The effect of salvage therapy on survival in a longitudinal study with treatment by indication

We consider using observational data to estimate the effect of a treatment on disease recurrence, when the decision to initiate treatment is based on longitudinal factors associated with the risk of recurrence. The effect of salvage androgen deprivation therapy (SADT) on the risk of recurrence of prostate cancer is inadequately described by the existing literature. Furthermore, standard Cox regression yields biased estimates of the effect of SADT, since it is necessary to adjust for prostate-specific antigen (PSA), which is a time-dependent confounder and an intermediate variable. In this paper, we describe and compare two methods which appropriately adjust for PSA in estimating the effect of SADT. The first method is a two-stage method which jointly estimates the effect of SADT and the hazard of recurrence in the absence of treatment by SADT. In the first stage, PSA is predicted in the absence of SADT, and in the second stage, a time-dependent Cox model is used to estimate the benefit of SADT, adjusting for PSA. The second method, called sequential stratification, reorganizes the data to resemble a sequence of experiments in which treatment is conditionally randomized given the time-dependent covariates. Strata are formed, each consisting of a patient undergoing SADT and a set of appropriately matched controls, and analysis proceeds via stratified Cox regression. Both methods are applied to data from patients initially treated with radiation therapy for prostate cancer and give similar SADT effect estimates.

[1]  L. Pisters.  Treatment failure after primary and salvage therapy for prostate cancer , 2008, Cancer.

[2]  A. V. von Eschenbach,et al.  Prostate‐specific antigen. An important marker for prostate cancer treated by external beam radiation therapy , 1993, Cancer.

[3]  Bo Lu.  Propensity Score Matching with Time‐Dependent Covariates , 2005, Biometrics.

[4]  T. Wilt,et al.  Early versus deferred androgen suppression in the treatment of advanced prostatic cancer. , 2001, The Cochrane database of systematic reviews.

[5]  D. Kuban,et al.  Radiation therapy for clinically localized prostate cancer: a multi-institutional pooled analysis. , 1999, JAMA.

[6]  S. Zeger,et al.  Longitudinal data analysis using generalized linear models , 1986 .

[7]  J. Kalbfleisch,et al.  The Statistical Analysis of Failure Time Data: Kalbfleisch/The Statistical , 2002 .

[8]  P. Carroll,et al.  Treatment failure after primary and salvage therapy for prostate cancer , 2008, Cancer.

[9]  M. Wulfsohn,et al.  A joint model for survival and longitudinal data measured with error. , 1997, Biometrics.

[10]  J. Mckinlay,et al.  Age, disease, and changing sex hormone levels in middle-aged men: results of the Massachusetts Male Aging Study. , 1991, The Journal of clinical endocrinology and metabolism.

[11]  J. Robins,et al.  Comparison of dynamic treatment regimes via inverse probability weighting. , 2006, Basic & clinical pharmacology & toxicology.

[12]  J. Robins.  The control of confounding by intermediate variables. , 1989, Statistics in medicine.

[13]  P. Rosenbaum.  The Consequences of Adjustment for a Concomitant Variable that Has Been Affected by the Treatment , 1984 .

[14]  J. Robins,et al.  Recovery of Information and Adjustment for Dependent Censoring Using Surrogate Markers , 1992 .

[15]  N. Stone,et al.  Response of prostate volume, prostate-specific antigen, and testosterone to flutamide in men with benign prostatic hyperplasia. , 1991, Journal of andrology.

[16]  A. Kibel.  Diabetes and Cardiovascular Disease During Androgen Deprivation Therapy for Prostate Cancer , 2007 .

[17]  S. Brophy,et al.  Interventions for latent autoimmune diabetes (LADA) in adults. , 2011, The Cochrane database of systematic reviews.

[18]  J. Robins.  A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect , 1986 .

[19]  L. Denis,et al.  CasodexTM 10–200 mg Daily, Used as Monotherapy for the Treatment of Patients with Advanced Prostate Cancer , 1998, European Urology.

[20]  Mark J van der Laan,et al.  History-adjusted marginal structural models for estimating time-varying effect modification. , 2007, American journal of epidemiology.

[21]  J. M. Taylor,et al.  A comparison of smoothing techniques for CD4 data measured with error in a time-dependent Cox proportional hazards model. , 1998, Statistics in medicine.

[22]  Robert M. Merion,et al.  Estimating the Effect of a Time-Dependent Treatment by Levels of an Internal Time-Dependent Covariate: Application to the Contrast Between Liver Wait-List and Posttransplant Mortality , 2009 .

[23]  Douglas E Schaubel,et al.  A Sequential Stratification Method for Estimating the Effect of a Time‐Dependent Experimental Treatment in Observational Studies , 2006, Biometrics.

[24]  Laurence L. George,et al.  The Statistical Analysis of Failure Time Data , 2003, Technometrics.

[25]  M. J. van der Laan,et al.  The International Journal of Biostatistics Causal Effect Models for Realistic Individualized Treatment and Intention to Treat Rules , 2011 .

[26]  James M. Robins,et al.  Marginal Structural Models versus Structural nested Models as Tools for Causal inference , 2000 .

[27]  Cécile Proust-Lima,et al.  Determinants of change in prostate-specific antigen over time and its association with recurrence after external beam radiation therapy for prostate cancer in five large cohorts. , 2008, International journal of radiation oncology, biology, physics.

[28]  L. Denis,et al.  Casodex 10-200 mg daily, used as monotherapy for the treatment of patients with advanced prostate cancer. An overview of the efficacy, tolerability and pharmacokinetics from three phase II dose-ranging studies. Casodex Study Group. , 1998, European Urology.

[29]  Paul R. Rosenbaum,et al.  Balanced Risk Set Matching , 2001 .

[30]  Yan Wang,et al.  Jointly Modeling Longitudinal and Event Time Data With Application to Acquired Immunodeficiency Syndrome , 2001 .