ESMARConf2023: {ROB-MEN} tutorial

Описание: Presenter: Virginia Chiocchia
Authors: Chiocchia, Virginia; Holloway, Alexander; Salanti, Georgia
Session: Tutorials 2
Title: ROB-MEN: Risk Of Bias due to Missing Evidence in Network meta-analysis
Abstract: The ROB-MEN (Risk Of Bias due to Missing Evidence in Network meta-analysis) tool was recently proposed as part of the CINeMA (Confidence In Network Meta-Analysis) framework to fill the methodological gap concerning the reporting bias domain. ROB-MEN first evaluates the risk of bias due to missing evidence in each pairwise comparison, performing a within-study assessment of bias (selective outcome reporting bias) and an across-study assessment of bias (publication bias). The tool then combines the overall judgements about the risk of bias due to missing evidence in pairwise comparisons with the percentage contribution of direct comparisons on the network meta-analysis (NMA) estimates, the presence or absence of small-study effects, as evaluated by network meta-regression, and any bias from unobserved comparisons. Finally, a level of “low risk”, “some concerns” or “high risk” for the bias due to missing evidence is assigned to each NMA estimate, which is the final output of ROB-MEN. The ROB-MEN web application (https://cinema.ispm.unibe.ch/rob-men) was developed to facilitate the ROB-MEN assessment process. The app runs the required analysis in the background, semi-automates some of the steps and built-in rules to assign the overall risk of bias level for the pairwise comparisons and network estimates, and produces the output tables. We present the newest version of the ROB-MEN app and demonstrate its functionality using a published network meta-analysis of antidepressants as an example. We also show how to integrate the output from the ROB-MEN tool in the updated reporting bias domain of the CINeMA web application (https://cinema.ispm.unibe.ch/).
GitHub repository: https://github.com/esm-ispm-unibe-ch/...