Risk Of Bias due to Missing Evidence in Network meta-analysis

ROB-MEN is a web-application that simplifies the evaluation of risk of bias due to missing evidence (i.e. evidence missing due to unpublished studies and/or selective outcome reporting) in the estimates from network meta-analysis. It is part of the CINeMA (Confidence in Network Meta-Analysis) framework.

Instructions

See the ROB-MEN tutorial article for more details

ROB-MEN requires data to be uploaded as a .csv file in long format, where each row contains one treatment arm. All studies identified in the systematic review, including those not reporting the outcome of interest, should be included in the dataset. The long format data file should contain five columns (for binary data) or six columns (for continuous data) labelled as follows:

  • Column id containing the study identifier, starting from 1, then 2, 3, 4... etc.
  • Column study containing the name (e.g. author, year) of the study.
  • Column t containing the treatment code used in each arm of the study.
  • Column n containing the number of participants in each arm of the study.
For binary data:
  • Column r containing the number of participants with the outcome of interest in each arm of the study.
For continuous data:
  • Column mean containing the mean value of the outcome in each arm of the study.
  • Column sd containing the standard deviation of the outcome in each arm of the study.
For studies not reporting the outcome of interest, columns r, mean, and sd should use non-numeric values for missing data (e.g. empty cell, NA, *).

Demo data

Click here to download a demo dataset: a network of non-invasive diagnostic modalities for the detection of coronary artery disease (Siontis G C, et al. BMJ 2018; 360 :k504).


Documentation and training material

How to cite ROB-MEN

Methodology article: Chiocchia V, Nikolakopoulou A, Higgins JPT, Page MJ, Papakonstantinou T, Cipriani A, Furukawa TA, Siontis GCM, Egger M, Salanti G. ROB-MEN: a tool to assess risk of bias due to missing evidence in network meta-analysis. BMC Med (2021) 19:304
ROB-MEN tutorial article: Chiocchia V, Holloway A & Salanti, G. Semi-automated assessment of the risk of bias due to missing evidence in network meta-analysis: a guidance paper for the ROB-MEN web-application. BMC Med Res Methodol (2023) 23:223

For more information on how to use the ROB-MEN app, watch the Cochrane Learning Live webinar videos.


ROB-MEN is distributed under the GNU AGPL V3 license. The source code is available on GitHub.