deidentify - Clinical Data De-identification Tool
Remove PHI from clinical research data using regex and heuristics locally
Tags
Updated: 2026-05-28Capabilities
Typical Inputs
Typical Outputs
What this skill does
- detect PHI
- scan data files
- classify columns
- remove names
- replace identifiers
- shift dates
- generate pseudonyms
- create mapping file
- write audit log
Inputs
- CSV file
- Excel file
- TSV file
- locale code
- locale file
Outputs
- deidentified file
- mapping file
- audit log
- scan report
- reviewed report
Requirements
- Python 3.10+
- openpyxl