Surrogate endpoints are often used in clinical trials instead of well-established hard endpoints for practical convenience. The meta-analytic approach relies on two measures of surrogacy: one at the individual level and one at the trial level. In the survival data setting, a two-step model based on copulas is commonly used. We present a new approach which employs a bivariate survival model with an individual random effect shared between the two endpoints and correlated treatment-by-trial interactions. We fit this model using auxiliary mixed Poisson models. We study via simulations the operating characteristics of this mixed Poisson approach as compared to the two-step copula approach. We illustrate the application of the methods on two individual patient data meta-analyses in gastric cancer, in the advanced setting (4069 patients from 20 randomized trials) and in the adjuvant setting (3288 patients from 14 randomized trials).
BurzykowskiTMolenberghsGBuyseM. The evaluation of surrogate endpoints, New York, NY: Springer Science & Business Media, 2006.
2.
ChakravartyASridharaR. Use of progression-free survival as a surrogate marker in oncology trials: some regulatory issues. Stat Methods Med Res2008; 17: 515–518.
3.
BuyseMMolenberghsGPaolettiXet al.Statistical evaluation of surrogate endpoints with examples from cancer clinical trials. Biom J2016; 58: 104–132.
4.
BlumenthalGMKaruriSWZhangHet al.Overall response rate, progression-free survival, and overall survival with targeted and standard therapies in advanced non-small-cell lung cancer: US food and drug administration trial-level and patient-level analyses. J Clin Oncol2015; 33: 1008–1014.
5.
DanielsMJHughesMD. Meta-analysis for the evaluation of potential surrogate markers. Stat Med1997; 16: 1965–1982.
6.
BuyseMMolenberghsG. Criteria for the validation of surrogate endpoints in randomized experiments. Biometrics1998; 54: 1014–1029.
7.
BuyseMMolenberghsGBurzykowskiTet al.The validation of surrogate endpoints in meta-analyses of randomized experiments. Biostatistics2000; 1: 49–67.
8.
BurzykowskiTMolenberghsGBuyseMet al.Validation of surrogate end points in multiple randomized clinical trials with failure time end points. J Roy Stat Soc Appl Stat2001; 50: 405–422.
9.
KendallMG. A new measure of rank correlation. Biometrika1938; 30: 81–93.
10.
van HouwelingenHCArendsLStijnenT. Advanced methods in meta-analysis: multivariate approach and meta-regression. Stat Med2002; 21: 589–624.
11.
SargentDJWieandHSHallerDGet al.Disease-free survival versus overall survival as a primary end point for adjuvant colon cancer studies: Individual patient data from 20,898 patients on 18 randomized trials. J Clin Oncol2005; 23: 8664–8670.
12.
BuyseMBurzykowskiTCarrollKet al.Progression-free survival is a surrogate for survival in advanced colorectal cancer. J Clin Oncol2007; 25: 5218–5224.
13.
BurzykowskiTBuyseMPiccart-GebhartMJet al.Evaluation of tumor response, disease control, progression-free survival, and time to progression as potential surrogate end points in metastatic breast cancer. J Clin Oncol2008; 26: 1987–1992.
14.
BuyseMBurzykowskiTMichielsSet al.Individual- and trial-level surrogacy in colorectal cancer. Stat Methods Med Res2008; 17: 467–75.
15.
MichielsSLe MaîtreABuyseMet al.Surrogate endpoints for overall survival in locally advanced head and neck cancer: meta-analyses of individual patient data. Lancet Oncol2009; 10: 341–350.
16.
ObaKPaolettiXAlbertsSet al.Disease-free survival as a surrogate for overall survival in adjuvant trials of gastric cancer: a meta-analysis. J Natl Canc Inst2013; 105: 1600–1607.
17.
PaolettiXObaKBangYJet al.Progression-free survival as a surrogate for overall survival in advanced/recurrent gastric cancer trials: a meta-analysis. J Natl Canc Inst2013; 105: 1667–1670.
18.
MauguenAPignonJPBurdettSet al.Surrogate endpoints for overall survival in chemotherapy and radiotherapy trials in operable and locally advanced lung cancer: a re-analysis of meta-analyses of individual patients’ data. Lancet Oncol2013; 14: 619–626.
19.
MichielsSPuglianoLMarguetSet al.Progression-free survival as surrogate end point for overall survival in clinical trials of HER2-targeted agents in HER2-positive metastatic breast cancer. Ann Oncol2016; 27: 1029–1034.
20.
RotoloFPignonJPBourhisJet al.Surrogate endpoints for overall survival in loco-regionally advanced nasopharyngeal carcinoma: an individual patient data meta-analysis. J Natl Canc Inst2017; 109.DOI:10.1093/jnci/djw239.
21.
GreenEYothersGSargentDJ. Surrogate endpoint validation: statistical elegance versus clinical relevance. Stat Methods Med Res2008; 17: 477–486.
22.
BurzykowskiT. Surrogate endpoints: wishful thinking or reality?Stat Methods Med Res2008; 17: 463–466.
23.
ShiQRenfroLABotBMet al.Comparative assessment of trial-level surrogacy measures for candidate time-to-event surrogate endpoints in clinical trials. Comput Stat Data Anal2011; 55: 2748–2757.
24.
RenfroLAShiQSargentDJet al.Bayesian adjusted R2 for the meta-analytic evaluation of surrogate time-to-event endpoints in clinical trials. Stat Med2012; 31: 743–761.
25.
GhoshDTaylorJMGSargentDJ. Meta-analysis for surrogacy: accelerated failure time models and semicompeting risks modeling. Biometrics2012; 68: 226–232.
26.
AlonsoAMolenberghsG. Evaluating time to cancer recurrence as a surrogate marker for survival from an information theory perspective. Stat Methods Med Res2008; 17: 497–504.
27.
VaupelJWMantonKGStallardE. The impact of heterogeneity in individual frailty on the dynamics of mortality. Demography1979; 16: 439–454.
28.
DuchateauLJanssenP. The frailty model, New York, NY: Springer Verlag, 2008.
29.
WienkeA. Frailty models in survival analysis. (Chapman & Hall/CRC biostatistics series), Boca Raton, FL: Taylor and Francis, 2010. DOI:10.1201/9781420073911.
30.
BurzykowskiTCortiñas AbrahantesJValidation in the case of two failure-time endpoints. In: BurzykowskiTMolenberghsGBuyseM (eds). The evaluation of surrogate endpoints, New York, NY: Springer, 2005, pp. 163–194.
31.
RondeauVPignonJPMichielsS. A joint model for the dependence between clustered times to tumour progression and deaths: a meta-analysis of chemotherapy in head and neck cancer. Stat Methods Med Res2011; 24: 711–729.
32.
WhiteheadJ. Fitting Cox’s regression model to survival data using GLIM. J Roy Stat Soc C Appl Stat1980; 29: 268–275.
33.
LairdNOlivierD. Covariance analysis of censored survival data using log-linear analysis techniques. J Am Stat Assoc1981; 76: 231–240.
34.
MaRKrewskiDBurnettRT. Random effects Cox models: a Poisson modelling approach. Biometrika2003; 90: 157–169.
35.
FengSNieLWolfeRA. Laplace’s approximation for relative risk frailty models. Lifetime Data Anal2009; 15: 343–356.
36.
HirschKWienkeAKussO. Log-normal frailty models fitted as Poisson generalized linear mixed models. Comput Meth Programs Biomed2016; 137: 167–175.
37.
CrowtherMJRileyRDStaessenJAet al.Individual patient data meta-analysis of survival data using Poisson regression models. BMC Med Res Methodol2012; 12: 34–34.
38.
The GASTRIC group. Role of chemotherapy for advanced/recurrent gastric cancer: an individual-patient-data meta-analysis. Eur J Cancer2013; 49: 1565–1577.
39.
The GASTRIC group. Benefit of adjuvant chemotherapy for resectable gastric cancer: a meta-analysis. J Am Med Assoc2010; 303: 1729–1737.
40.
RenfroLAShangHSargentDJ. Impact of copula directional specification on multi-trial evaluation of surrogate endpoints. J Biopharm Stat2015; 25: 857–877.
41.
ClaytonD. A model for association in bivariate life tables and its application in epidemiological studies of familial tendency in chronic disease incidence. Biometrika1978; 65: 141–151.
42.
PlackettRL. A class of bivariate distributions. J Am Stat Assoc1965; 60: 516–522.
43.
HougaardP. A class of multivariate failure time distributions. Biometrika1986; 73: 671–678.
44.
GasparriniAArmstrongBKenwardM. Multivariate meta-analysis for non-linear and other multi-parameter associations. Stat Med2012; 31: 3821–3839.
45.
HougaardP. Analysis of multivariate survival data, Germany: Springer Verlag, 2000.
46.
Munda M. Beyond the shared frailty model. PhD Thesis, Université Catholique de Louvain, Belgium, http://hdl.handle.net/2078.1/150625%0A (2014, accessed 19 June 2017).
47.
AsmussenSJensenJLRojas-NandayapaL. On the Laplace transform of the lognormal distribution. Meth Comput Appl Probab2014; 18: 441–458.
48.
GoutisCCasellaG. Explaining the saddlepoint approximation. Am Stat1999; 53: 216–224.
49.
Rotolo F. surrosurv: evaluation of failure time surrogate endpoints in individual patient data meta-analyses (R package version 1.1.15), https://cran.r-project.org/package=surrosurv (2017, accessed 19 June 2017).
50.
ShihJHLouisTA. Inferences on the association parameter in copula models for bivariate survival data. Biometrics1995; 51: 1384–1399.
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.
