Traditionally, statistical methods for futility analysis are developed based on a single study. To establish a drug's effectiveness, usually at least two adequate and well-controlled studies need to demonstrate convincing evidence on its own. Therefore, in a standard clinical development program in chronic diseases, two independent studies are generally conducted for drug registration. This paper proposes a statistical method to combine interim data from two independent and similar studies for interim futility analysis and shows that the conditional power approach based on combined interim data has better operating characteristics compared to the approach based on single-trial interim data, even with small to moderate heterogeneity on the treatment effects between the two studies.
BuzdarAJonatWHowellA, et al.Anastrozole, a potent and selective aromatase inhibitor, versus megestrol acetate in postmenopausal women with advanced breast cancer: results of overview analysis of two phase III trials. J Clin Oncol1996; 14: 2000–2011.
4.
BuzdarAUJonatWHowellA, et al.Anastrozole versus megestrol acetate in the treatment of postmenopausal women with advanced breast carcinoma – results of a survival update based on a combined analysis of data from two mature phase III trials. Cancer1998; 83: 1142–1152.
5.
KastenbergDChasenRChoudharyC, et al.Efficacy and safety of sodium phosphate tablets compared with peg solution in colon cleansing: two identically designed, randomized, controlled, parallel group, multicenter phase iii trials. Gastrointestinal Endosc2001; 54: 705–713.
6.
de WitRHerrstedtJRapoportB, et al.The oral nk1 antagonist, aprepitant, given with standard antiemetics provides protection against nausea and vomiting over multiple cycles of cisplatin-based chemotherapy: a combined analysis of two randomised, placebo-controlled phase iii clinical trials. Eur J Cancer2004; 40: 403–410.
7.
Van-CutsemEHoffPMHarperP, et al.Oral capecitabine vs intravenous 5-fluorouracil and leucovorin: integrated efficacy data and novel analyses from two large, randomised, phase III trials. Br J Cancer2004; 90: 1190–1197.
8.
StaskinDRRosenbergMTSandPK, et al.Trospium chloride once-daily extended release is effective and well tolerated for the treatment of overactive bladder syndrome: an integrated analysis of two randomised, phase III trials. Int J Clin Practice2009; 63: 1715–1723.
9.
GinsbergDAOefeleinMGEllsworthPI. Once-daily administration of trospium chloride extended release provides 24-hr coverage of nocturnal and diurnal symptoms of overactive bladder: an integrated analysis of two phase III trials. Neurourol Urodynam2011; 30: 563–567.
10.
CaseiroMMNelsonMDiazRS, et al.Vicriviroc plus optimized background therapy for treatment-experienced subjects with ccr5 HIV-1 infection: final results of two randomized phase III trials. J Infect2012; 65: 326–335.
11.
FeldmanSRMathesonRBruceS, et al.Efficacy and safety of calcipotriene 0.005% foam for the treatment of plaque-type psoriasis results of two multicenter, randomized, double-blind, vehicle-controlled, phase III clinical trials. Am J Clin Dermatol2012; 13: 261–271.
12.
CelioLAgustoniFRicchiniF, et al.Palonosetron plus dexamethasone in highly emetogenic chemotherapy: pooled data from two phase III trials. Future Oncol2013; 9: 1451–1458.
13.
AdamsSGrayRJDemariaS, et al.Prognostic value of tumor-infiltrating lymphocytes in triple-negative breast cancers from two phase III randomized adjuvant breast cancer trials: Ecog 2197 and ecog 1199. J Clin Oncol2014; 32: 2959–2967.
14.
DieciMVMathieuMCGuarneriV. Prognostic and predictive value of tumor-infiltrating lymphocytes in two phase III randomized adjuvant breast cancer trials. Ann Oncol2015; 26: 1698–1704.
15.
CoudevilleLBaurinNL'AzouM, et al.Potential impact of dengue vaccination: Insights from two large-scale phase III trials with a tetravalent dengue vaccine. Vaccine2016; 34: 6426–6435.
16.
AksamitTBandelTJCriolloM, et al.The respire trials: two phase III, randomized, multicentre, placebo-controlled trials of ciprofloxacin dry powder for inhalation (ciprofloxacin dpi) in non-cystic fibrosis bronchiectasis. Contemporary Clin Trials2017; 58: 78–85.
17.
HoffmanRWMerrillJTAlarcon-RiquelmeMME, et al.Gene expression and pharmacodynamic changes in 1,760 systemic lupus erythematosus patients from two phase III trialsof baff blockade with tabalumab. Arthritis Rheumatol2017; 69: 643–654.
18.
ZhuLYaoBXiaHA, et al.Statistical monitoring of safety in clinical trials. Stat Biopharmaceut Res2016; 8: 88–105.
19.
SnapinnSChenMJiangQ, et al.Assessment of futility in clinical trials. Pharm Stat2006; 5: 273–281.
20.
LanKKGSimonRHalperinM. Stochastically curtailed tests in long-term clinical trials. Commun Stat – Sequential Analysis1982; 1: 207–219.
21.
SpiegelhalterDJAbramsKRMylesJP. Bayesian approaches to clinical trials and health-care evaluation, Chichester: Wiley, 2004.
22.
LachinJM. A review of methods for futility stopping based on conditional power. Stat Med2005; 24: 2747–2764.
23.
Proschan MA, Lan KKG and Wittes JT. Statistical monitoring of clinical trials: a unified approach. New York, NY: Springer, 2006.
24.
BradleyAP. The use of the area under the roc curve in the evaluation of machine learning algorithms. Pattern Recognit1997; 30: 1145–1159.
25.
FawcettT. An introduction to roc analysis. Pattern Recognit Lett2006; 27: 861–874.
26.
ZhouXHLinHZ. Semi-parametric maximum likelihood estimates for roc curves of continuous-scale tests. Stat Med2008; 27: 5271–5290.
27.
GalloPMaoLShihVH. Alternative views on setting clinical trial futility criteria. J Biopharm Stat2014; 24: 976–993.
28.
DengQLuX. Choosing timing and boundary for futility analysis based on cost-effectiveness assessment. Stat Biopharmaceut Res2018; 10(2): 104–111.
29.
ChenCBeckmanRA. Optimal cost-effective go-no go decisions in late-stage oncology drug development. Stat Biopharmaceut Res2009; 1: 159–169.
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.
