Bayesian Meta-analysis for randomized controlled trials in anti-tuberculosis chemotherapy: A comprehensive approach.

Ponnuraja, C.; Venkatesan, P.

International Journal of Science and Technology; 2011; 1; 127-135.           

Abstract: Meta-analysis enables researchers to combine the results of several studies to get a reliable estimate. This paper examines the reviews and findings of sixteen randomized tuberculosis clinical trials and each reporting results from several independent trials. Each finding pools the results from the relevant trials in order to evaluate the efficacy of a certain treatment for a specified medical condition. These studies require consistent assessment of homogeneity of treatment effect before pooling. This paper outlined some innovations in Meta-analysis using Markov chain Monte Carlo (MCMC) techniques for implementing Bayesian random effects models. Additionally we compared the Bayesian approach with frequentist random effects model. We discuss more in a random effects approach to combining the evidence from a series of experiments particularly comparing two treatments. This approach incorporates the heterogeneity of effects in the analysis of the overall treatment efficacy. The model can be extended to include relevant covariates which would reduce the heterogeneity and allow for more specific therapeutic recommendations. We suggest a simple non iterative procedure for characterizing the distribution of treatment effects in a series of studies. These techniques allow different aspects of variation to be incorporated into descriptions of the association between studies. This work attempts to discuss the application of MCMC algorithm for high dimensional clinical trial tuberculosis data.

Keywords: Meta-analysis; Heterogeneity; Bayesian models; Fixed effect model; Random effect models; Markov chain Monte Carlo

Back to List of publications / Home