gemtc (version 0.8-8)

gemtc-package: GeMTC: Network meta-analysis in R

Description

An R package for performing network meta-analyses (mixed treatment comparisons).

Details

Network meta-analysis, or mixed treatment comparison (MTC) is a technique to meta-analyze networks of trials comparing two or more treatments at the same time [Dias et al. 2013a]. Using a Bayesian hierarchical model, all direct and indirect comparisons are taken into account to arrive at a single consistent estimate of the effect of all included treatments based on all included studies.

This package allows the automated generation of network meta-analysis models [van Valkenhoef et al. 2012], inclusing both fixed effect and random effects network meta-analysis, node-splitting models to identify inconsistency, and network meta-regression models. Models are estimated using JAGS (through the rjags package).

It is possible to get reproducible results, but as JAGS uses its own pseudo-random number generator, this is somewhat more involved. See mtc.model for details.

The package can read GeMTC files that were created by the GeMTC GUI (now obsolete) or exported from ADDIS 1.x, if the optional package XML is installed. The source for GeMTC is available under the GPL-3 on Github.

References

S. Dias, N.J. Welton, D.M. Caldwell, and A.E. Ades (2010), Checking consistency in mixed treatment comparison meta-analysis, Statistics in Medicine 29(7-8, Sp. Iss. SI):932-944. [doi:10.1002/sim.3767]

S. Dias, A.J. Sutton, A.E. Ades, and N.J. Welton (2013a), A Generalized Linear Modeling Framework for Pairwise and Network Meta-analysis of Randomized Controlled Trials, Medical Decision Making 33(5):607-617. [doi:10.1177/0272989X12458724]

S. Dias, A.J. Sutton, N.J. Welton, and A.E. Ades (2013b), Heterogeneity - Subgroups, Meta-Regression, Bias, and Bias-Adjustment, Medical Decision Making 33(5):618-640. [doi:10.1177/0272989X13485157]

S. Dias, N.J. Welton, A.J. Sutton, D.M. Caldwell, G. Lu, and A.E. Ades (2013c), Inconsistency in Networks of Evidence Based on Randomized Controlled Trials, Medical Decision Making 33(5):641-656. [doi:10.1177/0272989X12455847]

A. Gelman, A. Jakulin, M. Grazia Pittau, Y.-S. Su (2008), A weakly informative default prior distribution for logistic and other regression models, The Annals of Applied Statistics 2(4):1360-1383. [doi:10.1214/08-AOAS191]

R.M. Turner, J. Davey, M.J. Clarke, S.G. Thompson, J.P.T. Higgins (2012), Predicting the extent of heterogeneity in meta-analysis, using empirical data from the Cochrane Database of Systematic Reviews, International Journal of Epidemiology 41(3):818-827. [doi:10.1093/ije/dys041]

G. van Valkenhoef, G. Lu, B. de Brock, H. Hillege, A.E. Ades, and N.J. Welton (2012), Automating network meta-analysis, Research Synthesis Methods 3(4):285-299. [doi:10.1002/jrsm.1054]

G. van Valkenhoef, S. Dias, A.E. Ades, and N.J. Welton (2015), Automated generation of node-splitting models for assessment of inconsistency in network meta-analysis, Research Synthesis Methods, accepted manuscript. [doi:10.1002/jrsm.1167]

G. van Valkenhoef et al. (draft), Modeling inconsistency as heterogeneity in network meta-analysis, draft manuscript.

D.E. Warn, S.G. Thompson, and D.J. Spiegelhalter (2002), Bayesian random effects meta-analysis of trials with binary outcomes: methods for the absolute risk difference and relative risk scales, Statistics in Medicine 21(11):1601-1623. [doi:10.1002/sim.1189]

See Also

mtc.network, mtc.model, mtc.run

Examples

# NOT RUN {
# Load the example network and generate a consistency model:
model <- mtc.model(smoking, type="consistency")

# Load pre-generated samples instead of runing the model:
# }
# NOT RUN {
results <- mtc.run(model, thin=10)
# }
# NOT RUN {
results <- dget(system.file("extdata/luades-smoking.samples.gz", package="gemtc"))

# Print a basic statistical summary of the results:
summary(results)
## Iterations = 5010:25000
## Thinning interval = 10 
## Number of chains = 4 
## Sample size per chain = 2000 
## 
## 1. Empirical mean and standard deviation for each variable,
##    plus standard error of the mean:
## 
##         Mean     SD Naive SE Time-series SE
## d.A.B 0.4965 0.4081 0.004563       0.004989
## d.A.C 0.8359 0.2433 0.002720       0.003147
## d.A.D 1.1088 0.4355 0.004869       0.005280
## sd.d  0.8465 0.1913 0.002139       0.002965
## 
## 2. Quantiles for each variable:
## 
##          2.5%    25%    50%    75% 97.5%
## d.A.B -0.2985 0.2312 0.4910 0.7530 1.341
## d.A.C  0.3878 0.6720 0.8273 0.9867 1.353
## d.A.D  0.2692 0.8197 1.0983 1.3824 2.006
## sd.d   0.5509 0.7119 0.8180 0.9542 1.283
# }