Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 May 19:7:271.
doi: 10.3389/fvets.2020.00271. eCollection 2020.

How to Conduct a Bayesian Network Meta-Analysis

Dapeng Hu  1 , Annette M O'Connor  2 , Chong Wang  1   3 , Jan M Sargeant  4 , Charlotte B Winder  4
Affiliations

How to Conduct a Bayesian Network Meta-Analysis

Dapeng Hu et al. Front Vet Sci. .

Abstract

Network meta-analysis is a general approach to integrate the results of multiple studies in which multiple treatments are compared, often in a pairwise manner. In this tutorial, we illustrate the procedures for conducting a network meta-analysis for binary outcomes data in the Bayesian framework using example data. Our goal is to describe the workflow of such an analysis and to explain how to generate informative results such as ranking plots and treatment risk posterior distribution plots. The R code used to conduct a network meta-analysis in the Bayesian setting is provided at GitHub.

Keywords: Bayesian; network meta-analysis; systematic review; tutorial; veterinary science.

PubMed Disclaimer

Figures

Figure 1
Figure 1
An example of the formatting of the BUGS code for the comparative model. This code was modified from code originally published elsewhere (7).
Figure 2
Figure 2
An example of the formatting of the BUGS code for the baseline effects model. This code was modified from code originally published elsewhere (7).
Figure 3
Figure 3
The ranking plot. The left column is the treatment name with the number of studies including that treatment. The right column is the posterior mean ranking of the absolute risk of each treatment and 95% credible interval. Lower rankings have lower incidence of the disease.
Figure 4
Figure 4
The network plot. Each node represents treatment and the number is the corresponding number of studies including that treatment. An edge between two nodes (treatments) means there were studies comparing these two treatments.
Figure 5
Figure 5
The posterior distribution of the event risk of each treatment.
See this image and copyright information in PMC

References

    1. Coleman CI, Phung OJ, Cappelleri JC, Baker WL, Kluger J, White CM, et al. Use of Mixed Treatment Comparisons in Systematic Reviews [Internet]. Agency for Healthcare Research and Quality (2012). Available online at: www.effectivehealthcare.ahrq.gov/reports/final.cfm - PubMed
    1. van Houwelingen HC, Arends LR, Stijnen T. Advanced methods in meta-analysis: multivariate approach and meta-regression. Stat Med. (2002) 21:589–624. 10.1002/sim.1040 - DOI - PubMed
    1. Smith E, Hubbard S, Cooper N, Abrams K. Using network meta-analysis of individual patient data (IPD) & summary aggregate data (SAD) to identify which combinations of interventions work best for which individuals. Value Health. (2017) 20:A758 10.1016/j.jval.2017.08.2138 - DOI
    1. Lu G, Ades A. Combination of direct and indirect evidence in mixed treatment comparisons. Stat Med. (2004) 23:3105–24. 10.1002/sim.1875 - DOI - PubMed
    1. O'Connor AM, Coetzee JF, da Silva N, Wang C. A mixed treatment comparison meta-analysis of antibiotic treatments for bovine respiratory disease. Prev Vet Med. (2013) 3:77–87. 10.1016/j.prevetmed.2012.11.025 - DOI - PubMed

LinkOut - more resources