vmenger/deduce

Deduce: de-identification method for Dutch medical text

63
/ 100
Established

This tool helps researchers and healthcare professionals anonymize Dutch medical text by automatically detecting and removing sensitive patient information. You provide it with clinical notes or reports in Dutch, and it gives you a version where personal details like names, dates, locations, and identifiers are replaced with generic tags. It's designed for anyone working with Dutch medical data who needs to protect patient privacy for research, data sharing, or compliance.

Available on PyPI.

Use this if you need to quickly and accurately de-identify protected health information (PHI) from large volumes of clinical text written in Dutch.

Not ideal if your primary goal is to achieve perfect anonymity, as de-identification inherently mitigates risk rather than guarantees complete anonymity.

medical-research patient-privacy healthcare-data-management clinical-text-analysis data-anonymization
Maintenance 10 / 25
Adoption 8 / 25
Maturity 25 / 25
Community 20 / 25

How are scores calculated?

Stars

64

Forks

27

Language

Python

License

GPL-3.0

Last pushed

Feb 10, 2026

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/vmenger/deduce"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.