EcoSta 2019: Start Registration
View Submission - EcoSta2019
Title: On the efficiency of network meta-analysis Authors:  Lifeng Lin - Florida State University (United States) [presenting]
Abstract: Network meta-analysis (NMA) has become an increasingly used tool to compare multiple treatments simultaneously by synthesizing direct and indirect evidence in clinical research. However, the synthesized overall evidence is seldom compared with the direct evidence to validate the efficiency of an NMA. On the one hand, we propose three new measures (i.e., the effective number of studies, the effective sample size, and the effective precision) to preliminarily quantify overall evidence gained in NMAs at the pre-analysis stage. They permit evidence users to intuitively evaluate the benefit of performing NMAs, compared with pairwise meta-analyses based on only direct evidence. We use an illustrative example to demonstrate their derivations and interpretations. On the other hand, at the post-analysis stage, we use the recently proposed borrowing of strength (BoS) statistic to empirically evaluate the benefits by incorporating indirect evidence in 40 published NMAs. The BoS statistic quantifies the percentage reduction in the uncertainty of the effect estimate when adding indirect evidence to an NMA. We found that the incremental gain may reliably occur only when at least two head-to-head studies are available and treatments are well connected. Researchers should routinely report and compare the results from both network and pairwise meta-analyses.