Statistical issues in the design and analysis of expertise‐based randomized clinical trials

Abstract

SUMMARYIn order to avoid certain difficulties with the conventional randomized clinical trial design, the expertise-based design has been proposed as an alternative. In the expertise-based design, patients are randomized to clinicians (e.g. surgeons), who then treat all their patients with their preferred intervention. This design recognizes individual clinical preferences and so may reduce the rates of procedural crossovers compared with the conventional design. It may also facilitate recruitment of clinicians, because they are always allowed to deliver their therapy of choice, a feature that may also be attractive to patients.The expertise-based design avoids the possibility of so-called differential expertise bias. If a standard treatment is generally more familiar to clinicians than a new experimental treatment, then in the conventional design, more patients randomized to the standard treatment will have an expert clinician, compared with patients randomized to the experimental treatment. If expertise affects the study outcome, then a biased comparison of the treatment groups will occur.We examined the relative efficiency of estimating the treatment effect in the expertise-based and conventional designs. We recognize that expected patient outcomes may be better in the expertisebased design, which in turn may modify the estimated treatment effect. In particular, a larger treatment effect in the expertise-based design can sometimes offset a higher standard error arising from the confounding of clinician effects with treatments.These concepts are illustrated with data taken from a randomized trial of two alternative surgical techniques for tibial fractures.

Design and execution of clinical trials in orthopaedic surgery

“…28 The second challenge facing surgical RCTs is that of clinical equipoise. Although community equipoise may exist for a given condition among surgeons as a whole, individual surgeons often favour a particular intervention.…”

“…28 The concern surrounding expertise-based RCTs extends to the potential loss of generalisability, as community surgeons may not be as skilled as trial experts. 2 Nevertheless, the expertise-based RCT offers a pragmatic solution to these unavoidable challenges of surgeon experience and equipoise.…”

Optimising the two‐stage randomised trial design when some participants are indifferent in their treatment preferences

“…We previously developed significance tests and confidence intervals for these effects, with potentially heterogenous variances between the observable groups . We took into account the sample variation associated the trinomial preference distribution, but numerical work indicated little practical impact if one uses conditional estimates of α, β, and γ , ie, ignoring their sample variation, as we will do so here. For simplicity, we will also assume a common error variance ( σ 2 ) for all participants.…”

“…Relevant approaches include the two‐stage randomised design and variants of it, the fully randomised design, the partially randomised design, and Zelen's randomised consent designs . We have also discussed the related issue of treatment preferences among clinicians, involving the so‐called “expertise bias.” These various designs can be characterised according to whose preferences are identified, when and how those preferences are measured, and if any treatment assignments take preferences into account.…”

In search of the sample: Recent experiences of a trial team in Orthodontics

“…However, there is less discussion of the difficulties associated with undertaking such studies, including costs 2 , ethical problems, issues associated with informed consent 3 , problems of bias, clinician preference for certain treatment options 4 , difficulties in recruiting sufficient patients 5 and overestimating the number of patients who would be eligible for inclusion in the study or would agree to participate 6 .…”