Statistical Modeling and Graphical Analysis of Safety Data in Clinical Trials

Presented: Thursday, March 29, 2007

Speaker: Michael O’Connell, Insightful Corporation

View the on-demand web cast. Download instructions on how to view the web cast.

Download the web cast presentation.

Rigorous assessment of drug safety, pre- and post- drug approval, is essential to protect and promote public health. However, clinical trial design is focused on the efficacy endpoints, and safety data analysis is typically an afterthought.  For example, large amounts of safety data are collected in clinical trials, but basic information such as which types of patients have adverse events or elevated lab values, is not well captured or summarized in statistical analyses and clinical study reports.

This web cast will focus on statistical and graphical methods for analysis and reporting of safety data. Statistical methods considered include hierarchical models and and exploratory analyses such as trees and forests. Results from these analyses are presented as S-PLUS® graphical summaries that highlight key aspects of drug safety, such as risk difference and effect probabilities for adverse events. Such safety data analyses and reports have immense value for pharmaceutical companies, drug safety monitoring boards and regulatory agencies such as the FDA.