Network meta-analysis and random walks.
electrical networks
evidence flow
network meta-analysis
proportion contribution
random walks
statistical mechanics
Journal
Statistics in medicine
ISSN: 1097-0258
Titre abrégé: Stat Med
Pays: England
ID NLM: 8215016
Informations de publication
Date de publication:
30 05 2022
30 05 2022
Historique:
revised:
06
12
2021
received:
17
06
2021
accepted:
20
01
2022
pubmed:
17
3
2022
medline:
22
4
2022
entrez:
16
3
2022
Statut:
ppublish
Résumé
Network meta-analysis (NMA) is a central tool for evidence synthesis in clinical research. The results of an NMA depend critically on the quality of evidence being pooled. In assessing the validity of an NMA, it is therefore important to know the proportion contributions of each direct treatment comparison to each network treatment effect. The construction of proportion contributions is based on the observation that each row of the hat matrix represents a so-called "evidence flow network" for each treatment comparison. However, the existing algorithm used to calculate these values is associated with ambiguity according to the selection of paths. In this article, we present a novel analogy between NMA and random walks. We use this analogy to derive closed-form expressions for the proportion contributions. A random walk on a graph is a stochastic process that describes a succession of random "hops" between vertices which are connected by an edge. The weight of an edge relates to the probability that the walker moves along that edge. We use the graph representation of NMA to construct the transition matrix for a random walk on the network of evidence. We show that the net number of times a walker crosses each edge of the network is related to the evidence flow network. By then defining a random walk on the directed evidence flow network, we derive analytically the matrix of proportion contributions. The random-walk approach has none of the associated ambiguity of the existing algorithm.
Identifiants
pubmed: 35293631
doi: 10.1002/sim.9346
pmc: PMC9311228
doi:
Types de publication
Journal Article
Meta-Analysis
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
2091-2114Subventions
Organisme : Swiss National Science Foundation
ID : P400PM_186723
Pays : Switzerland
Informations de copyright
© 2022 The Authors. Statistics in Medicine published by John Wiley & Sons Ltd.
Références
Stat Med. 2014 Nov 10;33(25):4353-69
pubmed: 24942211
Clin Epidemiol. 2014 Dec 03;6:451-60
pubmed: 25506247
BMC Med. 2021 Nov 23;19(1):304
pubmed: 34809639
Res Synth Methods. 2011 Mar;2(1):43-60
pubmed: 26061599
Stat Med. 2004 Oct 30;23(20):3105-24
pubmed: 15449338
Biom J. 2020 May;62(3):808-821
pubmed: 31021449
Res Synth Methods. 2021 May;12(3):316-332
pubmed: 32935913
J Clin Epidemiol. 2018 Aug;100:122-129
pubmed: 29432861
Stat Med. 2010 May 30;29(12):1282-97
pubmed: 19408255
BMC Fam Pract. 2011 Nov 15;12:127
pubmed: 22085705
Cochrane Database Syst Rev. 2005 Oct 19;(4):CD004618
pubmed: 16235370
Ann Intern Med. 2008 Apr 1;148(7):544-53
pubmed: 18378949
Stat Med. 2002 Aug 30;21(16):2313-24
pubmed: 12210616
Stat Med. 1996 Dec 30;15(24):2733-49
pubmed: 8981683
BMJ. 2021 Mar 29;372:n71
pubmed: 33782057
Stat Med. 2022 May 30;41(12):2091-2114
pubmed: 35293631
BMC Med Res Methodol. 2013 Mar 09;13:35
pubmed: 23496991
Res Synth Methods. 2016 Sep;7(3):236-63
pubmed: 26754852
F1000Res. 2018 May 18;7:610
pubmed: 30338058
Stat Methods Med Res. 2013 Apr;22(2):169-89
pubmed: 22218368
Res Synth Methods. 2012 Jun;3(2):80-97
pubmed: 26062083
Stat Med. 2013 Dec 30;32(30):5414-29
pubmed: 24123165
PLoS One. 2019 Feb 20;14(2):e0212650
pubmed: 30785955
J R Soc Interface. 2008 Aug 6;5(25):813-34
pubmed: 18426776
Stat Methods Med Res. 2008 Jun;17(3):279-301
pubmed: 17925316
PLoS Med. 2020 Apr 3;17(4):e1003082
pubmed: 32243458
Res Synth Methods. 2012 Dec;3(4):312-24
pubmed: 26053424
BMC Med Res Methodol. 2015 Jul 31;15:58
pubmed: 26227148
Phys Rev Lett. 2004 Mar 19;92(11):118701
pubmed: 15089179