Indirect and mixed‐treatment comparison, network, or multiple‐treatments meta‐analysis: many names, many benefits, many concerns for the next generation evidence synthesis tool

By Georgia Salanti. Research Synthesis Methods, 2012

1,532 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/36d1d811be1423c8449fbfd8fabda091293c5fcf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

A graphical tool for locating inconsistency in network meta-analyses (2013, background): “References [1-4] give an overview of the recent methodological development.”
Visualizing Assumptions and Results in Network Meta-analysis: The Network Graphs Package (2015, background): “Sometimes, diﬀerences in comparisons can be an indication of potential violation of the assumption underlying network meta-analysis (Jansen and Naci 2013; Salanti 2012).”
Scholarship, Research, and Creative Work at Bryn Mawr College Scholarship, Research, and Creative Work at Bryn Mawr College (background): “Even the "faults," such as they are, are common to the majority of survey books on Greek sculp-ture, and therefore not specifically imputable to this particular author, who often tries to express original ideas and positions of his own.”
Evaluating the Quality of Evidence from a Network Meta-Analysis (2014, methodology): “by using directed acyclic graphs see [18]) can also be employed (for a review see [19]).”
Ranking treatments in frequentist network meta-analysis works without resampling methods (2015, neutral): “Salanti [1] criticized that ‘Presentation of results on the basis of the statistical significance of pairwise comparisons, as suggested by Fadda et al.”
Conceptual and Technical Challenges in Network Meta-analysis (2013, background): “This assumption has been described alongside several terms in the literature, including similarity (14, 15), transitivity (16, 17), consistency (4), and coherence (18).”
Network Meta-Analysis Using R: A Review of Currently Available Automated Packages (2014, background): “For the results of NMA to be valid, the network is assumed to maintain transitivity (potential modifiers of treatment effects are similarly distributed across trials) and consistency (indirect effect estimates are consistent with that of direct effects), while interpretation of the treatment effects”
Network Meta-Analysis: An Introduction for Clinicians (2016, methodology): “Many NMAs assume a common heterogeneity when there are only a small number of studies per direct comparison, since the estimation of heterogeneity can be more powerful by borrowing strength across the comparisons [6].”
GetReal in network meta‐analysis: a review of the methodology (2016, methodology): “An effect modifier might differ across studies of the same comparison (e.g., mean participant age might be different across the AC trials), but if it has a similar distribution across comparisons (AC and BC), the transitivity assumption may still be valid (Salanti, 2012).”
Graphical Tools for Network Meta-Analysis in STATA (2013, methodology): “Rather than weighting edges by amount of information, the use of weighted edges according to the distribution of study-specific variables may assist in evaluation of the transitivity assumption [17,12].”