Causal and Self-Controlled Tree-scan and Continuous Monitoring

Music City Center 

Monitoring the safety of drugs in real world settings following market approval is a crucial aspect of pharmacovigilance. It allows regulatory authorities and healthcare providers to swiftly address any emerging safety concerns. This process assesses whether the therapeutic benefits of a drug continue to outweigh any potential risks when used by the general population, a proactive approach aiming to ensure that patients receive treatments that are both effective and safe.

The analysis of a post-marketing data can be challenging due to the complexity, size, and variability inherent in real-world data. Various methods have been proposed to tackle these challenges, one of which is the tree-based scan statistic, a data mining method looks for excess risk by simultaneously evaluating large set of adverse events, as well as groups of adverse events, adjusting for the multiple testing inherent in the large number of overlapping groups evaluated.

Other interesting methods are sequential probability ratio test or the sequential FDR, which account for temporal nature of adverse events, and allow continuous data analysis as it accumulates while controlling false discovery rate.

In our talk, we will cover the fundamental principles of post-marketing monitoring, Tree Scan method and sequential probability testing in biopharmaceutical research. Practical application and examples will be provided.