Keywords: Real world data, real world evidence, machine learning
Data from “real world” (RW) practice and utilization – outside of clinical trials – are regarded as a pragmatic source of evidence with high potential to support clinical development and life cycle management of medical products. US and EU regulatory agencies, public-private partnerships and health technology assessment organizations have launched major initiatives to address the concerns and considerations in the use of real world evidence (RWE) to inform regulatory and reimbursement decision making. Recent publications have put forth the challenges and presented potential scenarios where RWE may be considered as part of the evidence package in support of regulatory decisions and fulfil the evidence needs for payers, providers, and patients. However, many challenges remain, from the quality of the data to the appropriate application of research methods to translate RW data (RWD) to robust RWE. In order to improve the confidence in decision making from such research, there is a need to improve 1) quality of data and linking of data sources; 2) observational study designs; 3) statistical methodologies; 4) the role of artificial intelligence and machine learning in RW research; and 5) transparency, standardization, and validation. In this talk, we will discuss the areas in RWE research where quantitative approaches could be applied.