Comparison of Model Averaging and Model Selection in Dose Finding Trials Analyzed by Nonlinear Mixed Effect Models

International audienceIn drug development, pharmacometric approaches consist in identifying via a model selection (MS) process the model structure that best describes the data. However, making predictions using a selected model ignores model structure uncertainty, which could impair predictive performance. To overcome this drawback, model averaging (MA)takes into account the uncertainty across a set of candidate models by weighting them as a function of an information criterion. Our primary objective was to use clinical trial simulations (CTSs) to compare model selection (MS) with model averaging (MA) in dose-finding clinical trials, based on the AIC information criterion. A secondary aim of this analysis was to challenge the use of AIC by comparing MA and MS using 5 different information criteria. CTSs were based on a nonlinear mixed effects model characterizing the time course of visual acuity in wet age-related macular degeneration patients. Predictive performances of the modeling approaches were evaluated using 3 performance criteria focused on the main objectives of a phase II clinical trial. In this framework, MA adequately described the data and showed better predictive performance than MS, increasing the likelihood of accurately characterizing the dose-response relationship and defining the minimum effective dose. Moreover, regardless of the modeling approach, AIC was associated with the best predictive performances