Safety Data Analysis and Reporting using S-PLUS® and Insightful Miner™

Presented: Thursday, March 10th, 2005

Speaker: Michael O'Connell, Insightful Corporation

Listen to the archived webcast.

Downloads:

• Webcast presentation slides
• S-PLUS Clinical Safety Miner datasheet

The analysis of safety data from prospective clinical trials and retrospective data such as the FDA adverse event reporting system database (AERS) has numerous challenges. Some of the key requirements include the ability to obtain:

• Publication-quality reports (tables and listing) and simultaneous interactive graphical representations of adverse events and related data (e.g. labs, demographics)
• Detailed statistical analysis and data mining of clinical data to identify risk factors for adverse events and related conditions
• Compelling graphical analyses of adverse event and related data (e.g. labs demographics)
• Automated, repeated reports as underlying data are updated
• Conditional generation and inclusion of graphical and tabular report components based on adverse event and lab data thresholds
• Updates and statistical monitoring results in Sequential Design situations
  

In the retrospective case, signal detection from the AERS database has the challenges of its very nature e.g. lack of incidence data and lack of denominator for appropriate rate calculations. In this setting one can define internal baseline rates and use relative reporting rates for examining drugs and adverse categories. In particular, Poisson and hierarchical (Bayesian) models for signal detection are helpful in comparing relative reporting rates for classes of adverse events between drugs in a therapeutic class.

This webinar describes the use of S-PLUS and Insightful Miner for safety data analysis and reporting in both the prospective and retrospective situations. S+Graphlets and the S-PLUS Clinical Reporting Pack are key components of the S-PLUS/Insightful Miner approach, for interactive and publication-quality reporting respectively. Data management and data mining in prospective and retrospective situations is nicely handled through the Insightful Miner visual workflow. The S-PLUS/Insightful Miner solution is illustrated using clinical trial and FDA AERS data.

Michael O'Connell is Director of Biopharmaceutical Solutions at Insightful Corporation and Adjunct Professor North Carolina State University Department of Statistics. Dr. O'Connell’s background and graduate work was in applied statistics and he has published more than 30 papers on graphics, statistics, data mining and biopharmaceutics. He has also written several statistical software packages and managed more than 50 successful custom software application development efforts. Dr. O'Connell holds a Bachelors degree in Science from the University of Sydney, a Masters degree in Statistics from the University of New South Wales and a Ph.D in Statistics from North Carolina State University.