Retrieved-Dropout-Based multiple imputation for time-to-event data in cardiovascular outcome trials

He, Jiwei; Crackel, Roberto; Koh, William Jen Hoe; Chen, Ling-Wan; Li, Feng; Zhang, Jialü; Rothmann, Mark D.

doi:10.1080/10543406.2022.2118763

Cited by 3 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, the application of these methods can be easily extended to other disease areas. Although only the imputation of missing data for a continuous endpoint is discussed in this paper, the authors have applied the RD approach to impute missing follow‐up time for time‐to‐event endpoints in several NDA or biologics licensure application (BLA) reviews 30 . A caveat in imputing time‐to‐event endpoints is that proper imputation should be used if Rubin's rules is utilized to combine analysis results from multiple imputed datasets.…”

Section: Discussionmentioning

confidence: 99%

“…Although only the imputation of missing data for a continuous endpoint is discussed in this paper, the authors have applied the RD approach to impute missing follow-up time for time-to-event endpoints in several NDA or biologics licensure application (BLA) reviews. 30 A caveat in imputing time-to-event endpoints is that proper imputation should be used if Rubin's rules is utilized to combine analysis results from multiple imputed datasets. If missing data are imputed using an "improper" or Type B imputation approach, 31 using Rubin's rules for combining results from separately imputed datasets is not appropriate, as it leads to an underestimated variance.…”

Section: Case Study 3-application Of Washout Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Statistical methods for handling missing data to align with treatment policy strategy

Wang

Kim

et al. 2023

Pharmaceutical Statistics

Self Cite

View full text Add to dashboard Cite

The International Council for Harmonization (ICH) E9(R1) addendum recommends choosing an appropriate estimand based on the study objectives in advance of trial design. One defining attribute of an estimand is the intercurrent event, specifically what is considered an intercurrent event and how it should be handled. The primary objective of a clinical study is usually to assess a product's effectiveness and safety based on the planned treatment regimen instead of the actual treatment received. The estimand using the treatment policy strategy, which collects and analyzes data regardless of the occurrence of intercurrent events, is usually utilized. In this article, we explain how missing data can be handled using the treatment policy strategy from the authors' viewpoint in connection with antihyperglycemic product development programs. The article discusses five statistical methods to impute missing data occurring after intercurrent events. All five methods are applied within the framework of the treatment policy strategy. The article compares the five methods via Markov Chain Monte Carlo simulations and showcases how three of these five methods have been applied to estimate the treatment effects published in the labels for three antihyperglycemic agents currently on the market.intercurrent events, missing data, retrieved dropouts, return-to-baseline, treatment policy strategy, washout method | INTRODUCTIONAn estimand is what treatment effect is to be estimated in a clinical trial. The International Council for Harmonization (ICH) E9(R1) addendum on "Estimands and Sensitivity Analysis in Clinical Trials" 1 defines an estimand as a precise description of the treatment effect aligning with a given clinical trial objective. As further explained in the addendum, an estimand features the following five attributes: treatment, target population, variable of interest (endpoint), intercurrent events, and population-level summary. An intercurrent event is defined as an event occurring after treatment initiation that affects either the interpretation or the existence of the measurements associated with the clinical question ofThe contribution was made while Dr. Susie Sinks worked at the FDA.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Case Study 3-application Of Washout Methodsmentioning

confidence: 99%

Statistical methods for handling missing data to align with treatment policy strategy

Wang

Kim

et al. 2023

Pharmaceutical Statistics

Self Cite

View full text Add to dashboard Cite

show abstract

“…In other words, after primary analysis and primary estimand are pre-specified in the protocol, the proposed sensitivity analyses must target the same estimand so that the results can be compared side by side. Because analyses of time to first events in CVOT are usually conducted under the intent to treat (ITT) principle with no exclusion of data post randomization, following the treatment policy (TP) strategy [ 22 , pp. 1–19] there is no controversy that all subsequent sensitivity analyses should target the same TP estimand, in terms of handling of missing data that arise from intercurrent events.…”

Section: Introductionmentioning

confidence: 99%

“…Recently He et al published a paper about retrieved dropout multiple imputation (MI) in CVOT using piecewise exponential distribution [ 22 , pp. 1–19].…”

Section: Introductionmentioning

confidence: 99%

Imputation of Missing Data for Time-to-Event Endpoints Using Retrieved Dropouts

Wang,

Frederich,

Mancuso

2023

Ther Innov Regul Sci

View full text Add to dashboard Cite

We have explored several statistical approaches to impute missing time-to-event data that arise from outcome trials with relatively long follow-up periods. Aligning with the primary estimand, such analyses evaluate the robustness of results by imposing an assumption different from censoring at random (CAR). Although there have been debates over which assumption and which method is more appropriate to be applied to the imputation, we propose to use the collection of retrieved dropouts as the basis of missing data imputation. As retrieved dropouts share a similar disposition, such as treatment discontinuation, with subjects who have missing data, they can reasonably be assumed to characterize the distribution of time-to-event among subjects with missing data. In terms of computational intensity and robustness to violation of underlying distributional assumption, we have compared parametric approaches via MCMC or MLE multivariate sampling procedures to a non-parametric bootstrap approach with respect to baseline hazard function. Each of these approaches follows a process of multiple imputation (“proper imputations”), analysis of complete datasets, and final combination. The type-I error, and power rates are examined under a wide range of scenarios to inform the performance characteristics. A subset of a real unblinded phase III CVOT is used to demonstrate the application of the proposed approaches, compared to the Cox proportional hazards model and jump-to-reference multiple imputation.

show abstract

Addressing missing outcome data in randomised controlled trials: A methodological scoping review

Medcalf,

Turner,

Espinoza

et al. 2024

Contemporary Clinical Trials

View full text Add to dashboard Cite

Retrieved-Dropout-Based multiple imputation for time-to-event data in cardiovascular outcome trials

Cited by 3 publications

References 6 publications

Statistical methods for handling missing data to align with treatment policy strategy

Statistical methods for handling missing data to align with treatment policy strategy

Imputation of Missing Data for Time-to-Event Endpoints Using Retrieved Dropouts

Addressing missing outcome data in randomised controlled trials: A methodological scoping review

Contact Info

Product

Resources

About