CRATE: Clinical Records Anonymisation and Text Extraction

Created by Rudolf Cardinal. Currently developed by Rudolf Cardinal and Martin Burchell. See contributors.

Note

If you’re a clinician or a researcher using a CRATE web site to explore a research database, see the Overview for clinicians and researchers.

Contents:

• 1. Overview
• 2. Package elements in brief
  • 2.1. Terminology
  • 2.2. Database connections
  • 2.3. Preprocessing
  • 2.4. Data dictionary generation and editing
  • 2.5. Anonymisation
  • 2.6. Natural language processing (NLP)
  • 2.7. Linkage
  • 2.8. Web front end
  • 2.9. Testing and additional tools
• 3. Reference publications
• 4. Installing CRATE
  • 4.1. Firewall setup
  • 4.2. Installing and running CRATE via Docker
  • 4.3. Installing CRATE
  • 4.4. Databases and database drivers
  • 4.5. Upgrading CRATE
• 5. Preprocessing tools
  • 5.1. crate_preprocess_pcmis
  • 5.2. crate_preprocess_rio
  • 5.3. crate_preprocess_systmone
  • 5.4. crate_postcodes
  • 5.5. crate_fetch_wordlists
• 6. Anonymisation
  • 6.1. Overview of anonymisation
  • 6.2. Data and database prerequisites
  • 6.3. The anonymiser config file
  • 6.4. Data dictionary (DD)
  • 6.5. Run the anonymiser
  • 6.6. Specific databases
  • 6.7. Using CRATE’s anonymisation API web server
  • 6.8. Anonymisation API documentation
• 7. Natural language processing (NLP)
  • 7.1. Overview of NLP
  • 7.2. NLP config file
  • 7.3. Testing NLP
  • 7.4. Run the NLP
  • 7.5. CRATE’s Python regex NLP
  • 7.6. GATE NLP applications
  • 7.7. MedEx-UIMA drug NLP
  • 7.8. Natural Language Processing Request Protocol (NLPRP)
  • 7.9. NLPRP web server
• 8. Configuring the CRATE web interface
  • 8.1. Web site components
  • 8.2. Configuring the web front end
  • 8.3. Web config file
  • 8.4. Manage the CRATE web server
  • 8.5. Launch the CRATE web server
  • 8.6. Configuring for Apache
  • 8.7. Launch Celery
  • 8.8. CRATE Windows service
• 9. Using the CRATE web interface
  • 9.1. Overview for clinicians and researchers using the CRATE web interface
  • 9.2. Database structure
  • 9.3. Research queries
  • 9.4. Standard site queries
  • 9.5. SQL helpers
  • 9.6. Patient Explorer queries
  • 9.7. Privileged functions for clinicians
  • 9.8. Archive view
  • 9.9. Contacting patients about research studies
  • 9.10. Research Database Manager functions
  • 9.11. Developer functions
• 10. Ancillary tools
  • 10.1. crate_help
  • 10.2. crate_make_demo_database
  • 10.3. crate_test_extract_text
  • 10.4. crate_test_anonymisation
  • 10.5. crate_email_rdbm
• 11. FAQs and troubleshooting
  • 11.1. Known bugs elsewhere affecting CRATE
  • 11.2. General
  • 11.3. CRATE anonymiser
  • 11.4. CRATE NLP
  • 11.5. CRATE web site
  • 11.6. MySQL
  • 11.7. SQL Server
  • 11.8. Windows
  • 11.9. MedEx-UIMA
• 12. Linkage tools
  • 12.1. Linkage: overview
  • 12.2. crate_bulk_hash
  • 12.3. crate_fuzzy_id_match
• 13. Additional notes
  • 13.1. Testing
  • 13.2. Technical notes
  • 13.3. Common relevant TCP/IP ports
  • 13.4. External dependencies
  • 13.5. Calling Python from SQL Server
  • 13.6. Using SemEHR
• 14. Automatic documentation of source code
  • 14.1. crate_anon/anonymise
  • 14.2. crate_anon/common
  • 14.3. crate_anon/crateweb
  • 14.4. crate_anon/linkage
  • 14.5. crate_anon/nlp_manager
  • 14.6. crate_anon/nlp_webserver
  • 14.7. crate_anon/preprocess
  • 14.8. crate_anon/tools
• 15. Index of CRATE commands
• 16. Licences
  • 16.1. CRATE
  • 16.2. GATE-related code
  • 16.3. US name frequency data
  • 16.4. UK postcode-related data
• 17. Change log/history
  • 17.1. Contributors
  • 17.2. Changes
  • 17.3. To do
• 18. Things to do
• 19. Abbreviations
• 20. Glossary

Indices and tables

• Index

• Search Page