Delayed treatment effects, treatment switching and heterogeneous patient populations: How to design and analyze RCTs in oncology.
Journal
Pharmaceutical statistics
ISSN: 1539-1612
Titre abrégé: Pharm Stat
Pays: England
ID NLM: 101201192
Informations de publication
Date de publication:
01 2021
01 2021
Historique:
received:
23
09
2019
revised:
16
04
2020
accepted:
16
07
2020
pubmed:
25
8
2020
medline:
26
11
2021
entrez:
25
8
2020
Statut:
ppublish
Résumé
In the analysis of survival times, the logrank test and the Cox model have been established as key tools, which do not require specific distributional assumptions. Under the assumption of proportional hazards, they are efficient and their results can be interpreted unambiguously. However, delayed treatment effects, disease progression, treatment switchers or the presence of subgroups with differential treatment effects may challenge the assumption of proportional hazards. In practice, weighted logrank tests emphasizing either early, intermediate or late event times via an appropriate weighting function may be used to accommodate for an expected pattern of non-proportionality. We model these sources of non-proportional hazards via a mixture of survival functions with piecewise constant hazard. The model is then applied to study the power of unweighted and weighted log-rank tests, as well as maximum tests allowing different time dependent weights. Simulation results suggest a robust performance of maximum tests across different scenarios, with little loss in power compared to the most powerful among the considered weighting schemes and huge power gain compared to unfavorable weights. The actual sources of non-proportional hazards are not obvious from resulting populationwise survival functions, highlighting the importance of detailed simulations in the planning phase of a trial when assuming non-proportional hazards.We provide the required tools in a software package, allowing to model data generating processes under complex non-proportional hazard scenarios, to simulate data from these models and to perform the weighted logrank tests.
Identifiants
pubmed: 32830428
doi: 10.1002/pst.2062
pmc: PMC7818232
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
129-145Informations de copyright
© 2020 The Authors. Pharmaceutical Statistics published by John Wiley & Sons Ltd.
Références
Biom J. 2020 May;62(3):742-750
pubmed: 30623465
BMC Med Res Methodol. 2016 Feb 01;16:12
pubmed: 26830911
J Clin Oncol. 2018 Aug 10;36(23):2444-2449
pubmed: 29949395
Cochrane Database Syst Rev. 2017 Jun 27;6:CD007047
pubmed: 28654140
Clin Cancer Res. 2017 Sep 1;23(17):4959-4969
pubmed: 28864724
N Engl J Med. 2018 May 31;378(22):2078-2092
pubmed: 29658856
Stat Methods Med Res. 2017 Apr;26(2):724-751
pubmed: 25416688
Pharm Stat. 2021 Jan;20(1):129-145
pubmed: 32830428
Lifetime Data Anal. 2015 Apr;21(2):218-40
pubmed: 25053470
J Immunother Cancer. 2013 Oct 21;1:18
pubmed: 24829754
Pharm Stat. 2016 Sep;15(5):412-9
pubmed: 27353855
Pharm Stat. 2014 Mar-Apr;13(2):128-35
pubmed: 24497461
Stat Med. 2009 Aug 30;28(19):2473-89
pubmed: 19472308
Methods Inf Med. 2018 May;57(3):89-100
pubmed: 29719915
Vaccine. 2007 Sep 27;25 Suppl 2:B97-B109
pubmed: 17916465
Pharm Stat. 2018 Sep;17(5):541-554
pubmed: 30058101
Pharm Stat. 2019 May;18(3):287-303
pubmed: 30592138
BMC Med Res Methodol. 2013 Dec 07;13:152
pubmed: 24314264
Stat Methods Med Res. 2019 Aug;28(8):2475-2493
pubmed: 29940824
J Hyg (Lond). 1949 Jun;47(2):188
pubmed: 15406758
Stat Med. 2019 Jan 30;38(2):192-209
pubmed: 30281165
Proc Natl Acad Sci U S A. 2019 Jan 22;116(4):1195-1200
pubmed: 30610179
Lifetime Data Anal. 2017 Jul;23(3):339-352
pubmed: 26969674
PLoS One. 2015 Jan 23;10(1):e0116774
pubmed: 25615624