Case Study: Global Biotechnology Company achieves fully automated, accurate data de-identification for safe analytics with PKWARE

Data Privacy and Protection at Global Biotech

Global Biotechnology Company, a California-based biotech with nearly 15,000 employees and roughly $2 billion in annual revenue, faced a complex data-protection challenge: dozens of project-specific data types (17 classifiers) and large third-party JSON/CSV feeds being ingested into a new data lake. They needed flexible, high-performance policies to find sensitive data (PHI/HIPAA), strict time-bound ingestion, minimal false positives in unstructured data, and an automated solution that would integrate with AWS and a designated solution provider. PKWARE was engaged to deliver discovery and protection capabilities using the PKWARE platform, policy builder, PKWARE APIs, and AWS services.

PKWARE built custom rules from out-of-the-box elements, fine-tuned policies to capture patient IDs and serial numbers with no false positives or false negatives, and automated the pipeline using PKWARE APIs and AWS Lambda, leveraging Amazon EMR and S3 to detect and mask data at scale. The result delivered by PKWARE was a fully automated, high-performance de-identification workflow that converted slow, manual processes into rapid, accurate operations and fed a protected “safe zone” data lake for analytics—enabling compliant, usable data for the company’s analytics team.