Configuring Privacy Policies
Select and customize OpenMed's seven bundled privacy policy profiles for...
Install
npx skills add maziyarpanahi/openmed --skill configuring-privacy-policies -g -a claude-code -y- Repository
- maziyarpanahi/openmed5.8k
- Category
- Data and ML
- Updated
- 4d ago
- License
- Apache-2.0
- Context cost
- Mediumabout 1,919 tokens
- Runs scripts
- No, instructions only
What it does
Select and customize OpenMed's seven bundled privacy policy profiles for de-identification, and build custom surrogate generators. Use when the user asks which policy fits HIPAA Safe Harbor vs Expert Determination vs GDPR vs PIPEDA vs a research limited dataset vs strict no-leak, wants to pass policy= to deidentify(), needs to keep quasi-identifiers for research, or must register a custom MRN/name/address surrogate provider. Covers the profile-to-use-case map, AnonymizerConfig/Anonymizer for fine control, and register_clinical_provider / register_label_generator. Pairs with OpenMed deidentifying-clinical-text and generating-synthetic-surrogates.
Configuring privacy policies
A policy profile is a named bundle of de-identification decisions: which
action (mask/redact/replace/keep) applies to each label, how aggressively
detectors arbitrate, whether the mandatory safety sweep runs, and whether a
reversible mapping is produced. OpenMed ships seven profiles. Pass one by name
to deidentify(policy=...) and you get a compliance-aligned default without
hand-wiring 50+ per-label actions. Everything runs on-device.
When to use this skill
Use it to pick the right policy= for a regulatory context, to understand what
a profile actually changes, or to go beyond the bundle, keeping quasi-
identifiers for research, or registering a custom surrogate generator (e.g. your
own MRN format).
Quick start
import openmed
note = "Jane Roe, DOB 1979-04-11, lives in Cambridge MA 02139. SSN 123-45-6789."
# HIPAA Safe Harbor: mask every identifier class.
safe = openmed.deidentify(note, policy="hipaa_safe_harbor")
# GDPR pseudonymization: replace with fakes AND keep a reversible mapping.
gdpr = openmed.deidentify(note, policy="gdpr_pseudonymization")
mapping = gdpr.mapping # present because the profile sets keep_mapping=True
# Research limited dataset: mask direct identifiers, KEEP quasi-identifiers
# (dates, age, ZIP, geography) so the data stays analytically useful.
lds = openmed.deidentify(note, policy="research_limited_dataset")
The seven bundled profiles
Each profile lives in openmed/core/policies/<name>.json. Summary of what each
actually configures:
