Elicitation of Expert Prior Opinion: Application to the MYPAN Trial in Childhood Polyarteritis Nodosa

Abstract

ObjectivesDefinitive sample sizes for clinical trials in rare diseases are usually infeasible. Bayesian methodology can be used to maximise what is learnt from clinical trials in these circumstances. We elicited expert prior opinion for a future Bayesian randomised controlled trial for a rare inflammatory paediatric disease, polyarteritis nodosa (MYPAN, Mycophenolate mofetil for polyarteritis nodosa).MethodsA Bayesian prior elicitation meeting was convened. Opinion was sought on the probability that a patient in the MYPAN trial treated with cyclophosphamide would achieve disease remission within 6-months, and on the relative efficacies of mycophenolate mofetil and cyclophosphamide. Expert opinion was combined with previously unseen data from a recently completed randomised controlled trial in ANCA associated vasculitis.ResultsA pan-European group of fifteen experts participated in the elicitation meeting. Consensus expert prior opinion was that the most likely rates of disease remission within 6 months on cyclophosphamide or mycophenolate mofetil were 74% and 71%, respectively. This prior opinion will now be taken forward and will be modified to formulate a Bayesian posterior opinion once the MYPAN trial data from 40 patients randomised 1:1 to either CYC or MMF become available.ConclusionsWe suggest that the methodological template we propose could be applied to trial design for other rare diseases.

Rett Syndrome: Crossing the Threshold to Clinical Translation

“…Response-adaptive trials and sequential designs offer the ability to recruit fewer participants overall, and minimize the number who receive placebo [87]. Crossover designs necessitate longer trials and pose the risk of carryover effect; as an alternative, Bayesian statistics can help incorporate previous information (e.g., from natural history studies) into the clinical trial design, improving statistical power and limiting the number of subjects needed for a trial [88]. Alternative trial designs can increase the possibility of type 1 error and, thereby, the approval of medications that are not in fact safe and efficacious.…”

Practical help for specifying the target difference in sample size calculations for RCTs: the DELTA2 five-stage study, including a workshop

“…Other variations include the approach used to elicit opinion (e.g. group and/or individual interviews, questionnaires, e-mail surveys or workshops), [73][74][75] the complexity of the data elicited (from a single value 76 to multiple assessments incorporating uncertainty 77 and/or sensitivity to key factors, such as baseline level 78 ) and the method used to consolidate the results into an overall value, range of values or distribution. 69 Many elicitation techniques have been developed in the context of Bayesian statistics to establish a prior distribution, quantifying an expert's uncertainty about the true treatment difference.…”

Choosing the Target Difference (“effect size”) for a Randomised Controlled Trial - DELTA² Guidance

“…Various approaches can be used to identify experts (e.g., key opinion leaders, literature search, mailing list, or conference attendance). Other variations include the approach used to elicit opinion (e.g., group and/or individual interviews, questionnaires, email surveys, or workshops) [71][72][73], the complexity of the data elicited (from a single value [74] to multiple assessments incorporating uncertainty [75] and/or sensitivity to key factors such as baseline level [76]), and the method used to consolidate the results into an overall value, range of values, or distribution. [67] Many elicitation techniques have been developed in the context of Bayesian statistics to establish a prior distribution quantifying an expert's uncertainty about the true treatment difference.…”

“…Examples of prior elicitation include the CHART and MYPAN trials. [75,77,78] When the opinions of several experts are elicited, several priors may be used to capture a spectrum of beliefs (e.g., sceptical, neutral, or enthusiastic). Priors may be used to inform the design of a conventional trial, e.g., when setting the sample size or an early stopping rule [77,79] to ensure the study would convince a prior sceptic.…”

“…[76] However, the complexity increases substantially when undertaken as a formal elicitation. [75] Whatever the approach used, it should ideally match, as closely as possible, the intended trial research question. [71,76,81] Findings will vary according to the patient population and comparison of interest.…”