Associate Professor of Biostatistics Northeastern University Boston, Massachusetts, United States
Abstract: Advanced computational approaches to handle and make sense of the massive amounts of data generated related to health play an increasing role in how educational programs and academic research can make impact in healthcare and life sciences.
Real-World Data (RWD), defined as routinely collected data relating to a patient’s health status and/or the delivery of care, is collected through a variety of sources such as electronic health records, medical billing claims, and disease and patient reported outcomes, creating several challenges and opportunities. While randomized control trials remain the gold standard for clinical evidence generation, RWD is increasingly being capitalized on and relied upon throughout the entire drug-development pipeline including marketing, research and development, and post-marketing safety surveillance of therapeutics. Healthcare systems use RWD to monitor patient care, quality, and value and regulatory agencies continue to expand the use of RWD in the regulatory approval process, in addition to modern approaches to safety surveillance.
While the uses of these types of data have expanded greatly over the last decade, RWD poses many computational and statistical challenges to ensure we extract valid inferences and predictions from these rich data. Through a series of examples, I will demonstrate how Real-World Data can be used to impact healthcare and clinical decision making and discuss how RWD is prompting the development of new academic opportunities.
