Considerations for Prevention and Handling of Missing Data in Clinical Trials

• Activity Number: 319
• Type: Topic Contributed
• Date/Time: Tuesday, August 5, 2014 : 10:30 AM to 12:20 PM
• Sponsor: Biopharmaceutical Section
• Author(s): Cynthia DeSouza and Abdul J. Sankoh*+
• Companies: Vertex Pharmaceuticals and Vertex Pharmaceuticals
• Keywords: dropouts ; missing data assumptions ; sensitivity analyses ; design and conduct ; new drug application ; approval

Abstract

Some recent new drug applications have been denied approval primarily due to the presence of serious missing data issues such as treatment-related patient dropouts that made it difficult to evaluate treatment efficacy. In this presentation, we will review examples of some of these missing data issues that were the primary drivers for the non-approval decisions of recent promising new drug applications. We will also discuss the use of specific design and operational strategies to prevent the occurrence of missing data, and statistical analysis strategies to handle non-preventable missing data problems. Finally, we will provide results from limited simulation studies to investigate the properties of proposed statistical analyses used to make inferences about the treatment effect.