An investigation of the impact of using different methods for network meta-analysis

A protocol for an empirical evaluation

Amalia (Emily) Karahalios, Georgia Salanti, Simon L. Turner, G. Peter Herbison, Ian R. White, Areti Angeliki Veroniki, Adriani Nikolakopoulou, Joanne E. McKenzie

Research output: Contribution to journalArticleOtherpeer-review

1 Citation (Scopus)

Abstract

Background: Network meta-analysis, a method to synthesise evidence from multiple treatments, has increased in popularity in the past decade. Two broad approaches are available to synthesise data across networks, namely, arm- and contrast-synthesis models, with a range of models that can be fitted within each. There has been recent debate about the validity of the arm-synthesis models, but to date, there has been limited empirical evaluation comparing results using the methods applied to a large number of networks. We aim to address this gap through the re-analysis of a large cohort of published networks of interventions using a range of network meta-analysis methods. Methods: We will include a subset of networks from a database of network meta-analyses of randomised trials that have been identified and curated from the published literature. The subset of networks will include those where the primary outcome is binary, the number of events and participants are reported for each direct comparison, and there is no evidence of inconsistency in the network. We will re-analyse the networks using three contrast-synthesis methods and two arm-synthesis methods. We will compare the estimated treatment effects, their standard errors, treatment hierarchy based on the surface under the cumulative ranking (SUCRA) curve, the SUCRA value, and the between-trial heterogeneity variance across the network meta-analysis methods. We will investigate whether differences in the results are affected by network characteristics and baseline risk. Discussion: The results of this study will inform whether, in practice, the choice of network meta-analysis method matters, and if it does, in what situations differences in the results between methods might arise. The results from this research might also inform future simulation studies.

Original languageEnglish
Article number119
Number of pages10
JournalSystematic Reviews
Volume6
Issue number1
DOIs
Publication statusPublished - 24 Jun 2017

Keywords

  • Arm-based
  • Bayesian
  • Contrast-based
  • Empirical evaluation
  • Evidence-based methods
  • Heterogeneity
  • Indirect treatment comparison
  • Mixed-treatment comparison
  • Multiple treatment comparison
  • Network meta-analysis

Cite this

Karahalios, Amalia (Emily) ; Salanti, Georgia ; Turner, Simon L. ; Herbison, G. Peter ; White, Ian R. ; Veroniki, Areti Angeliki ; Nikolakopoulou, Adriani ; McKenzie, Joanne E. / An investigation of the impact of using different methods for network meta-analysis : A protocol for an empirical evaluation. In: Systematic Reviews. 2017 ; Vol. 6, No. 1.
@article{76d40af3f45242209931bfaa3693e826,
title = "An investigation of the impact of using different methods for network meta-analysis: A protocol for an empirical evaluation",
abstract = "Background: Network meta-analysis, a method to synthesise evidence from multiple treatments, has increased in popularity in the past decade. Two broad approaches are available to synthesise data across networks, namely, arm- and contrast-synthesis models, with a range of models that can be fitted within each. There has been recent debate about the validity of the arm-synthesis models, but to date, there has been limited empirical evaluation comparing results using the methods applied to a large number of networks. We aim to address this gap through the re-analysis of a large cohort of published networks of interventions using a range of network meta-analysis methods. Methods: We will include a subset of networks from a database of network meta-analyses of randomised trials that have been identified and curated from the published literature. The subset of networks will include those where the primary outcome is binary, the number of events and participants are reported for each direct comparison, and there is no evidence of inconsistency in the network. We will re-analyse the networks using three contrast-synthesis methods and two arm-synthesis methods. We will compare the estimated treatment effects, their standard errors, treatment hierarchy based on the surface under the cumulative ranking (SUCRA) curve, the SUCRA value, and the between-trial heterogeneity variance across the network meta-analysis methods. We will investigate whether differences in the results are affected by network characteristics and baseline risk. Discussion: The results of this study will inform whether, in practice, the choice of network meta-analysis method matters, and if it does, in what situations differences in the results between methods might arise. The results from this research might also inform future simulation studies.",
keywords = "Arm-based, Bayesian, Contrast-based, Empirical evaluation, Evidence-based methods, Heterogeneity, Indirect treatment comparison, Mixed-treatment comparison, Multiple treatment comparison, Network meta-analysis",
author = "Karahalios, {Amalia (Emily)} and Georgia Salanti and Turner, {Simon L.} and Herbison, {G. Peter} and White, {Ian R.} and Veroniki, {Areti Angeliki} and Adriani Nikolakopoulou and McKenzie, {Joanne E.}",
year = "2017",
month = "6",
day = "24",
doi = "10.1186/s13643-017-0511-x",
language = "English",
volume = "6",
journal = "Systematic Reviews",
issn = "2046-4053",
publisher = "Springer-Verlag London Ltd.",
number = "1",

}

An investigation of the impact of using different methods for network meta-analysis : A protocol for an empirical evaluation. / Karahalios, Amalia (Emily); Salanti, Georgia; Turner, Simon L.; Herbison, G. Peter; White, Ian R.; Veroniki, Areti Angeliki; Nikolakopoulou, Adriani; McKenzie, Joanne E.

In: Systematic Reviews, Vol. 6, No. 1, 119, 24.06.2017.

Research output: Contribution to journalArticleOtherpeer-review

TY - JOUR

T1 - An investigation of the impact of using different methods for network meta-analysis

T2 - A protocol for an empirical evaluation

AU - Karahalios, Amalia (Emily)

AU - Salanti, Georgia

AU - Turner, Simon L.

AU - Herbison, G. Peter

AU - White, Ian R.

AU - Veroniki, Areti Angeliki

AU - Nikolakopoulou, Adriani

AU - McKenzie, Joanne E.

PY - 2017/6/24

Y1 - 2017/6/24

N2 - Background: Network meta-analysis, a method to synthesise evidence from multiple treatments, has increased in popularity in the past decade. Two broad approaches are available to synthesise data across networks, namely, arm- and contrast-synthesis models, with a range of models that can be fitted within each. There has been recent debate about the validity of the arm-synthesis models, but to date, there has been limited empirical evaluation comparing results using the methods applied to a large number of networks. We aim to address this gap through the re-analysis of a large cohort of published networks of interventions using a range of network meta-analysis methods. Methods: We will include a subset of networks from a database of network meta-analyses of randomised trials that have been identified and curated from the published literature. The subset of networks will include those where the primary outcome is binary, the number of events and participants are reported for each direct comparison, and there is no evidence of inconsistency in the network. We will re-analyse the networks using three contrast-synthesis methods and two arm-synthesis methods. We will compare the estimated treatment effects, their standard errors, treatment hierarchy based on the surface under the cumulative ranking (SUCRA) curve, the SUCRA value, and the between-trial heterogeneity variance across the network meta-analysis methods. We will investigate whether differences in the results are affected by network characteristics and baseline risk. Discussion: The results of this study will inform whether, in practice, the choice of network meta-analysis method matters, and if it does, in what situations differences in the results between methods might arise. The results from this research might also inform future simulation studies.

AB - Background: Network meta-analysis, a method to synthesise evidence from multiple treatments, has increased in popularity in the past decade. Two broad approaches are available to synthesise data across networks, namely, arm- and contrast-synthesis models, with a range of models that can be fitted within each. There has been recent debate about the validity of the arm-synthesis models, but to date, there has been limited empirical evaluation comparing results using the methods applied to a large number of networks. We aim to address this gap through the re-analysis of a large cohort of published networks of interventions using a range of network meta-analysis methods. Methods: We will include a subset of networks from a database of network meta-analyses of randomised trials that have been identified and curated from the published literature. The subset of networks will include those where the primary outcome is binary, the number of events and participants are reported for each direct comparison, and there is no evidence of inconsistency in the network. We will re-analyse the networks using three contrast-synthesis methods and two arm-synthesis methods. We will compare the estimated treatment effects, their standard errors, treatment hierarchy based on the surface under the cumulative ranking (SUCRA) curve, the SUCRA value, and the between-trial heterogeneity variance across the network meta-analysis methods. We will investigate whether differences in the results are affected by network characteristics and baseline risk. Discussion: The results of this study will inform whether, in practice, the choice of network meta-analysis method matters, and if it does, in what situations differences in the results between methods might arise. The results from this research might also inform future simulation studies.

KW - Arm-based

KW - Bayesian

KW - Contrast-based

KW - Empirical evaluation

KW - Evidence-based methods

KW - Heterogeneity

KW - Indirect treatment comparison

KW - Mixed-treatment comparison

KW - Multiple treatment comparison

KW - Network meta-analysis

UR - http://www.scopus.com/inward/record.url?scp=85021189769&partnerID=8YFLogxK

U2 - 10.1186/s13643-017-0511-x

DO - 10.1186/s13643-017-0511-x

M3 - Article

VL - 6

JO - Systematic Reviews

JF - Systematic Reviews

SN - 2046-4053

IS - 1

M1 - 119

ER -