NegBio documentation

NegBio is a high-performance NLP tool for negation and uncertainty detection in radiology reports.

Beloved Features

• Patterns on both universal dependency graph and regular expressions
• Creating user patterns
• Transparency
• Multiprocessing

NegBio officially supports Python>=3.6.

These instructions will get you a copy of the project up and run on your local machine for development and testing purposes. The package should successfully install on Linux (and possibly macOS).

The User Guide:

• Installation of NegBio
  • Prerequisites
  • Installation of MetaMap
  • Getting the source code
• Quickstart
  • Preparing the dataset
  • Running NegBio
• Advanced Usage
  • Running the pipeline step-by-step
  • General arguments
  • Convert text files to BioC format
  • Normalize reports
  • Split each report into sections
  • Splits each report into sentences
  • Named entity recognition
    • Using MetaMap
    • Using vocabularies
  • Parse the sentence
  • Convert the parse tree to UD
  • Detect negative and uncertain findings
    • Patterns on the dependency graph
    • Regular expression patterns
  • Cleans intermediate information
• NegBio Developer Guide
  • Create this documentation
  • Testing the code
• License
• Contributing
• Maintainers
• Acknowledgments
• Disclaimer
• Reference

Indices and tables

• Index
• Module Index
• Search Page