Causal inference for real-world evidence
July 2022
What is causal inference?
Causal inference is used to answer cause and effect research questions and yield estimates of effect. These study design considerations and statistical methods address the effects of confounding variables and other potential biases, and allow researchers to answer questions such as, “Does Treatment A produce better patient outcomes compared to Treatment B?”
Why is it important?
Causal study interpretations have traditionally been restricted to randomized controlled trials; however, causal inference applied to observational data is growing in importance, driven by the need for generalizable and rapidly delivered real-world evidence to inform regulatory, payer, and patient or provider decision-making. The application of causal inference methods leads to stronger and more powerful evidence, and when these techniques are applied to observational data, the results generated are both from and for the real world.
Case study
A life sciences client wanted to know whether patients with type 2 diabetes (T2D) taking a specific GLP-1 RA agent were more adherent and persistent relative to other antidiabetic medications.
- In a real-world evidence study, Carelon Research (formerly HealthCore) used claims data to compare six-month adherence, persistence, and treatment patterns of patients with T2D using three different GLP-1 RA agents.
- Researchers selected adults with T2D using any of the three medications between February 2018 and December 2018, without prior use of a similar antidiabetic medication in the previous six months
(August 2017 to January 2018). - Researchers at Carelon Research created a study design allowing for causal inference. They selected an active comparator, new user population, and employed multiple forms of matching to balance patient characteristics at the time of medication initiation for a more equivalent comparison.
- The study team found that a higher proportion of patients initiating the specific GLP-1 RA agent were adherent to and persistent with their treatment, compared to matched patients initiating either of the other medications.
Critical components for causal inference
Causal inference with observational data combines numerous theoretical and technical concepts, necessitating specialized training and competency. Researchers within the health economics & outcomes research and safety & epidemiology research teams at Carelon Research offer highly specialized scientists, access to a robust source of integrated real-world data, and decades of experience necessary for successfully employing these methods.
Our experienced scientists can collaborate with your team to curate the most appropriate research questions and identify the optimal study design and analytic approach to address your specific needs. Whether working to satisfy regulatory requirements or generating evidence regarding an important public health concern or any other creative scientific endeavor, Carelon Research can help you find evidence and truth at the core of healthcare.
“Causal inference applied to observational data is growing in importance, driven by the need for generalizable and rapidly delivered real-world evidence to inform regulatory, payer, and patient or provider decision-making.”
— Michael Grabner, PhD
