Short Course 1: The Evolving Landscape of Real-World Data (RWD) and the Use of Pharmacoepidemiologic Methods and Machine Learning to Generate Credible Real-World Evidence (RWE)

概览

Real-world data availability (RWD) and utilization continue to evolve, bringing challenges and opportunities for evidence generation and assessment. This session includes primers on types of RWD, causal inference methods for estimating treatment effects, and the opportunities for incorporating machine learning methods. Speakers will discuss the future of RWD and effective communication of real-world evidence to stakeholders.

学习目标

At the conclusion of this short course, participants should be able to:

Describe the evolution of the RWD landscape
Define types of RWD and RWE use cases and appraise their importance
Recognize potential future RWD challenges and opportunities, including privacy, linkage and completeness
Explain the counterfactual and exchangeability principles as foundations of causal inference
Recognize key sources of confounding and time-related biases and their impact on treatment effect estimates
Describe best practices in retrospective cohort study design and data analysis
Introduce the concept of artificial intelligence/machine learning (AI/ML) methods and how they relate to pharmacoepidemiology, drug development and RWE
Explain the main differences in terminology and expertise required in AI/ML studies compared to established epidemiology and biostatistics
Provide examples of where AI/ML methods can benefit RWD use and research

Short Course 1: The Evolving Landscape of Real-World Data (RWD) and the Use of Pharmacoepidemiologic Methods and Machine Learning to Generate Credible Real-World Evidence (RWE)

概览

学习目标

获得信息并保持参与