On 21st June Vivli and Microsoft will be hosting an innovation challenge (datathons) on methods and technologies to perform privacy protective analysis on rare disease clinical trial datasets. The challenge will take place for a full day in Boston.
One of the difficulties with broadly sharing rare disease clinical trial datasets is that it is more difficult to do so in a privacy protective manner while still maintaining a high level of data utility. Hence, this challenge invites entrants to present new ideas and technologies that would make that possible and scalable.
In support of this challenge, Replica Analytics is preparing synthetic clinical trial datasets that the entrants can use as part of the competition. The fully synthetic datasets are all generated from real trials and will be provided to the entrants in a consistent manner to enable them to participate in the challenge. These synthetic data will use Replica's proprietary synthetic data generation methodology and engine, plus of course our deep expertise with clinical trial data.
The Vivli challenge is a good demonstration of what you can do with synthetic data to support efficient innovation at scale. Here we will be able to provide multiple teams with realistic data very quickly, allowing them to work on solving the problem at hand with minimal constraints.
You can get more information about this challenge from here: