Best Practices for Causal Study Designs Using Real-World Data


Discussion Leader: Michael Grabner, PhD, Scientific Affairs, HealthCore, Inc., Wilmington, DE, USA
Discussants: Nilesh Gangan, PhD, HealthCore, Inc., Wilmington, DE, USA; Susan Dosreis, PhD, Department of Pharmaceutical Health Services Research, University of Maryland School of Pharmacy, Baltimore, MD, USA

PURPOSE: This workshop provides step-by-step guidance on the conduct of causal inference studies using observational real-world data (RWD), highlighting practical considerations, and illustrated with case study examples. Participants will use real-time voting to share their own experiences and take part in a knowledge assessment.

DESCRIPTION: Causal inference in observational research is growing more important, driven by the need for generalizable and rapidly delivered real-world evidence (RWE) to inform regulatory, payer, and patient/provider decision-making. Existing methodological literature on this topic – from the new-user, active comparator design to the adjustment of time-varying confounders – is rich but can be complex and daunting to navigate. It is important that appropriate measures to mitigate bias are incorporated both into the design and the analysis of causal inference studies using RWD.

Workshop participants with intermediate-level subject knowledge will be familiarized with concepts needed to successfully design causal inference studies using RWD. Dr Grabner will initiate the workshop highlighting the underlying need for explicit consideration of causal study design principles, introduce the best-practices documents that the authors have developed, and solicit feedback from participants on their level of comfort with causal methods and interpretations using RWD (~15-20 minutes). Afterwards, Dr Gangan will present step-by-step guidance in designing a causal RWD study, including selecting an estimand, creating a directed acyclic graph, identifying biases and corresponding solutions, and conducting sensitivity analyses (~15-20 minutes). Next, Dr dosReis will present case study examples of specific causal design/analytic issues and how they were addressed (or not addressed). Dr dosReis will also conduct the second part of the knowledge assessment and provide workshop conclusions (~15-20 minutes).

Besides real-time voting, there will be time for audience questions. In addition, the best-practices documents (consisting of a step-by-step guide to causal study design and a glossary of key terms) will be available to all participants.

Conference/Value in Health Info

2022-05, ISPOR 2022, Washington, DC, USA




Methodological & Statistical Research, Real World Data & Information Systems

Your browser is out-of-date

ISPOR recommends that you update your browser for more security, speed and the best experience on Update my browser now