Seminar Series: Dr. Anna Heath
Bayesian Methods to Improve Clinical Trials for Children
Anna Heath
Associate Professor
Biostatistics Division
Dalla Lana School of Public Health
University of Toronto
Canada Research Chair
Statistical Trial Design
Senior Scientist
The Hospital for Sick Children
Honorary Research Fellow
University College London
Short Biography:
Dr. Anna Heath is a Senior Scientist at The Hospital for Sick Children (SickKids), Toronto, an Associate Professor at University of Toronto and Honorary Research Fellow at University College London, UK. She is the Canada Research Chair in Statistical Trial Design. She holds a degree in Mathematics with French language from the University of Sheffield, UK and a PhD in Statistical Science from University College London. She arrived at SickKids in 2018 to lead the development of innovative statistical methodology for four clinical trials for novel treatments in the paediatric emergency department. In 2020, she founded the EMBaRC lab to focus on developing novel statistical methodology, software, expertise and guidance to improve the efficiency and design of randomised clinical trials. This research combines many areas including biostatistics, evidence synthesis, meta-analysis, Bayesian methods, decision theory, health economic modelling and simulation based methods.
Abstract:
Enrolling children into clinical trials can be challenging due to the relative rarity of diseases, ethical challenges with enrolling children into trials and lower willingness to engage in research for children and their families. Thus, many interventions that are currently used in practice have not been tested appropriately in children. In fact, around 80% of medications used in children’s hospitals are used off-label, meaning that they have not been approved for that indication. Bayesian clinical trials can be more flexible than standard clinical trial designs and they can incorporate external information to reduce sample size requirements. As such, novel Bayesian designs can be developed to address these key challenges in paediatric clinical trials and provide feasible clinical trials to evaluate medical interventions for use in children.
This presentation will focus on two different designs that are currently being used to test interventions in children. Each design uses an alternative approach to improve the feasibility of these clinical trials. Firstly, we will discuss a novel method to rank interventions during the trial to determine the best intervention. This method is particularly useful when it is challenging to specify a “control” intervention as there is a great variation in current practice, which is common in paediatrics. We will then discuss a design that uses Bayesian hierarchical modelling to evaluate interventions when sample size is severely limited, e.g., for rare diseases, by combining information across rare and common diagnoses.
Area of Research:
Clinical Trials; Bayesian Methods; Decision Theory
Date: Friday, October 23
Time: 1:30 pm - 2:30 pm
Location: PHFM 3015 (Western Centre for Public Health and Family Medicine) or Zoom (request link by email epibio@uwo.ca )
