A reflection on the causal interpretation of individual-level surrogacy

Alonso, Ariel; Elst, Wim Van der; Molenberghs, Geert; Flórez, Alvaro J.

doi:10.1080/10543406.2019.1579221

Cited by 4 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, strands from the CE and CA paradigms have been combined in the quest for surrogacy evaluation. Alonso et al (2019) 30 emphasize that this new measure of individual causal association does not substitute for the original R 2 indiv which retains distinct value in its own right. Van der Elst et al (2021) 31 go on to extend the original surrogate threshold effect metric from the CA paradigm to the new individual causal association in the CE context.…”

Section: Statistical Methods For Surrogate Evaluationmentioning

confidence: 99%

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

Weir

Taylor

2022

Pharmaceutical Statistics

View full text Add to dashboard Cite

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.

show abstract

Section: Statistical Methods For Surrogate Evaluationmentioning

confidence: 99%

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

Weir

Taylor

2022

Pharmaceutical Statistics

View full text Add to dashboard Cite

show abstract

“…Note, the focus in this article is the association between SEP and CEP. This does not imply a causal relationship between SEP and CEP (12). Two methodological approaches have been proposed to assess ILS within longitudinal data without specifying specific time periods.…”

Section: Introductionmentioning

confidence: 99%

Individual level surrogacy of MRI T2 lesion information for future disease severity: a methodological discussion and application to recent MS Phase II and III trials

Buchka,

Joachim,

Begüm

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: Individual-level surrogacy (ILS) describes settings where individual-patient information on a biomarker captures information on future patient-relevant clinical outcomes. For persons with relapsing-remitting multiple sclerosis (PwRRMS), whether the number of new or newly enlarged hyperintense lesions in T2 magnetic resonance images (MRI) or the T2 lesions’ volume can act as ILS for disability progression and disease activity is of interest. However, ILS of new T2 lesions for individual PwRRMS has not yet been demonstrated, although new T2 lesions already serve as a primary outcome parameter for pivotal trials. Methods: Our synthesis used individual-patient data from ten randomized controlled trials (n = 5673 PwRRMS). Longitudinal data on either the number or volume of new T2 lesions were analyzed as potential ILS for disability progression measured by the expanded disability status scale (EDSS) and disease activity shown by clinical relapses. ILS metrics were calculated: R2A) for the Meta-analytic (MA) and LRF (likelihood reduction factor) for the information theoretic (IT) approach. A simulation study elucidates the approaches’ potential to detect ILS and provides the basis to interpret the results derived from the trial data. Results: The simulation study demonstrates good performance for the IT approach. MA algorithms work well when applied to continuous data. When applied to counting data, the results may numerically be unstable. However, transformations of the counting data allow successful calculations with methods for Gaussian data. Analyses following IT methodology provide in all trial-based settings reliable results on ILS and identified two studies with weak ILS for the combination of T2 Volume and EDSS (LRF = 0.21, CI95%: 0.16 – 0.26; LRF = 0.28, CI95%: 0.23 – 0.34). Conclusion: The simulation study showed robust and sensitive results for IT and MA when not applied to counting data outcomes-based ILS strategies. The high potential of these algorithms to detect ILS strengthens the interpretation of our findings. Within most arms of ten pivotal MS trials, ILS measures were close to zero. Evidence on the surrogacy of T2 lesion measures and disease progression and activity as a general principle could not be generated. More research using proper designs and methodology is needed.

show abstract