Network meta-analysis synthesizes direct and indirect evidence in a network of trials that compare multiple interventions and has the potential to rank the competing treatments according to the studied outcome. Despite its usefulness network meta-analysis is often criticized for its complexity and for being accessible only to researchers with strong statistical and computational skills. The evaluation of the underlying model assumptions, the statistical technicalities and presentation of the results in a concise and understandable way are all challenging aspects in the network meta-analysis methodology. In this paper we aim to make the methodology accessible to non-statisticians by presenting and explaining a series of graphical tools via worked examples. To this end, we provide a set of STATA routines that can be easily employed to present the evidence base, evaluate the assumptions, fit the network meta-analysis model and interpret its results.

In view of the currently available evidence from randomized trials, we aimed to compare the collective safety and efficacy of transcatheter aortic valve implantation (TAVI) vs. surgical aortic valve replacement (SAVR) across the spectrum of risk and in important subgroups. Trials comparing TAVI vs. SAVR were identified through Medline, Embase, and Cochrane databases. The primary outcome was death from any cause at 2 years. We performed random-effects meta-analyses to combine the available evidence and to evaluate the effect in different subgroups. This systematic review and meta-analysis is registered with PROSPERO (CRD42016037273). We identified four eligible trials including 3806 participants, who were randomly assigned to undergo TAVI (n = 1898) or SAVR (n = 1908). For the primary outcome of death from any cause, TAVI when compared with SAVR was associated with a significant 13% relative risk reduction [hazard ratio (95% CI): 0.87 (0.76–0.99); P = 0.038] with homogeneity across all trials irrespective of TAVI device (P_interaction = 0.306) and baseline risk (P_interaction = 0.610). In subgroup analyses, TAVI showed a robust survival benefit over SAVR for patients undergoing transfemoral access [0.80 (0.69–0.93); P = 0.004], but not transthoracic access [1.17 (0.88–1.56); P = 0.293] (P_interaction = 0.024) and in female [0.68 (0.50–0.91); P = 0.010], but not male patients [0.99 (0.77–1.28); P = 0.952] (P_interaction = 0.050). Secondary outcomes of kidney injury, new-onset atrial fibrillation, and major bleeding favoured TAVI, while major vascular complications, incidence of permanent pacemaker implantation, and paravalvular regurgitation favoured SAVR. Compared with SAVR, TAVI is associated with a significant survival benefit throughout 2 years of follow-up. Importantly, this superiority is observed irrespective of the TAVI device across the spectrum of intermediate and high-risk patients, and is particularly pronounced among patients undergoing transfemoral TAVI and in females.

How to assess publication bias: funnel plot, trim-and-fill method and selection models doi:10.1136/eb-2013-101699 This new section of the Journal is aimed at providing the essen-tial information readers should know about the topics that are addressed in the “Statistics in practice ” paper published in the same issue of the journal. This stand-alone section has to be seen as an articulated summary of the main notions clinicians have to know about some basic concepts in statistics, which may be useful for their evidence based practice. After going through these notes, readers are encouraged to read the “Statistics in practice ” articles. Of course, we welcome any feed-back from you (via email or Twitter) about this