Drug development is a complex set of inter-linked processes in which the cumulative understanding of a drug's safety and efficacy profile is shaped during different learning phases. Often, drugs are approved based on limited safety information, for example in highly at risk or rare disease populations. Therefore, post approval, regulatory organizations have mandated proactive surveillance strategies that include the collection of reported adverse events experienced by exposed populations, some of whom may have been on treatment for extended periods of time. Analyzing these accumulating adverse event reports to understand their clinical significance, given the limitations imposed by the methods of data collection, is a complicated task. The aim of this chapter is to provide the readers with a general understanding of safety signal detection and assessment, followed by a description of statistical methods (both classical and Bayesian) typically utilized for quantifying the strength of association between a drug and an adverse event.
THE RELATION BETWEEN THE GENERALIZED MATCHING LAW AND SIGNAL-DETECTION THEORY
