THIS IS A TEST INSTANCE. ALL YOUR CHANGES WILL BE LOST!!!!
The following typographical styles are used:
- Monospace text indicates file system paths or file names.
- <Monospace text in angle brackets> indicates any part of text that you type in which must be replaced with something else, for example, file system paths or file names, to match your configuration or your preference.
- Bold monospace text indicates a command that you need to type on the command line or a system path or file name that needs to be replaced. Command line arguments for which you need to substitute a value are surrounded by angle brackets. For long commands you might see a caret symbol (^ Windows) or a backslash symbol (\ Linux) dividing lines of the command. This allows the command to be cut and pasted across multiple rows. An operating system icon is used to distinguish between the two.
For example,
java -cp <classpath> edu.mayo.uima.Class <arg1> <arg2>
Where:
<classpath> is the absolute path to the class being executed
<arg1> is an argument
<arg2> is another argument
Other conventions
| Code Block | ||
|---|---|---|
| ||
Monospace text enclosed in a box of this style
indicates contents in a file. |
| Info |
|---|
A box like this provides additional information or remarks. |
| Note |
|---|
A box like this denotes an important part of the steps not to miss. |
are not part of Apache cTAKES but may be of interest to cTAKES users.
| Name | When used | Site | Description | License | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Anafora | github.com/weitechen/anafora | web-based raw text annotation tool | https://github.com/weitechen/anafora#download-anafora | ||||||||||||||||
| Annotation Viewer | post | github.com/GeisingerBTI/AnnotViewer | view cTAKES' annotations from XMIs in a batch | https://github.com/GeisingerBTI/AnnotViewer/blob/master/LICENSE | |||||||||||||||
| Command line tool | wrapper | github.com/giuseppetotaro/ctakes-clinical-pipeline | run the complete pipeline for annotating clinical documents in plain text format using the built in UMLS (SNOMEDCT and RxNORM) dictionaries from a command line | https://github.com/giuseppetotaro/ctakes-clinical-pipeline#license | |||||||||||||||
| Command line tool | wrapper | github.com/dmitriydligach/ctakes-misc | a simple pipeline that involves dictionary lookup. Mentioned in this post to dev@. | unknown | |||||||||||||||
| Hadoop, cTAKES integration | github.com/pcodding/hadoop_ctakes | allows cTAKES to be invoked on clinical document data presented as Tuples to cTAKES | https://github.com/pcodding/hadoop_ctakes/blob/master/LICENSE | ||||||||||||||||
| MIST | pre | mist-deid.sourceforge.net/ | a suite of tools for identifying and redacting
| See "What license does it have?" on | |||||||||||||||
| RESTful interface | wrapper | github.com/dirkweissenborn/ctakes-server | a simple REST-server around ctakes clinical pipeline | unknown | |||||||||||||||
| Tika, cTAKES integration | wiki.apache.org/tika/cTAKESParser | detects and extracts from over a thousand different file types | http://www.apache.org/licenses/ | ||||||||||||||||
UMLS and NLM tools such as | www.nlm.nih.gov/research/umls/implementation_resources/ | NLM applications utilize UMLS data | https://uts.nlm.nih.gov//license.html |
Definitions
PII = personally identifiable information
MIST = MITRE Identification Scrubber Toolkit
NLM = U.S. National Library of Medicine
UMLS = Unified Medical Language System
...