Mayo clinical Text Analysis and Knowledge Extraction System (cTAKES): architecture, component evaluation and applications
- Guergana K Savova1,
- James J Masanz1,
- Philip V Ogren2,
- Jiaping Zheng1,
- Sunghwan Sohn1,
- Karin C Kipper-Schuler1,
- Christopher G Chute1
- 1Division of Biomedical Statistics and Informatics, Mayo Clinic College of Medicine, Rochester, Minnesota, USA
- 2Computer Science Department, University of Colorado, Denver, Colorado, USA
- Correspondence to Guergana Savova, Children's Hospital Informatics Program, Children's Hospital Boston and Harvard Medical School, 300 Longwood Avenue, Enders 138, Boston, MA 02115, USA;
- Received 30 October 2009
- Accepted 29 June 2010
We aim to build and evaluate an open-source natural language processing system for information extraction from electronic medical record clinical free-text. We describe and evaluate our system, the clinical Text Analysis and Knowledge Extraction System (cTAKES), released open-source at http://www.ohnlp.org. The cTAKES builds on existing open-source technologies—the Unstructured Information Management Architecture framework and OpenNLP natural language processing toolkit. Its components, specifically trained for the clinical domain, create rich linguistic and semantic annotations. Performance of individual components: sentence boundary detector accuracy=0.949; tokenizer accuracy=0.949; part-of-speech tagger accuracy=0.936; shallow parser F-score=0.924; named entity recognizer and system-level evaluation F-score=0.715 for exact and 0.824 for overlapping spans, and accuracy for concept mapping, negation, and status attributes for exact and overlapping spans of 0.957, 0.943, 0.859, and 0.580, 0.939, and 0.839, respectively. Overall performance is discussed against five applications. The cTAKES annotations are the foundation for methods and modules for higher-level semantic processing of clinical free-text.
The annotation guidelines will be made available at http://www.ohnlp.org after manuscript publication. The clinical corpus created from Mayo Clinic notes is not released with cTAKES. For model-building purposes, that corpus was anonymized per Safe Harbor Health Insurance Portability and Accountability Act76 guidelines. Technical details and discussions on technical topics related to cTAKES are posted on the Forums at http://www.ohnlp.org.
Funding The work was partially supported by a 2007 IBM UIMA grant.
Provenance and peer review Not commissioned; externally peer reviewed.