PRIVACY IN MEDICAL DATA PUBLISHING

Privacy in data publishing concerns itself with the problem of releasing data to enable its study and analysis while protecting the privacy of the people or the subjects whose data is being released. The main motivation behind this work is the need to comply with HIPAA (Health Insurance Portability and Accountability Act) requirements on preserving patient’s privacy before making their data public. In this work, we present a policy-aware system that detects HIPAA privacy rule violations in medical records in textual format and takes remedial steps to mask the attributes that cause the violation to make them HIPAA-compliant.