The effects of heterogeneity on Simon Phase II clinical trial design operating characteristics

Abstract

The homogeneity assumption of a Simon Phase II clinical trial is commonly violated due to excess variation in the response known as response heterogeneity. Using a general framework to model heterogeneity, we investigate its effects on the operating characteristics of the Simon trial design using the standard practice of averaging responses. We show that, under heterogeneity and averaging, the Simon designs have higher than expected errors which may result in false negative and false positive Phase II outcomes.

Adjusting Simon's optimal two‐stage design for heterogeneous populations based on stratification or using historical controls

“…In such a situation, where the response probabilities vary across the population, it is clearly inappropriate to apply a classical single‐arm trial with fixed response probabilities p 0 and p 1 (Barnes & Rai, ). Notably, the type I error of such a trial will be substantially too high, when a large fraction of patients with good prognoses enter the trial, similarly the power will be too low when many patients with unfavorable prognoses are recruited.…”

Phase II Clinical Trials: Issues and Practices

“…The single arm studies also assume homogeneity of the population to make statistical inferences but homogeneity is not guaranteed. Barnes and Rai [4] examine the impact of subgroups which create heterogeneity in the response on the operating characteristics of the Simon's 2-Stage design [5]. They find that the traditional design has higher than expected type I and II error rates resulting in false negative and false positive phase II outcomes.…”

Clinical trials: innovation, progress and controversy

“…These articles have spanned many aspects of clinical trials wonderfully, including trial design and management; legal, ethical and regulatory issues of clinical trials; subject participation and retention in clinical trials; and data collection and data management. The breadth of subjects covered is remarkable, with articles discussing study subject enrollment, engagement, and retention; 1–4 the effects of participant heterogeneity on intermediate phase clinical trials; 5 important methodological concerns with complementary and alternative medications; 6 modern issues with clinical-trial data management; 7 and state-of-the-art reviews of clinical importance such as pharmacological drug toxicity 8 and biomarkers in cardiovascular diseases. 9 To complement these contemporary commentaries and reviews, the Open Access Journal of Clinical Trials has published original research in a number of different fields in medicine, biostatistics, and epidemiology.…”