Determining Optimal Study Design Utilizing Synthetic Data

Realistic data generation has become a hot topic in health research, especially to determine optimal randomized clinical trial design. A growing field of research is “virtual” trials, which are trials conducted through computer simulations to generate synthetic data such that the generated distribution mimics the original data distribution without simply copying the original observations. Especially in more complex trials with multiple treatment arms and treatments that can change over time, it would be of great benefit to study different iterations of study designs in a timely, efficient manner to determine which study design to implement in a full scale, real-life trial. However, there is a lack of consensus regarding how best to harness synthetic data to inform trial design, especially within the context of time-varying treatments that are commonplace in treating chronic illnesses. This project aims to develop a statistical framework for utilizing realistic synthetic trial data to inform optimal trial design. This work will be of value to both institutions, as governmental bodies in both places (North America and Europe) have recently provided guidelines to clinicians regarding implementing trials that utilize external (including synthetic) data.

Faculty Supervisor:

Erica Moodie

Student:

Partner:

Université Toulouse 1 Jean Jaurès

Discipline:

Mathematics

Sector:

Education

University:

McGill University

Program: