Statistical Consideration for Fit-for-Use Real-World Data to Support Regulatory Decision Making in Drug Development

ABSTRACT

A Real-World Evidence (RWE) scientific working group of the American Statistical Association Biopharmaceutical Section has been reviewing the statistical considerations for the generation of real-world evidence to support regulatory decision making. As part of the effort, the working group is addressing the fitness-for-use of real-world data (RWD). RWD may be used in a variety of ways and study designs including in randomized studies, externally controlled studies, and purely observational studies. The use of RWD poses unique issues surrounding study integrity, transparency, and reproducibility. Rule-based methods and machine learning approaches can be used to extract key data elements from RWD sources. In some cases, multiple sources of data may be linked to obtain the necessary study data. Missing data may have unique considerations in the RWD sources, since data elements are collected for the practice of medicine and are not protocol driven. Lack or imperfect capture of some information in an RWD source may lead to multiple biases that threaten the fitness-for-use of an RWD source, including information bias, selection bias, and confounding. Validation studies and quantitative bias assessment can be used to assess the potential bias. The working group proposes a data-driven approach framework for determining the fit-for-use of RWD.

KEYWORDS:

• Confounding
• Fit-for-use real-world data
• Machine learning
• Missing data
• Rule-based methods

Funding

The author(s) reported there is no funding associated with the work featured in this article.