I-HDS (Institute for Healthcare Delivery Science) invites you to join its Seminar Series, today, Wednesday, March 2^nd at 12:00pm EST via Zoom Conferencing.

Our guest speaker will be Mireille Schnitzer, PhD, Associate Professor, Université de Montréal.

Biography:

Mireille Schnitzer is an Associate Professor of Biostatistics at the Université de Montréal. She holds a Canada Research Chair in Causal Inference and Machine Learning in Health Science. Mireille received her PhD in Biostatistics from McGill University in 2012 and was a postdoctoral researcher at the Harvard T.H. Chan School of Public Health in 2013. She also had the opportunity to study causal inference at U.C. Berkeley and the University of Pennsylvania as a visiting student. Mireille's current research interests are causal inference methodology in pharmacoepidemiology, semiparametric efficient estimation in longitudinal and survival settings with an emphasis on targeted maximum likelihood estimation, and individual participant data meta-analysis. Mireille currently holds an NSERC Discovery Grant and a CIHR Project Grant as PI, and is a co-investigator on multiple CIHR-funded health studies.

Background:

In this presentation, Dr. Schnitzer will demonstrate how the target trials approach can be used to define and estimate treatment effects when some patients may develop a contraindication and are thus ineligible to receive a treatment of interest during follow-up. Mireille will first describe a previous study involving contrasting the effects of different anticoagulant medications on major bleeding in patients with atrial fibrillation. Given this motivation, Mireille will explain the challenge of "positivity", which is the requirement that all subjects in an analysis be eligible for all treatments of interest conditional on their baseline covariates. She will present analyses of simulated datasets with violations of longitudinal positivity in order to explain how standard methods can produce misleading estimates of the effect of treatment on the outcome of interest. Mireille will then explain how one may define “treatment strategies,” such as “treat with medication unless contraindicated,” to overcome the problems linked to time-varying eligibility. She will then show how inverse probability of treatment weighting can be applied to estimate these effects.