Automated generation of node-splitting models for assessment of inconsistency in network meta-analysis.

摘要: Network meta-analysis enables the simultaneous synthesis of a network clinical trials comparing any number treatments. Potential inconsistencies between estimates relative treatment effects are an important concern, and several methods to detect inconsistency have been proposed. This paper is concerned with node-splitting approach, which particularly attractive because its straightforward interpretation, contrasting from both direct indirect evidence. However, analyses labour-intensive each comparison interest requires separate model. It would be advantageous if models could estimated automatically for all comparisons interest. We present unambiguous decision rule choose split, prove that it selects only in potentially inconsistent loops network, investigated. Moreover, circumvents problems parameterisation multi-arm trials, ensuring model generation trivial cases. Thus, our eliminate most manual work involved using enabling analyst focus on interpreting results.