ctakes-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From digital paula <cybersat...@hotmail.com>
Subject RE: Question pertaining to HistoryOf and SegmentID features
Date Mon, 25 Nov 2013 19:13:45 GMT



Hi Pei,
 
Thanks so much for the prompt response.  
 
Question 1:   I forgot that one can use the Assertion or NE Contexts component, which are
used separately.    The Assertion component is what's including in the default Aggregate AE
and considered the preferred one.    I guess I could switch to NE contexts to get historyOf
then switch back to Assertion for everything else but that seems like a waste of time.   However,
I hope I'm just missing some switch or something and REALLY hope that some else can chime
in to explain how to get Assertion to provide the historyOf feature.    
 
Question 2:   Thanks or this reference to the HL7/CCDA sectionizer.   I know I should be getting
more experience w/UIMAfit but I jut like working with the XML descriptor since once created
it's easily added to the aggregate AE as part of the clinical pipeline.  Would you be able
to provide the XML descriptor or provide how to create it for the CCDA sectionizer?
 
Thanks.
 
Regards,
Paula
 
> From: Pei.Chen@childrens.harvard.edu
> To: user@ctakes.apache.org
> Subject: RE: Question pertaining to HistoryOf and SegmentID features
> Date: Mon, 25 Nov 2013 16:48:39 +0000
> 
> >1.)  In the CVD tool, depression is showing a subject of family_member which is correct.
 However hypertension is showing a historyOf: 0.     I'm using the clinical pipeline that
is setup in the AggregateAE by default.    Is there something that I need to add to the Assertion
component to be able to see patient history be denoted correctly?  I would expect to see with
the text "history of depression, for the patient" to show as 'historyOf:1'   
> I was still using the old StatusAnnotator for history/family history of.  I don't recall
where the new assertion AE is setting the history... perhaps someone else could chime in here.
> 
> >2.) In my sample text above I have two segments:  (History: and Current Diagnosis:)
 However the SegmentID features always shows:  SIMPLE_SEGMENT.  I would think that it should
have 'segmentID: History'  for the first sample text section and 'segmentID: Current Diagnosis'
for the second text sample.  Is there a way to make this happen?
> 
> Check out the HL7/CCDA sectionizer in the sandbox area:
> http://svn.apache.org/repos/asf/ctakes/sandbox/ctakes-sectionizer/
> It's a simple regex based annotator that will identify the different sections and normalize
them to HL7 template id's.  It hasn't gone into mainstream ctakes yet.
> Which uses a simple mapping file: http://svn.apache.org/repos/asf/ctakes/sandbox/ctakes-sectionizer/src/main/resources/org/apache/ctakes/core/sections/ccda_sections.txt
> 
> Thanks,
> Pei
> 
> From: digital paula [mailto:cybersation@hotmail.com] 
> Sent: Monday, November 25, 2013 11:26 AM
> To: user@ctakes.apache.org
> Subject: Question pertaining to HistoryOf and SegmentID features
> 
> Hello again cTakes Community,
>  
> Okay I have two questions this time and both pertain to the HistoryOf and SegmentID features.
>  
> Using this sample text:  
> History:  Patient has a history of hypertension and family history of depression.  
> Current Diagnosis:  Patient has CAD.  
>  
> 1.)  In the CVD tool, depression is showing a subject of family_member which is correct.
 However hypertension is showing a historyOf: 0.     I'm using the clinical pipeline that
is setup in the AggregateAE by default.    Is there something that I need to add to the Assertion
component to be able to see patient history be denoted correctly?  I would expect to see with
the text "history of depression, for the patient" to show as 'historyOf:1'   
>  
> 2.) In my sample text above I have two segments:  (History: and Current Diagnosis:) 
However the SegmentID features always shows:  SIMPLE_SEGMENT.  I would think that it should
have 'segmentID: History'  for the first sample text section and 'segmentID: Current Diagnosis'
for the second text sample.  Is there a way to make this happen?
>  
> Thanks.
>  
> Regards,
> Paula

 		 	   		  
Mime
View raw message