CPRD Synthetic Data

Introduction

The RSF have access to the four synthetic datasets that CPRD offer. The overarching goal of this work package is to streamline the process for researchers using the real CPRD datasets. The RSF aims to expedite the creation of efficient data management and analytical pipelines. The RSF will work with CPRD and research collaborators with the AIM programme to test workflows written with synthetic datasets on the real datasets, to ensure transferability and utility. Documentation & code will be created and shared, in openly available languages (postgreSQL, Python, R).