Sample size re-estimation without un-blinding for time-to-event outcomes in oncology clinical trials

Abstract

Sample size re-estimation is essential in oncology studies. However, the use of blinded sample size reassessment for survival data has been rarely reported. Based on the density function of the exponential distribution, an expectation-maximization (EM) algorithm of the hazard ratio was derived, and several simulation studies were used to verify its applications. The method had obvious variation in the hazard ratio estimates and overestimation for the relatively small hazard ratios. Our studies showed that the stability of the EM estimation results directly correlated with the sample size, the convergence of the EM algorithm was impacted by the initial values, and a balanced design produced the best estimates. No reliable blinded sample size re-estimation inference can be made in our studies, but the results provide useful information to steer the practitioners in this field from repeating the same endeavor.

Keywords

oncology study / clinical trial / sample size re-estimation / expectation-maximization algorithm

References

[1] ICH. ICH Harmonised Tripartite Guideline. Statistical principles for clinical trials. International Conference on Harmonisation E9 Expert Working Group[J]. Stat Med, 1999, 18(15): 1905–1942. 

[2] Posch M, Bauer  P. Interim analysis and sample size reassessment[J]. Biometrics, 2000, 56(4): 1170–1176.

[3] Proschan MA. Sample size re-estimation in clinical trials[J]. Biom J, 2009, 51(2): 348–357.

[4] CPMP. Biostatistical methodology in clinical trials in applications for marketing authorizations for medicinal products. CPMP Working Party on Efficacy of Medicinal Products Note for Guidance III/3630/92-EN[J]. Stat Med, 1995, 14(15): 1659–1682.

[5] EMEA/CHMP.Reflection Paper on Methodological Issues in Confirmatory Clinical Trials with Flexible Design and Analysis Plan[J]. Available online at http://wwwemeaeuint. 2006.

[6] Gould AL, Shih  WJ. Sample size re-estimation without unblinding for normally distributed outcomes with unknown variance[J]. Commun Stat Theory Methods, 1992, 21(10): 2833–2853

[7] Friede T, Kieser  M. Blinded sample size reassessment in non-inferiority and equivalence trials[J]. Stat Med, 2003, 22(6): 995–1007.

[8] Kieser M, Friede  T. Blinded sample size Reestimation in multiarmed clinical trials[J]. Drug Inf J, 2000, 34(2): 455–460.

[9] Friede T, Schmidli  H. Blinded sample size reestimation with negative binomial counts in superiority and non-inferiority trials[J]. Methods Inf Med, 2010, 49(6): 618–624.

[10] Friede T, Schmidli  H. Blinded sample size reestimation with count data: methods and applications in multiple sclerosis[J]. Stat Med, 2010, 29(10): 1145–1156

[11] Schoenfeld DA. Sample-size formula for the proportional-hazards regression model[J]. Biometrics, 1983, 39(2): 499–503.

[12] Chang M. Adaptive design theory and implementation using SAS and R[M]. Boca Raton: Chapman & Hall/CRC, 2008. 

[13] Desu MM, Raghavarao  D. Sample size methodology[M]. Boston: Academic Press; 1990. 

[14] Bain LJ, Engelhardt  M. Statistical analysis of reliability and life-testing models: theory and methods[M]. 2nd ed. New York: M. Dekker; 1991.

[15] Birkett MA, Day  SJ. Internal pilot studies for estimating sample size[J]. Stat Med, 1994, 13(23-24): 2455–2463.

[16] Xie J, Quan  H, Zhang J. Blinded assessment of treatment effects for survival endpoint in an ongoing trial[J]. Pharm Stat, 2012, 11(3): 204–213.

[17] Friede T, Kieser  M. Sample size recalculation in internal pilot study designs: a review[J]. Biom J, 2006, 48(4): 537–555.

[18] Kieser M, Friede  T. Simple procedures for blinded sample size adjustment that do not affect the type I error rate[J]. Stat Med, 2003, 22(23): 3571–3581.

Acknowledgments

This research was supported by the National Natural Science Foundation of China (81273184), and the National Natural Science Foundation of China Grant for Young Scientists (81302512). We would like to thank the referees for their comments that greatly helped us improve the manuscript.

RIGHTS & PERMISSIONS

2017 2017 by the Journal of Biomedical Research. All rights reserved