Please use this identifier to cite or link to this item: http://hdl.handle.net/2381/40319
Title: Three-dimensional evidence network plot system: covariate imbalances and effects in network meta-analysis explored using a new software tool
Authors: Batson, Sarah
Score, Robert
Sutton, Alex J.
First Published: 24-Mar-2017
Publisher: Elsevier
Citation: Journal of Clinical Epidemiology, 2017, 86, pp. 182-195
Abstract: OBJECTIVES: The aim of the study was to develop the three-dimensional (3D) evidence network plot system-a novel web-based interactive 3D tool to facilitate the visualization and exploration of covariate distributions and imbalances across evidence networks for network meta-analysis (NMA). STUDY DESIGN AND SETTING: We developed the 3D evidence network plot system within an AngularJS environment using a third party JavaScript library (Three.js) to create the 3D element of the application. Data used to enable the creation of the 3D element for a particular topic are inputted via a Microsoft Excel template spreadsheet that has been specifically formatted to hold these data. We display and discuss the findings of applying the tool to two NMA examples considering multiple covariates. These two examples have been previously identified as having potentially important covariate effects and allow us to document the various features of the tool while illustrating how it can be used. RESULTS: The 3D evidence network plot system provides an immediate, intuitive, and accessible way to assess the similarity and differences between the values of covariates for individual studies within and between each treatment contrast in an evidence network. In this way, differences between the studies, which may invalidate the usual assumptions of an NMA, can be identified for further scrutiny. Hence, the tool facilitates NMA feasibility/validity assessments and aids in the interpretation of NMA results. CONCLUSION: The 3D evidence network plot system is the first tool designed specifically to visualize covariate distributions and imbalances across evidence networks in 3D. This will be of primary interest to systematic review and meta-analysis researchers and, more generally, those assessing the validity and robustness of an NMA to inform reimbursement decisions.
DOI Link: 10.1016/j.jclinepi.2017.03.008
ISSN: 0895-4356
eISSN: 1878-5921
Links: http://www.sciencedirect.com/science/article/pii/S0895435616308459?via%3Dihub
http://hdl.handle.net/2381/40319
Embargo on file until: 24-Mar-2018
Version: Post-print
Status: Peer-reviewed
Type: Journal Article
Rights: Copyright © Elsevier, 2017. After an embargo period this version of the paper will be an open-access article distributed under the terms of the Creative Commons Attribution-Non Commercial-No Derivatives License (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.
Description: The file associated with this record is under embargo until 12 months after publication, in accordance with the publisher's self-archiving policy. The full text may be available through the publisher links provided above.
Appears in Collections:Published Articles, Dept. of Health Sciences

Files in This Item:
File Description SizeFormat 
nma3dcov paper.pdfPost-review (final submitted author manuscript)394.62 kBAdobe PDFView/Open


Items in LRA are protected by copyright, with all rights reserved, unless otherwise indicated.