Living network meta-analysis compared with pairwise meta-analysis in comparative effectiveness research: empirical studyBMJ 2018; 360 doi: https://doi.org/10.1136/bmj.k585 (Published 28 February 2018) Cite this as: BMJ 2018;360:k585
All rapid responses
Re: Living network meta-analysis compared with pairwise meta-analysis in comparative effectiveness research: empirical study
Early stop of clinical trials for benefit has been considered as a risk for overstimating clinical benefits. Accordingly, strict stopping rules requiring p values far lower than the conventional p<0.05 are commonly used. However, early stopped trials usually report the nominal p value of the comparison, with no correction for the multiple analysis implicit in interim analysis.
Living network meta-analysis are a way of continuous interim analysis. It is thus hardly surprising that living-network meta-analysis provide an early 'demonstration' of clinical benefit. Should we rely on living network meta-analysis to provide an estimation of treatment benefit? Do we need stricter 'stopping rules' for living network meta-analysis as compared to conventional meta-analysis as we do for interim analysis of conventional clinical trials?
A more rigorous threshold for stopping early for benefit has been suggested for clinical trials. Should this also apply to living network meta-analysis ?
Tharmanathan P, Calvert M, Hampton J, Freemantle N. The use of interim data
and Data Monitoring Committee recommendations in randomized controlled trial
reports: frequency, implications and potential sources of bias. BMC Med Res
Methodol. 2008 Mar 20;8:12. doi: 10.1186/1471-2288-8-12. Review. PubMed PMID:
18366697; PubMed Central PMCID: PMC2279143.
Montori VM, Devereaux PJ, Adhikari NK, Burns KE, Eggert CH, Briel M, Lacchetti
C, Leung TW, Darling E, Bryant DM, Bucher HC, Schünemann HJ, Meade MO, Cook DJ,
Erwin PJ, Sood A, Sood R, Lo B, Thompson CA, Zhou Q, Mills E, Guyatt GH.
Randomized trials stopped early for benefit: a systematic review. JAMA. 2005 Nov
2;294(17):2203-9. Review. PubMed PMID: 16264162.
Randomized trials addressing a similar question are commonly published after a trial stopped early for benefit.
Murad MH, Guyatt GH, Domecq JP, Vernooij RWM, Erwin PJ, Meerpohl JJ, Prutsky GJ, Akl EA, Mueller K, Bassler D, Schandelmaier S, Walter SD, Busse JW, Kasenda B, Pagano G, Pardo-Hernandez H, Montori VM, Wang Z, Briel M.
J Clin Epidemiol. 2017 Feb;82:12-19. doi: 10.1016/j.jclinepi.2016.10.006. Epub 2016 Nov 8. Review.
Competing interests: No competing interests