Standard futility analyses designed for a proportional hazards setting may have serious drawbacks when non-proportional hazards are present. One important type of non-proportional hazards occurs when the treatment effect is delayed. That is, there is little or no early treatment effect but a substantial later effect.
Methods
We define optimality criteria for futility analyses in this setting and propose simple search procedures for deriving such rules in practice.
Results
We demonstrate the advantages of the optimal rules over commonly used rules in reducing the average number of events, the average sample size, or the average study duration under the null hypothesis with minimal power loss under the alternative hypothesis.
Conclusion
Optimal futility rules can be derived for a non-proportional hazards setting that control the loss of power under the alternative hypothesis while maximizing the gain in early stopping under the null hypothesis.
ChenTT.Statistical issues and challenges in immuno-oncology. J Immunother Cancer2013; 1: 18–19.
2.
HoeringADurieBWangH, et al. End points and statistical considerations in immuno-oncology trials: impact on multiple myeloma. Future Oncol2017; 13(13): 1181–1193.
3.
AnanthakrishnanRGreenSPrevitaliA, et al. Critical review of oncology clinical trial design under non-proportional hazards. Crit Rev Oncol Hematol2021; 162: 103350.
4.
LiBSuLGaoJ, et al. A group sequential design and sample size estimation for an immunotherapy trial with a delayed treatment effect. Stat Methods Med Res2021; 30(3): 904–915.
5.
MukhopadhyayPHuangWMetcalfeP, et al. Statistical and practical considerations in designing of immuno-oncology trials. J Biopharm Stat2020; 30(6): 1130–1146.
6.
FlemingTRHarringtonDP.A class of hypothesis tests for one and two sample censored survival data. Commun Stat Theory Method1981; 10(8): 763–794.
7.
RoystonPParmarMKB. A simulation study comparing the power of nine tests of the treatment effect in randomized controlled trials with a time-to-event outcome. Trials2020; 21(1): 1–17.
8.
KarrisonTG.Versatile tests for comparing survival curves based on weighted log-rank statistics. Stata J2016; 16(3): 678–690.
9.
RoychoudhurySAndersonKMYeJ, et al. Robust design and analysis of clinical trials with non-proportional hazards: a straw man guidance from a cross-pharma working group. Stat Biopharm Res2021; 15(2): 280–294.
10.
GhoshPRistlRKönigF, et al. Robust group sequential designs for trials with survival endpoints and delayed response. Biom J2022; 64(2): 343–360.
11.
DemetsDL.Futility approaches to interim monitoring by data monitoring committees. Clin Trials2006; 3(6): 522–529.
12.
SnapinnSChenMGJiangQ, et al. Assessment of futility in clinical trials. Pharmaceut Stat2006; 5(4): 273–281.
13.
HePLaiTLLiaoOY.Futility stopping in clinical trials. Stat Interface2012; 5(4): 415–423.
14.
Gordon LanKKSimonRHalperinM.Stochastically curtailed tests in long–term clinical trials. Sequen Anal1982; 1(3): 2071982–2071219.
15.
HögelJKronM.Comparison of conditional power criteria for early termination of clinical trials. Comput Stat Data Anal2004; 46(2): 377–395.
16.
LachinJM.A review of methods for futility stopping based on conditional power. Stat Med2005; 24(18): 2747–2764.
17.
ZhangYClarkeWR.A flexible futility monitoring method with time-varying conditional power boundary. Clin Trials2010; 7(3): 209–218.
18.
DmitrienkoAWangMD.Bayesian predictive approach to interim monitoring in clinical trials. Stat Med2006; 25(13): 2178–2195.
19.
SavilleBRConnorJTAyersGD, et al. The utility of Bayesian predictive probabilities for interim monitoring of clinical trials. Clin Trials2014; 11(4): 485–493.
20.
ThomasRFleming DavidPHarrington PeterC, et al. Designs for group sequential tests. Control Clin Trial1984; 5(4): 348–361.
21.
PampallonaSTsiatisAA.Group sequential designs for one-sided and two-sided hypothesis testing with provision for early stopping in favor of the null hypothesis. J Stat Plan Infer1994; 42(1–2): 19–35.
22.
AndersonJRHighR.Alternatives to the standard Fleming, Harrington, and O’Brien futility boundary. Clin Trials2011; 8(3): 270–276.
23.
WieandSSchroederGO’FallonJR.Stopping when the experimental regimen does not appear to help. Stat Med1994; 13(13–14): 1453–1458.
24.
WhiteheadJMatsushitaT.Stopping clinical trials because of treatment ineffectiveness: a comparison of a futility design with a method of stochastic curtailment. Stat Med2003; 22(5): 677–687.
25.
JiménezJLStalbovskayaVJonesB.Properties of the weighted log-rank test in the design of confirmatory studies with delayed effects. Pharma Stat2019; 18(3): 287–303.
26.
RistlRBallariniNMGötteH, et al. Delayed treatment effects, treatment switching and heterogeneous patient populations: how to design and analyze RCTs in oncology. Pharm Stat2021; 20(1): 129–145.
27.
OhrnCF.Group sequential and adaptive methods: topics with applications to clinical trials. PhD Thesis, University of Bath, Bath, 2011.
SchülerSKieserMRauchG.Choice of futility boundaries for group sequential designs with two endpoints. BMC Med Res Methodol2017; 17(1): 1–10.
30.
XiDGalloPOhlssenD.On the optimal timing of futility interim analyses. Stat Biopharm Res2017; 9(3): 293–301.
31.
DengQLuX.Choosing timing and boundary for futility analysis based on cost-effectiveness assessment. Stat Biopharm Res2018; 10(2): 104–111.
32.
LiXHerrmannCRauchG.Optimality criteria for futility stopping boundaries for group sequential designs with a continuous endpoint. BMC Med Res Methodol2020; 20(1): 1–8.
33.
SchoenfeldD.The asymptotic properties of nonparametric tests for comparing survival distributions. Biometrika1981; 68(1): 316–319.
34.
LachinJMFoulkesMA.Evaluation of sample size and power for analyses of survival with allowance for nonuniform patient entry, losses to follow-up, noncompliance, and stratification. Biometrics1986; 42(3): 507–519.
35.
SchemperMWakounigSHeinzeG.The estimation of average hazard ratios by weighted Cox regression. Stat Med2009; 28(19): 2473–2489.
36.
YuCHuangXNianH, et al. A weighted log-rank test and associated effect estimator for cancer trials with delayed treatment effect. Pharm Stat2021; 20(3): 528–550.
37.
KalbfleischJDPrenticeRL.Estimation of the average hazard ratio. Biometrika1981; 68(1): 105–112.
38.
JennisonCTurnbullBW.Group sequential methods with applications to clinical trials. Boca Raton, FL: CRC Press, 1999.
39.
FreidlinBKornEL.A comment on futility monitoring. Control Clin Trials2002; 23(4): 355–366.
40.
TsiatisAA.Repeated significance testing for a general class of statistics used in censored survival analysis. J Am Stat Assoc1982; 77(380): 855–861.
41.
KornELFreidlinB.Interim futility monitoring assessing immune therapies with a potentially delayed treatment effect. J Clin Oncol2018; 36(23): 2444–2449.
FangLSuZ.A hybrid approach to predicting events in clinical trials with time-to-event outcomes. Contemp Clin Trials2011; 32(5): 755–759.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
