Informed decision‐making: Statistical methodology for surrogacy evaluation and its role in licensing and reimbursement assessments

Abstract

The desire, by patients and society, for faster access to therapies has driven a long tradition of the use of surrogate endpoints in the evaluation of pharmaceuticals and, more recently, biologics and other innovative medical technologies. The consequent need for statistical validation of potential surrogate outcome measures is a prime example on the theme of statistical support for decision-making in health technology assessment (HTA). Following the pioneering methodology based on hypothesis testing that Prentice presented in 1989, a host of further methods, both frequentist and Bayesian, have been developed to enable the value of a putative surrogate outcome to be determined. This rich methodological seam has generated practical methods for surrogate evaluation, the most recent of which are based on the principles of information theory and bring together ideas from the causal effects and causal association paradigms. Following our synopsis of statistical methods, we then consider how regulatory authorities (on licensing) and payer and HTA agencies (on reimbursement) use clinical trial evidence based on surrogate outcomes. We review existing HTA surrogate outcome evaluative frameworks.We conclude with recommendations for further steps: (1) prioritisation by regulators and payers of the application of formal surrogate outcome evaluative frameworks, (2) application of formal Bayesian decision-analytic methods to support reimbursement decisions, and (3) greater utilization of conditional surrogate-based licensing and reimbursement approvals, with subsequent reassessment of treatments in confirmatory trials based on final patientrelevant outcomes.

A framework for the definition and interpretation of the use of surrogate endpoints in interventional trials

“…8,18 Methods for the statistical validation of surrogates and examples of multidimensional frameworks evaluating the level of evidence for surrogate endpoint validity are described elsewhere. [19][20][21][22][23] In conclusion, our results have important implications for the future use of surrogate endpoints in the design, interpretation, and reporting of interventional trials. Determining what is (and what is not) a surrogate endpoint can be challenging and dependent on the framing within trials.…”

“… 8 , 18 Methods for the statistical validation of surrogates and examples of multidimensional frameworks evaluating the level of evidence for surrogate endpoint validity are described elsewhere. 19 , 20 , 21 , 22 , 23 …”

Interpreting Randomized Controlled Trials

“…OS time is a clinically meaningful, intuitive, and objective clinical endpoint to compare the efficacy of a new intervention versus control in an RCT [181]. Intermediate endpoints are clinical endpoints such as DFS and PFS time, which themselves directly measure clinical benefit but do not necessarily reflect the end of a patient's treatment course [178,[181][182][183]. For example, the outcome represented by the time to recurrence (TTR) clinical endpoint in oncology RCTs is used to record the presence or absence of a cure.…”

“…Consideration of the data-generating processes (Figure 12) can help to determine the most appropriate endpoints and statistical analysis models for a RCT. Clinical endpoints are defined as outcomes that reflect how patients feel, function, or survive [178]. The International Council for Harmonization of Technical Requirements for Pharmaceuticals for Human Use (ICH) E9 recently issued the addendum R1 on "Estimands and Sensitivity Analyses in Clinical Trials," whereby an estimand is defined as the parameter θ corresponding to the comparative relative treatment effect of the RCT interventions on the clinical endpoint of interest [179,180].…”

“…Surrogate endpoints are early or intermediate variables used in RCTs to make inferences about the effects of treatment on long-term outcomes, such as PFS or OS time [178]. A surrogate may be a biomarker, tumor response, or other endpoints that can be measured in a short timeframe, such as at the end of one cycle of therapy.…”