cTAKES (Clinical Text Analysis and Knowledge Extraction System)
cTAKES processes clinical notes and identifies types of clinical named entities – drugs, diseases/disorders, signs/symptoms, anatomical sites and procedures. Each named entity has attributes for the text span, the ontology mapping code, whether the named entity is negated, and the context (family history of, history of, probable). cTAKES also includes a smoking status classifier, a coreference resolver, and a physician-asserted drug side effect annotator. cTAKES is licensed under Apache License, Verson 2.0, and is built on top of the UIMA framework. cTAKES relies on GUIs provided by UIMA.
- Apache cTAKES 3.0.0 (incubating) - includes relation extractor
- cTAKES 2.5 (See Apache cTAKES for the latest version) - includes a new attributes (assertion) extractor, a semantic role labeler, an additional sectionizer, updates to the coreference resolver, and an updated part-of-speech model
- cTAKES 2.0 - includes changes to the Type System which is central to cTAKES. It also includes a new tokenizer, which implements Penn Treebank tokenization rules
- cTAKES 1.3 - cTAKES now includes bundled SNOMED CT and RxNorm dictionaries, a constituency parser, and a coreference resolver
- cTAKES 1.2 - complete rewrite of the documentation, introduction to integrated cTAKES
At a Glance Details
- Apache cTAKES 3.0.0 (incubating), February 2013
- Installation Level: Intermediate to Advanced
- System Requirements: Installation requires several GBs of disk space. Some components can be run with 512MB RAM but some require 2GB RAM.
Presentations, Demos and Other Materials
Documentation and Training
Latest Release Documentation
cTAKES 2.5 and Earlier Documentation
Asking Questions about this Tool
- Mailing lists at apache.org are the preferring method for asking questions.
- You can search the cTAKES forums for historical information for cTAKES 2.5 and earlier.