Bayesian adaptive designs for multi-arm trials: an orthopaedic case study

Research output: Contribution to journalArticlepeer-review

Standard

Bayesian adaptive designs for multi-arm trials : an orthopaedic case study. / Ryan, Elizabeth; Lamb, Sarah E; Williamson, Esther; Gates, Simon.

In: Trials, Vol. 21, No. 1, 83, 14.01.2020, p. 1-16.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Ryan, Elizabeth ; Lamb, Sarah E ; Williamson, Esther ; Gates, Simon. / Bayesian adaptive designs for multi-arm trials : an orthopaedic case study. In: Trials. 2020 ; Vol. 21, No. 1. pp. 1-16.

Bibtex

@article{f99f5a7fa04445e8bd374c16ceef6111,
title = "Bayesian adaptive designs for multi-arm trials: an orthopaedic case study",
abstract = "Background Bayesian adaptive designs can be more efficient than traditional methods for multi-arm randomised controlled trials. The aim of this work was to demonstrate how Bayesian adaptive designs can be constructed for multi-arm phase III clinical trials and assess potential benefits that these designs offer.   Methods We constructed several alternative Bayesian adaptive designs for the Collaborative Ankle Support Trial (CAST), which was a randomised controlled trial that compared four treatments for severe ankle sprain. These designs incorporated response adaptive randomisation (RAR), arm dropping, and early stopping for efficacy or futility. We studied the operating characteristics of the Bayesian designs via simulation. We then virtually re-executed the trial by implementing the Bayesian adaptive designs using patient data sampled from the CAST study to demonstrate the practical applicability of the designs.   Results We constructed five Bayesian adaptive designs, each of which had high power and recruited fewer patients on average than the original designs target sample size. The virtual executions showed that most of the Bayesian designs would have led to trials that declared superiority of one of the interventions over the control. Bayesian adaptive designs with RAR or arm dropping were more likely to allocate patients to better performing arms at each interim analysis. Similar estimates and conclusions were obtained from the Bayesian adaptive designs as from the original trial.   Conclusions Using CAST as an example, this case study shows how Bayesian adaptive designs can be constructed for phase III multi-arm trials using clinically relevant decision criteria. These designs demonstrated that they can potentially generate earlier results and allocate more patients to better performing arms. We recommend the wider use of Bayesian adaptive approaches in phase III clinical trials.   Trial registration CAST study registration ISRCTN, ISRCTN37807450. Retrospectively registered on 25 April 2003.",
keywords = "Arm dropping, Bayesian adaptive design, Emergency medicine, Interim analysis, Monitoring, Multi-arm trial, Orthopaedic, Phase III, Randomised controlled trials, Response adaptive randomisation",
author = "Elizabeth Ryan and Lamb, {Sarah E} and Esther Williamson and Simon Gates",
year = "2020",
month = jan,
day = "14",
doi = "10.1186/s13063-019-4021-0",
language = "English",
volume = "21",
pages = "1--16",
journal = "Trials",
issn = "1745-6215",
publisher = "Springer",
number = "1",

}

RIS

TY - JOUR

T1 - Bayesian adaptive designs for multi-arm trials

T2 - an orthopaedic case study

AU - Ryan, Elizabeth

AU - Lamb, Sarah E

AU - Williamson, Esther

AU - Gates, Simon

PY - 2020/1/14

Y1 - 2020/1/14

N2 - Background Bayesian adaptive designs can be more efficient than traditional methods for multi-arm randomised controlled trials. The aim of this work was to demonstrate how Bayesian adaptive designs can be constructed for multi-arm phase III clinical trials and assess potential benefits that these designs offer.   Methods We constructed several alternative Bayesian adaptive designs for the Collaborative Ankle Support Trial (CAST), which was a randomised controlled trial that compared four treatments for severe ankle sprain. These designs incorporated response adaptive randomisation (RAR), arm dropping, and early stopping for efficacy or futility. We studied the operating characteristics of the Bayesian designs via simulation. We then virtually re-executed the trial by implementing the Bayesian adaptive designs using patient data sampled from the CAST study to demonstrate the practical applicability of the designs.   Results We constructed five Bayesian adaptive designs, each of which had high power and recruited fewer patients on average than the original designs target sample size. The virtual executions showed that most of the Bayesian designs would have led to trials that declared superiority of one of the interventions over the control. Bayesian adaptive designs with RAR or arm dropping were more likely to allocate patients to better performing arms at each interim analysis. Similar estimates and conclusions were obtained from the Bayesian adaptive designs as from the original trial.   Conclusions Using CAST as an example, this case study shows how Bayesian adaptive designs can be constructed for phase III multi-arm trials using clinically relevant decision criteria. These designs demonstrated that they can potentially generate earlier results and allocate more patients to better performing arms. We recommend the wider use of Bayesian adaptive approaches in phase III clinical trials.   Trial registration CAST study registration ISRCTN, ISRCTN37807450. Retrospectively registered on 25 April 2003.

AB - Background Bayesian adaptive designs can be more efficient than traditional methods for multi-arm randomised controlled trials. The aim of this work was to demonstrate how Bayesian adaptive designs can be constructed for multi-arm phase III clinical trials and assess potential benefits that these designs offer.   Methods We constructed several alternative Bayesian adaptive designs for the Collaborative Ankle Support Trial (CAST), which was a randomised controlled trial that compared four treatments for severe ankle sprain. These designs incorporated response adaptive randomisation (RAR), arm dropping, and early stopping for efficacy or futility. We studied the operating characteristics of the Bayesian designs via simulation. We then virtually re-executed the trial by implementing the Bayesian adaptive designs using patient data sampled from the CAST study to demonstrate the practical applicability of the designs.   Results We constructed five Bayesian adaptive designs, each of which had high power and recruited fewer patients on average than the original designs target sample size. The virtual executions showed that most of the Bayesian designs would have led to trials that declared superiority of one of the interventions over the control. Bayesian adaptive designs with RAR or arm dropping were more likely to allocate patients to better performing arms at each interim analysis. Similar estimates and conclusions were obtained from the Bayesian adaptive designs as from the original trial.   Conclusions Using CAST as an example, this case study shows how Bayesian adaptive designs can be constructed for phase III multi-arm trials using clinically relevant decision criteria. These designs demonstrated that they can potentially generate earlier results and allocate more patients to better performing arms. We recommend the wider use of Bayesian adaptive approaches in phase III clinical trials.   Trial registration CAST study registration ISRCTN, ISRCTN37807450. Retrospectively registered on 25 April 2003.

KW - Arm dropping

KW - Bayesian adaptive design

KW - Emergency medicine

KW - Interim analysis

KW - Monitoring

KW - Multi-arm trial

KW - Orthopaedic

KW - Phase III

KW - Randomised controlled trials

KW - Response adaptive randomisation

UR - http://www.scopus.com/inward/record.url?scp=85077877426&partnerID=8YFLogxK

U2 - 10.1186/s13063-019-4021-0

DO - 10.1186/s13063-019-4021-0

M3 - Article

C2 - 31937341

VL - 21

SP - 1

EP - 16

JO - Trials

JF - Trials

SN - 1745-6215

IS - 1

M1 - 83

ER -