Anonymize Clinical Trial Data Automatically with Anonymize DS Software
TrialAssure ANONYMIZE DS is an anonymization application for datasets that allows sponsors to anonymize all structured clinical trial data, including datasets and tables, with ease. This exclusive application is entirely configurable to sponsor specifications and architected to take advantage of machine learning capabilities.
TrialAssure ANONYMIZE DS has proven to be up to 80% more efficient than traditional anonymization tools and techniques.
With a simple design and rule builder function, ANONYMIZE DS saves sponsors time by allowing users to build a library of custom, reusable variables and reapply the same anonymization rules across studies. This saves valuable time and resources, especially with larger drug development pipelines where multiple studies share the same variables. As the library continually develops, the process becomes more efficient.
Once a sponsor determines which data fields to anonymize, the software will perform an analysis and assign a risk score. This analysis can be saved and replicated for future use, making the decision-making process easier.
ANONYMIZE DS is part of a fully-integrated suite of transparency tools, allowing information to be shared among health authorities without compromising patient privacy. ANONYMIZE DS also works closely with TrialAssure ANONYMIZE R – the anonymization application for reports and documents – using the same data rules, saving time and reducing discrepancies among related deliverables.
“In order to share data, it has to be done in a way that protects patient privacy. TrialAssure’s ANONYMIZE DS solves an industry-wide problem of balancing this need while maintaining the data’s utility.”
– Zach Weingarden
- Transforms original data into anonymized data using industry-standard techniques that Can be reused and customized for each dataset
- Assigns a risk score associated with the re-identification of this data based on thresholds set by the sponsor
- Is entirely configurable to sponsor specifications
- Was built from the ground up with input from data experts, and
- Drives efficiency with modern machine learning technology in mind