Intent-to-Treat Analysis for Longitudinal Studies with Dose Titration Scheme

• Activity Number: 145
• Type: Contributed
• Date/Time: Monday, August 10, 2015 : 8:30 AM to 10:20 AM
• Sponsor: Biopharmaceutical Section
• Author(s): Peter Zhang* and Ye Yang and Xiaoshu Feng
• Companies: Otsuka Pharmaceutical Development & Commercialization, Inc. and Otsuka Pharmaceutical Development & Commercialization, Inc. and Otsuka Pharmaceutical Development & Commercialization, Inc.
• Keywords: Clinical trials ; Intent-to-treat ; MMRM ; dose titration ; missing values ; multiple imputation

Abstract

We consider intent-to-treat (ITT) analysis of clinical trials involving longitudinal data subject to dose titration scheme and drop-out by employing a more precise MMRM model (Planned Dose - Titration Scheme). In this model, the low dose and high dose groups were modeled as the planned dose titration scheme since the dosing is identical during the titration period. This model is justified by its more accurate grouping of the treatment doses. This new MMRM model expanded the ITT model proposed by Little and Yau (1996) to model drop-out. Simulations and Multiple Imputations are performed for comparisons to the common MMRM model by randomized group. The new planned dose MMRM method is illustrated by an example of clinical trial in the adjunctive treatment of Major Depression Disorder (MMD).