Network meta-analysis for clinicians

Abstract

Decision making in clinical practice requires consideration of the relative efficacy and safety of medical interventions. A systematic review and meta-analysis, the results of which have the highest level of confidence in evidence-based medicine, only compare the effectiveness of two interventions, provided that there is a direct comparison between them in a set of randomized controlled trials. The development of statistical methods has led to the development of the network meta-analysis method, the application of which allows comparison for more than two interventions and even if the interventions were not directly compared in randomized controlled trials, but have a common comparison intervention. As a result, network meta-analysis is increasingly being used as an evidence base for the effectiveness of medical interventions. However, there are important assumptions and conditions underlying the performance of network meta-analysis. In this work, we tried to outline the main aspects of network meta-analysis that are important for clinicians in terms of its implementation and interpretation of its results.