Replica Analytics Ltd., a leading provider of privacy protective synthetic data, is proud to announce that it is providing its data synthesis platform to PHUSE members. These data scientists can now synthesize health data using common statistical programming languages, and readily integrate synthesis within their current analytical pipelines. The synthetic data are non-identifiable variants of the original data.
Demand for health data in the life sciences industry is growing rapidly, which is partially driven by the rapid adoption of AI and machine learning methods by data science teams. This trajectory enables data driven innovation and discovery.
While this new capability through Replica Analytics is intended for non-commercial purposes, it allows members to experiment with the technology and start creating datasets and simulators that can be shared broadly within the community. The generative models created during synthesis can also be used as data simulators, augmenting small datasets and creating synthetic cohorts.
“The data synthesis platform will support our education mission by allowing members to learn state-of-the art technologies and start applying them to their current problems. Data transparency and data science are two key threads in our programs and this launch supports both.”
Stephen Bamford, Founder and Executive Director of PHUSE
“There is rapidly growing interest in data synthesis. The PHUSE synthesis platform moves that interest to real world application and makes it easy for members to experiment with the technology, learn how it works and where it can solve problems in their data science programs.”
Khaled El Emam, Co-Founder of Replica Analytics