Network meta-analysis: drawing conclusions regarding trials of psychosocial interventions for bipolar disorder.

Network meta-analysis (NMA) is a statistical technique for making direct and indirect comparisons between different treatment and control groups. Despite its many advantages, NMA may be misleading when evaluating networks that are disconnected, inconsistent or of low reliability and validity. We review how well the analysis of trials of adjunctive psychosocial treatment in bipolar disorder is served by NMA. We conclude with recommendations for future treatment trials in bipolar disorder and guidelines for NMAs.
Competing Interests: Declaration of interestA.C. and D.J.M. are currently carrying out a network meta-analysis of psychological interventions in bipolar disorder (CRD42015016085). D.J.M. receives grant funding from the National Institute of Mental Health and private funding from the Deutsch Foundation, Kayne Foundation, Dan and Diana Attias Foundation, and Max Gray Foundation. A.C. is supported by the National Institute for Health Research (NIHR) Oxford Cognitive Health Clinical Research Facility. G.M.G is a NIHR senior investigator, holds a grant from the Wellcome Trust, holds shares in P1vital and has served as consultant, advisor or continuing medical education speaker for Angelini, Compass pathways, MSD, Lundbeck (/Otsuka or/Takeda), Medscape, P1vital, Pfizer, Servier and Shire. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health.
(© The Royal College of Psychiatrists 2017.)