You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 5 Next »

The default configuration of Dictionary Lookup uses an hsqldb database containing terms and normalized codes (CUIs).  Dictionary databases containing typically desired information from the UMLS are available at sourceforge .

However, there may be cases for which the standard dictionaries are not applicable.  For this reason cTAKES has a GUI that can assist in the creation of custom dictionaries.  The GUI currently only allows the most basic customization: Desired source vocabularies, semantic types, and additional vocabulary codes of interest.  

    *Greater customization is available, but requires the editing of property files and is outside the scope of this document.

 

Step-by-step guide

  1. From a command-line in the cTAKES root directory, execute:   bin\runDictionaryCreator
      

  2. Select a cTAKES installation directory.  The default directory should be correct.
  3. Select a UMLS installation directory.  This is the directory containing RRF files in the META/ subdirectory. 
    After selecting the UMLS installation directory, the available vocabularies are gathered.
      
  4. Select Source Vocabularies.  Source vocabularies contain CUIs that interest you.
  5. Select Target Vocabularies.  The dictionary will contain target vocabulary codes.
  6. Select Semantic Types.  The standard cTAKES types are selected by default.
  7. Type a Dictionary Name.  Use all lower case.
  8. Click Build Dictionary.

 

Once a new dictionary has been build, point to it in one of 2 ways:

Set the fast dictionary parameter LookupXml to org/apache/ctakes/dictionary/lookup/fast/DictionaryName/DictionaryName.xml

or

Set the runClinicalPipeline or runPiperFile command-line parameter -l to org/apache/ctakes/dictionary/lookup/fast/DictionaryName/DictionaryName.xml

  • No labels