1. Incorporating individual historical controls and aggregate treatment effect estimates into a Bayesian survival trial: a simulation study
- Author
-
Lisa V. Hampson, Marie-Cécile Le Deley, Caroline Brard, Nathalie Gaspar, Gwénaël Le Teuff, Centre de recherche en épidémiologie et santé des populations (CESP), Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Université Paris-Sud - Paris 11 (UP11)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Hôpital Paul Brousse-Institut National de la Santé et de la Recherche Médicale (INSERM), Service de biostatistique et d'épidémiologie (SBE), Direction de la recherche clinique [Gustave Roussy], Institut Gustave Roussy (IGR)-Institut Gustave Roussy (IGR), Statistical Methodology [Bâle, Suisse], Novartis Pharma AG, Département de cancérologie de l'enfant et de l'adolescent [Gustave Roussy], Institut Gustave Roussy (IGR), Unité de Méthodologie et de Biostatistique [Lille] (UMB), Centre Régional de Lutte contre le Cancer Oscar Lambret [Lille] (UNICANCER/Lille), Université de Lille-UNICANCER-Université de Lille-UNICANCER, We acknowledge for the design, analysis, interpretation of the simulation study, and for the writing of the manuscript, funding from – PhD grant from doctoral school of public health, Paris-Sud, Paris-Saclay – Lisa Hampson’s contribution to the paper was partly funded by the UK Medical Research Council (grant MR/M013510/1) and was completed while she was an employee of Lancaster University – Ligue contre le cancer, Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Université Paris-Sud - Paris 11 (UP11)-Hôpital Paul Brousse-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ), Université Lille Nord de France (COMUE)-UNICANCER-Université Lille Nord de France (COMUE)-UNICANCER, and Bodescot, Myriam
- Subjects
Simulation study ,Epidemiology ,Computer science ,Bayesian probability ,Health Informatics ,[SDV.CAN]Life Sciences [q-bio]/Cancer ,Power prior ,law.invention ,03 medical and health sciences ,0302 clinical medicine ,Adjuvants, Immunologic ,[SDV.CAN] Life Sciences [q-bio]/Cancer ,Randomized controlled trial ,law ,Statistics ,Prior probability ,Humans ,Computer Simulation ,030212 general & internal medicine ,Set (psychology) ,Baseline (configuration management) ,Bayesian randomised survival trial ,Randomized Controlled Trials as Topic ,Weibull distribution ,Osteosarcoma ,lcsh:R5-920 ,Phosphatidylethanolamines ,030503 health policy & services ,Aggregate (data warehouse) ,Bayes Theorem ,Variance (accounting) ,Models, Theoretical ,[SDV.SP]Life Sciences [q-bio]/Pharmaceutical sciences ,Control Groups ,Mixture prior ,3. Good health ,[SDV.SP] Life Sciences [q-bio]/Pharmaceutical sciences ,Research Design ,Sample Size ,Individual control data ,0305 other medical science ,lcsh:Medicine (General) ,Aggregate treatment effect ,Acetylmuramyl-Alanyl-Isoglutamine ,Rare disease ,Algorithms ,Research Article - Abstract
Background Performing well-powered randomised controlled trials (RCTs) of new treatments for rare diseases is often infeasible. However, with the increasing availability of historical data, incorporating existing information into trials with small sample sizes is appealing in order to increase the power. Bayesian approaches enable one to incorporate historical data into a trial’s analysis through a prior distribution. Methods Motivated by a RCT intended to evaluate the impact on event-free survival of mifamurtide in patients with osteosarcoma, we performed a simulation study to evaluate the impact on trial operating characteristics of incorporating historical individual control data and aggregate treatment effect estimates. We used power priors derived from historical individual control data for baseline parameters of Weibull and piecewise exponential models, while we used a mixture prior to summarise aggregate information obtained on the relative treatment effect. The impact of prior-data conflicts, both with respect to the parameters and survival models, was evaluated for a set of pre-specified weights assigned to the historical information in the prior distributions. Results The operating characteristics varied according to the weights assigned to each source of historical information, the variance of the informative and vague component of the mixture prior and the level of commensurability between the historical and new data. When historical and new controls follow different survival distributions, we did not observe any advantage of choosing a piecewise exponential model compared to a Weibull model for the new trial analysis. However, we think that it remains appealing given the uncertainty that will often surround the shape of the survival distribution of the new data. Conclusion In the setting of Sarcome-13 trial, and other similar studies in rare diseases, the gains in power and accuracy made possible by incorporating different types of historical information commensurate with the new trial data have to be balanced against the risk of biased estimates and a possible loss in power if data are not commensurate. The weights allocated to the historical data have to be carefully chosen based on this trade-off. Further simulation studies investigating methods for incorporating historical data are required to generalise the findings. Electronic supplementary material The online version of this article (10.1186/s12874-019-0714-z) contains supplementary material, which is available to authorized users.
- Published
- 2019