Handling missing within-study correlations in the evaluation of surrogate endpoints.
Bayesian hierarchical modeling
meta-regression
missing-data
surrogate endpoint
Journal
Statistics in medicine
ISSN: 1097-0258
Titre abrégé: Stat Med
Pays: England
ID NLM: 8215016
Informations de publication
Date de publication:
20 Nov 2023
20 Nov 2023
Historique:
revised:
16
07
2023
received:
12
07
2022
accepted:
14
08
2023
pmc-release:
20
11
2024
medline:
1
11
2023
pubmed:
17
10
2023
entrez:
17
10
2023
Statut:
ppublish
Résumé
Rigorous evaluation of surrogate endpoints is performed in a trial-level analysis in which the strength of the association between treatment effects on the clinical and surrogate endpoints is quantified across a collection of previously conducted trials. To reduce bias in measures of the performance of the surrogate, the statistical model must account for the sampling error in each trial's estimated treatment effects and their potential correlation. Unfortunately, these within-study correlations can be difficult to obtain, especially for meta-analysis of published trial results where individual patient data is not available. As such, these terms are frequently partially or completely missing in the analysis. We show that improper handling of these missing terms can meaningfully alter the perceived quality of the surrogate and we introduce novel strategies to handle the missingness.
Identifiants
pubmed: 37845797
doi: 10.1002/sim.9886
pmc: PMC10704210
mid: NIHMS1942015
doi:
Substances chimiques
Biomarkers
0
Types de publication
Meta-Analysis
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
4738-4762Subventions
Organisme : NCATS NIH HHS
ID : UL1 TR002538
Pays : United States
Informations de copyright
© 2023 The Authors. Statistics in Medicine published by John Wiley & Sons Ltd.
Références
J Am Soc Nephrol. 2019 Sep;30(9):1735-1745
pubmed: 31292197
Diabetes Obes Metab. 2016 Jan;18(1):64-71
pubmed: 26434564
Lancet Diabetes Endocrinol. 2019 Feb;7(2):128-139
pubmed: 30635226
Stat Methods Med Res. 2017 Oct;26(5):2287-2318
pubmed: 26271918
Stat Med. 1997 Sep 15;16(17):1965-82
pubmed: 9304767
Res Synth Methods. 2015 Jun;6(2):157-74
pubmed: 26099484
Stat Med. 2019 Sep 30;38(22):4218-4239
pubmed: 31338848
Radiother Oncol. 2015 Aug;116(2):157-66
pubmed: 26243677
Stat Med. 2013 Mar 30;32(7):1191-205
pubmed: 23208849
Ann Intern Med. 2009 May 5;150(9):604-12
pubmed: 19414839
Lancet Oncol. 2021 Mar;22(3):402-410
pubmed: 33662287
Eur J Surg Oncol. 2017 Oct;43(10):1956-1961
pubmed: 28747249
Stat Med. 2020 Apr 15;39(8):1103-1124
pubmed: 31990083
Am J Kidney Dis. 1996 Jun;27(6):765-75
pubmed: 8651239
J Clin Oncol. 2008 Apr 20;26(12):1987-92
pubmed: 18421050
Stat Med. 2019 Aug 15;38(18):3322-3341
pubmed: 31131475
Stat Med. 2016 Mar 30;35(7):1063-89
pubmed: 26530518
Stat Med. 2005 Jan 30;24(2):163-82
pubmed: 15515150
Am J Kidney Dis. 2020 Jan;75(1):84-104
pubmed: 31473020
Biom J. 2016 Jan;58(1):104-32
pubmed: 25682941
J Am Soc Nephrol. 2006 Nov;17(11):2974-84
pubmed: 17035611
Stat Med. 2008 Feb 28;27(5):670-86
pubmed: 17492826
Ann Oncol. 2016 Jun;27(6):1029-1034
pubmed: 26961151
BMC Med Res Methodol. 2007 Jan 12;7:3
pubmed: 17222330
J Intern Med. 2003 Sep;254(3):216-24
pubmed: 12930230
Stat Med. 2013 Sep 30;32(22):3926-43
pubmed: 23630081
EClinicalMedicine. 2020 Apr 13;21:100332
pubmed: 32382717