Skip to main content

CRATE: clinical records anonymisation and text extraction

Project description


Create and use de-identified databases for research.

  • Anonymises relational databases.

  • Extracts and de-identifies text from associated binary files.

  • Performs some specific preprocessing tasks; e.g.

    • preprocesses some specific databases (e.g. Servelec RiO EMR);

    • drafts a “data dictionary” for anonymisation, with special knowledge of some databases (e.g. TPP SystmOne);

    • fetches some word lists, e.g. forenames/surnames/eponyms.

  • Provides tools to link databases, including via Bayesian personal identity matching, in identifiable or de-identified fashion.

  • Provides a natural language processing (NLP) pipeline, including built-in NLP, support for external tools, and client/server support for the Natural Language Processing Request Protocol (NLPRP).

  • Web app for

    • querying the anonymised database;

    • providing a de-identification API;

    • managing a consent-to-contact process.





  • Copyright (C) 2015, University of Cambridge, Department of Psychiatry. Created by Rudolf Cardinal (

  • Licensed under the GNU GPL v3+: see LICENSE file.

  • Some third-party libraries have slightly different licences; see the documentation.

Project details

Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

crate-anon-0.20.4.tar.gz (89.7 MB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page