cTAKES on Ivy Linux VMs

cTAKES Overview

cTAKES or The clinical Text Analysis and Knowledge Extraction System, is a Mayo Clinic developed Natural Language Processing (NLP) tool used to
extract information out of clinical records. It is open-source, and built on the Apache Unstructured Information Management Architecture. cTAKES
is modular, expandable, for a number of generic use cases, and contains excellent best practice notes.

cTAKES Usage

cTAKES components

Some of cTAKES components are listed below:

  • Sentence boundary detection (OpenNLP technology)
    *Tokenization (rule-based)
  • Morphologic normalization (NLM’s LVG)
  • POS tagging (OpenNLP technology)
  • Shallow parsing (OpenNLP technology)
  • Named Entity Recognition
  • Negation and context identification (both based on NegEx)

cTAKES Named Entities

cTAKES contains the following Named Entities:

  • Drug mentions
  • Disease/disorder mentions
  • Sign/symptom mentions
  • Anatomical site mentions
  • Smoking status classifier
  • Detailed drug mention annotator
  • Peripheral Artery Disease (PAD) annotator
  • Dependency parser

cTAKES Installation

Please note that cTAKES requires pre-installation approval by us. Please consult us prior to requesting a new VM regarding your cTAKES requirements.

More Information

For more information on cTAKES, and how to use it, please visit the following links: