| name | hipaa-compliance-auditor |
| description | Automatically detect and de-identify PII (Personal Identifiable Information) and PHI (Protected Health Information) from clinical/medical text to ensure HIPAA compliance. Trigger when processing medical records, patient data, clinical notes, insurance information, or any healthcare-related text containing potential patient identifiers. |
| version | 1.0.0 |
| category | Clinical |
| tags | [] |
| author | AIPOCH |
| license | MIT |
| status | Draft |
| risk_level | Medium |
| skill_type | Tool/Script |
| owner | AIPOCH |
| reviewer | |
| last_updated | 2026-02-06 |
HIPAA Compliance Auditor
A clinical-grade PII/PHI detection and de-identification tool for healthcare text data.
Overview
This skill analyzes text for HIPAA-protected identifiers and automatically redacts or anonymizes them. It uses a combination of regex patterns, NLP entity recognition, and contextual analysis to identify 18 HIPAA identifier categories.
Features
- 18 HIPAA Identifiers Detection: Names, dates, SSN, MRN, phone/fax, email, geographic data, etc.
- Automatic De-identification: Replace PII with semantic tokens (e.g.,
[PATIENT_NAME], [DATE_1])
- Context-Aware Detection: Distinguishes between similar patterns (dates vs. lab values)
- Audit Logging: Track all redaction actions for compliance documentation
- Confidence Scoring: Flag uncertain detections for manual review
Usage
Command Line
python scripts/main.py --input "patient_text.txt" --output "deidentified.txt"
python scripts/main.py --text "Patient John Doe, SSN 123-45-6789..." --audit-log audit.json
Python API
from scripts.main import HIPAAAuditor
auditor = HIPAAAuditor()
result = auditor.deidentify("Patient John Doe was admitted on 2024-01-15...")
print(result.cleaned_text)
print(result.detected_pii)
Parameters
| Parameter | Type | Default | Required | Description |
|---|
--input, -i | string | - | No | Path to input text file |
--text | string | - | No | Direct text input (alternative to file) |
--output, -o | string |
