Lifeng Lin1, Aiwen Xing2, Michael J Kofler3, Mohammad Hassan Murad4. 1. Department of Statistics, Florida State University, Tallahassee, FL 32306, USA. Electronic address: linl@stat.fsu.edu. 2. Department of Statistics, Florida State University, Tallahassee, FL 32306, USA. 3. Department of Psychology, Florida State University, Tallahassee, FL 32306, USA. 4. Evidence-Based Practice Center, Mayo Clinic, Rochester, MN 55905, USA.
Abstract
OBJECTIVES: Network meta-analysis (NMA) is increasingly being used to synthesize direct and indirect evidence and help decision makers simultaneously compare multiple treatments. We empirically evaluate the incremental gain in precision achieved by incorporating indirect evidence in NMAs. STUDY DESIGN AND SETTING: We performed both network and pairwise meta-analyses on 40 published data sets of multiple-treatment comparisons. Their results were compared using the recently proposed borrowing of strength (BoS) statistic, which quantifies the percentage reduction in the uncertainty of the effect estimate when adding indirect evidence to an NMA. RESULTS: We analyzed 915 possible treatment comparisons, from which 484 (53%) had no direct evidence (BoS = 100%). In 181 comparisons with only one study contributing direct evidence, NMAs resulted in reduced precision (BoS < 0) and no appreciable improvements in precision (0 < BoS < 30%) for 104 (57.5%) and 23 (12.7%) comparisons, respectively. In 250 comparisons with at least two studies contributing direct evidence, NMAs provided increased precision with BoS ≥ 30% for 166 (66.4%) comparisons. CONCLUSION: Although NMAs have the potential to provide more precise results than those only based on direct evidence, 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.
OBJECTIVES: Network meta-analysis (NMA) is increasingly being used to synthesize direct and indirect evidence and help decision makers simultaneously compare multiple treatments. We empirically evaluate the incremental gain in precision achieved by incorporating indirect evidence in NMAs. STUDY DESIGN AND SETTING: We performed both network and pairwise meta-analyses on 40 published data sets of multiple-treatment comparisons. Their results were compared using the recently proposed borrowing of strength (BoS) statistic, which quantifies the percentage reduction in the uncertainty of the effect estimate when adding indirect evidence to an NMA. RESULTS: We analyzed 915 possible treatment comparisons, from which 484 (53%) had no direct evidence (BoS = 100%). In 181 comparisons with only one study contributing direct evidence, NMAs resulted in reduced precision (BoS < 0) and no appreciable improvements in precision (0 < BoS < 30%) for 104 (57.5%) and 23 (12.7%) comparisons, respectively. In 250 comparisons with at least two studies contributing direct evidence, NMAs provided increased precision with BoS ≥ 30% for 166 (66.4%) comparisons. CONCLUSION: Although NMAs have the potential to provide more precise results than those only based on direct evidence, 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.
Authors: Orestis Efthimiou; Thomas P A Debray; Gert van Valkenhoef; Sven Trelle; Klea Panayidou; Karel G M Moons; Johannes B Reitsma; Aijing Shang; Georgia Salanti Journal: Res Synth Methods Date: 2016-01-11 Impact factor: 5.273
Authors: Edward J Mills; John P A Ioannidis; Kristian Thorlund; Holger J Schünemann; Milo A Puhan; Gordon H Guyatt Journal: JAMA Date: 2012-09-26 Impact factor: 56.272
Authors: Rebecca M Turner; Jonathan Davey; Mike J Clarke; Simon G Thompson; Julian Pt Higgins Journal: Int J Epidemiol Date: 2012-03-29 Impact factor: 7.196
Authors: Sofia Dias; Nicky J Welton; Alex J Sutton; Deborah M Caldwell; Guobing Lu; A E Ades Journal: Med Decis Making Date: 2013-07 Impact factor: 2.583