The relative ranking of competing treatments is a key output of network meta-analysis (NMA), yet it has been criticized for overinterpretation and for overemphasizing small differences in treatment effects.
The presenter introduced a new probabilistic framework for estimating treatment hierarchies in NMA based on a clinically relevant treatment-choice criterion (TCC).
The approach estimates a latent “ability” parameter that reflects each treatment’s propensity to produce clinically important and beneficial effects, according to the TCC, when compared to the rest of the treatments in the network. To facilitate implementation, the R package mtrank was developed. The proposed method offers an alternative to existing ranking approaches and is understood to be the first to explicitly and quantitatively address treatment hierarchy questions using a predefined TCC.
This Learning Live webinar was intended for participants with a basic understanding of biostatistics and prior experience in network meta-analysis. It was also aimed at health professionals, policymakers, and epidemiologists interested in integrating NMA methods and treatment ranking into decision-making.
The session was delivered in July 2026 and below you will find the recording with the accompanying slides to download [PDF].
Presenter Bio
Dr. Theodoros Evrenoglou is the Group Leader of the Meta-Analysis Group at the Institute of Medical Biometry and Statistics in Freiburg, Germany. He holds a PhD in Biostatistics and is a co-convenor of the Cochrane Statistical Methods Group. His scientific interests include the development of statistical methods for evidence synthesis, the creation of statistical software, and the application of statistical methods in clinical practice.
