Borrowing of strength from indirect evidence in 40 network meta-analyses

Lifeng Lin, Aiwen Xing, Michael J. Kofler, Mohammad H Murad

Research output: Contribution to journalArticle

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.

LanguageEnglish (US)
Pages41-49
Number of pages9
JournalJournal of Clinical Epidemiology
Volume106
DOIs
StatePublished - Feb 1 2019

Fingerprint

Uncertainty
Research Personnel
Network Meta-Analysis
Datasets

Keywords

  • Bayesian analysis
  • Borrowing of strength
  • Indirect evidence
  • Network meta-analysis
  • Research synthesis
  • Systematic review

ASJC Scopus subject areas

  • Epidemiology

Cite this

Borrowing of strength from indirect evidence in 40 network meta-analyses. / Lin, Lifeng; Xing, Aiwen; Kofler, Michael J.; Murad, Mohammad H.

In: Journal of Clinical Epidemiology, Vol. 106, 01.02.2019, p. 41-49.

Research output: Contribution to journalArticle

Lin, Lifeng ; Xing, Aiwen ; Kofler, Michael J. ; Murad, Mohammad H. / Borrowing of strength from indirect evidence in 40 network meta-analyses. In: Journal of Clinical Epidemiology. 2019 ; Vol. 106. pp. 41-49.
@article{921fa0b1879b4a24ac37b1e57eb357df,
title = "Borrowing of strength from indirect evidence in 40 network meta-analyses",
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.",
keywords = "Bayesian analysis, Borrowing of strength, Indirect evidence, Network meta-analysis, Research synthesis, Systematic review",
author = "Lifeng Lin and Aiwen Xing and Kofler, {Michael J.} and Murad, {Mohammad H}",
year = "2019",
month = "2",
day = "1",
doi = "10.1016/j.jclinepi.2018.10.007",
language = "English (US)",
volume = "106",
pages = "41--49",
journal = "Journal of Clinical Epidemiology",
issn = "0895-4356",
publisher = "Elsevier USA",

}

TY - JOUR

T1 - Borrowing of strength from indirect evidence in 40 network meta-analyses

AU - Lin, Lifeng

AU - Xing, Aiwen

AU - Kofler, Michael J.

AU - Murad, Mohammad H

PY - 2019/2/1

Y1 - 2019/2/1

N2 - 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.

AB - 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.

KW - Bayesian analysis

KW - Borrowing of strength

KW - Indirect evidence

KW - Network meta-analysis

KW - Research synthesis

KW - Systematic review

UR - http://www.scopus.com/inward/record.url?scp=85056164247&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056164247&partnerID=8YFLogxK

U2 - 10.1016/j.jclinepi.2018.10.007

DO - 10.1016/j.jclinepi.2018.10.007

M3 - Article

VL - 106

SP - 41

EP - 49

JO - Journal of Clinical Epidemiology

T2 - Journal of Clinical Epidemiology

JF - Journal of Clinical Epidemiology

SN - 0895-4356

ER -