Traditional meta-analytical methods commonly used for synthesizing evidence from clinical trials are limited in comparing two interventions at a time. However, for any given condition there is usually a plethora of alternative treatment options. This situation has motivated the development of network meta-analysis which is an extension of conventional meta-analysis that allows the simultaneous synthesis of data from networks of trials. By combining direct and indirect information, network meta-analysis can inform every possible treatment comparison, even those for which no head-to-head trials exist.

This course will focus on the role of network meta-analyses in comparative effectiveness research. We will examine the statistical methods and methodological aspects involved, the assumptions underlying the method and the potential sources of bias that can invalidate the results. Finally, we will discuss methods for reporting and critically appraising the results from network meta-analyses.

By the end of the course, participants will be able to:

1. Understand the concept and principles of network meta-analysis
2. Describe and the different steps of conducting a network meta-analysis of (framing question, forming the network, evaluating the assumptions, synthesizing evidence, interpreting findings)
3. To synthesize the data from a network of trials using Stata
4. Interpret the results of a network meta-analysis
5. Identify the limitations and potential sources of bias
6. Critically appraise the results from a meta-analysis and know the reporting guidelines in this field (PRISMA extension)

Some previous experience with systematic reviews and meta-analyses and basic knowledge of statistics is required for all participants. Basic knowledge of Stata is also desirable. All participants should bring a laptop, with Stata software installed (version 13 or a more recent version).

Mavridis D, Giannatsi M, Cipriani A, Salanti G. 2015. A Primer on Network Meta-Analysis with Emphasis on Mental Health. Evidence-Based Mental Health 18:40–46.

Caldwell DM, Ades AE, Higgins JP. 2005. Simultaneous Comparison of Multiple Treatments: Combining Direct and Indirect Evidence. BMJ 331: 897–900.

Cipriani A, Higgins JP, Geddes JR, Salanti G. 2013. Conceptual and Technical Challenges in Network Meta-Analysis. Ann Intern Med. 159: 130–37.

Salanti G. 2012. Indirect and Mixed-Treatment Comparison, Network, or Multiple-Treatments Meta-Analysis: Many Names, Many Benefits, Many Concerns for the next Generation Evidence Synthesis Tool. Res Synth Meth 3 (2): 80–97.

Chaimani A, Higgins JPT, Mavridis D, Spyridonos P, Salanti G. 2013. Graphical Tools for Network Meta-Analysis in STATA. PLoS.One. 8 (10): e76654.

Anna Chaimani, PhD

Anna Chaimani is a tenured Researcher at the Inserm METHODS Team – Sorbonne Paris Cité Epidemiology and Statistics Research Centre (UMR 1153), University of Paris. She is also a co-convenor of the Cochrane Statistical Methods group and of the Cochrane Comparing Multiple Interventions Methods group. She obtained her PhD in Epidemiology and Biostatistics in 2014 from the University of Ioannina in Greece and in 2016 she obtained a Chaire d'Excellence position from Université Sorbonne Paris Cité. Her research interests lie in the field of evidence synthesis with a particular focus on methodology about pairwise meta-analysis and network meta-analysis. She has worked on models for small-study effects in network meta-analysis, network meta-epidemiological models and methods for missing data. She also works on software development for meta-analysis and she is the author of the network graphs package in Stata.