Surrogate endpoint research has grown in recent years with the increasing development and usage of biomarkers in clinical research. Surrogacy analysis is derived through randomized clinical trial data and it is performed at the individual level and at the trial level.
A common surrogate analysis at the individual level is the application of the Prentice criteria. An approach for the evaluation of the Prentice criteria is discussed, with a focus on its most difficult component, the determination of whether the treatment effect is captured by the surrogate. An interpretation of this criterion is illustrated using data from a randomized clinical trial in prostate cancer.
Annals of oncology : official journal of the European Society for Medical Oncology / ESMO. 2015 Aug 07 [Epub ahead of print]
G Heller
Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center, New York, NY USA.