Improving the Analysis of Adverse Events


Refining time-to-event models to detect non-constant hazards to signal adverse drug reactions (ADRs)

Team: Odile Sauzet, Victoria Cornelius

Pharmacovigilance is the process of monitoring the emergence of harm from a medicine once it has been licensed and is in use. The last decade has seen increased interest for the use of electronic health records (EHRs) in pharmacovigilance. The causal mechanism of an ADR will often result in the occurrence being time dependant. In this project we look at identifying signals for ADRs based on detecting a variation in hazard of an event using time-to-event models. Based on previous work we extend this study to examine generalised Weibull model-based approaches on simulated data and applied to a case study.


Better Methods for the analysis of adverse events – The why and how

Team: Rachel Phillips, Victoria Cornelius

In this project we are writing a series of article with collaborators which include in the first batch: 

  • The “Why” of safety analyses and adverse events collection in clinical trials

  • A guide for optimal analysis when dichotomising continuous adverse event outcomes

  • The important use of regression analysis for adverse event outcomes