Blur
Built by Pharma. For Pharma.

Blur

Life Science Data & Document Anonymization with NLP Automation

Insource innovation with the #1 tool for anonymization and quantifiable risk measurement.  Built in collaboration with enterprise pharmaceutical sponsors, Blur is the efficient solution for scaling anonymization and quantitative risk.  With its user centered design, risk assessment engine and NLP capabilities, Blur is the tool dozens of sponsors have chosen to share clinical data and associated documents consistently.

How Can Blur Help You?

Request a Demo

Blur

Product Features

Insource Blur software into your organization and begin sharing on any scale. Blur offers the following key features:

  • Support for EMA 070, Health Canada, HIPAA, and CDISC standards
  • UX menu-driven functionality
  • No SAS programmers needed
  • Fully authenticated and maintained product
  • Audit trail with built-in workflow review
  • Summarized documentation reports
  • Automated data configuration
  • Structured UI supporting risk simulation
  • Customizable risk target parameters

What makes Blur different?

Based on a study’s specific population and/or entire therapeutic populations, the most practical approach for sponsors, Blur runs thousands of permutations optimizing risk through advanced anonymization techniques. By automating sponsors sharing processes and assessing re-identification risk, Blur balances sharing aspirations against constraints faced by global sponsors.  This refined design obtained from iterative feedback, has led Blur to become the most used and trusted tool to accelerate sharing in Life Sciences. Using NLP, Blur can be trained to automate sharing.

“We wanted to expand the availability of patient clinical trial data, doing our part to drive medical innovation. Blur is the tool we needed to streamline our processes and maintain the utmost quality of sensitive patient data being released to the public.”- Global Pharmaceutical, Chief Privacy Officer
  • Risk Measurement Complex

  • Agencies Pressure to Anonymize

  • Manual Approaches Not Scalable