Real-world evidence has advanced health research over the past two or three decades. The challenges of procuring sufficient, high-quality real-world data, of unlocking the knowledge contained in the data, and of sharing information without compromising patient privacy are ever-present. Synthetic data, novel data sets that are created to reproduce the statistical properties and interrelationships of the source data, facilitate access to and sharing of real-world evidence on a broader and deeper scale. Self-service analytics allows exploration of data by the primary researchers, without requiring technical intermediaries or specialized knowledge of database structure. Taken together, synthetic data and self-service analytics have the potential to produce major advances in real-world data exploration.
Learning Objectives
-
Understand the concept of synthetic data, how synthetic data are generated, and how their use facilitates access to real-world, patient-level data without compromising patient privacy.
-
Understand how self-service analytics tools facilitate research by bringing primary researchers closer to the point of innovation, shortening the time to innovation and discovery.
-
Understand how the combination of synthetic data and self-service analytics synergistically creates a new model for real-world evidence.
Hosted by ISPOR; Sponsored by MDClone
