may not naturally occur. While this amalgamation of trials does not directly affect the underlying assumptions invoked by a fixed-effects or a random effect meta-analysis, which pertain to the sampling of the effect estimates rather than the sampling of trials [13, 15], we argue that, without taking into account any potential differences between the structure of the superpopulation and that of a naturally occurring population, the generalizability of the produced results would be hindered
Summary
Meta-analyses of randomized controlled trials (RCTs) have been considered as the highest level of evidence in the pyramid of the evidence-based medicine. When a randomized design is not feasible, data from observational study designs can be used to emulate a randomized experiment based on causal inference approach to obtain a valid causal estimate [3, 4]. By combining evidence from RCTs using meta-analytical approaches, one can potentially achieve higher levels of evidence. One caveat of this approach is that while each study’s estimate can potentially have a causal interpretation, their aggregation may lose this capacity, mainly due to differences on inherent study characteristics including (but not restricted to) differences in populations, in treatments and/or on the definition of outcome across studies
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
