On Inclusion of Covariates in Model Based Dose Finding Clinical Trial Designs.

There is a growing number of Phase I dose-finding studies that use a model-based approach, such as the CRM or the EWOC method to estimate the dose-toxicity relationship. It is common to assume that all patients will have similar toxicity risk given the dose regardless of patients' individual characteristics. In many trials, however, some patients' covariates (e.g., a concomitant drug assigned by a clinician) might have an impact on the dose-toxicity relationship. In this work, motivated by a real trial, we evaluate an impact of taking into account (or omitting) some patients' covariates on the individual target dose recommendations and patients' safety in Phase I model-based dose-finding study. We investigate several variable penalisation criteria and found that, for continuous and binary covariates, omitting a prognostic covariate leads to a drastically low proportion of correct selections and an increase of overdosing. At the same time, including a covariate can lead to good operating characteristics in all scenarios but can sometimes slightly decrease the proportion of good selections and increase the overdosing. To tackle this, we propose to use a Bayesian Lasso Bayesian Logistic Regression Model (BLRM) and Spike-and-Slab BLRM. We have found that the BLRM coupled to the Bayesian LASSO and the BLRM with Spike-and-Slab are on average better appropriate to consider variable inclusion.