Re: polarity tag in output for mention/concept. [EXTERNAL] [SUSPICIOUS] [SUSPICIOUS]

[Kathy Ferro]

Tim and Sean,

I think I spoke too soon. Don't know why it didn't work the 1st few times I
ran it.

I changed both to 20.  Looks like we are safe here; looks like it's 20 to
the left/right within the same sentence because the term "right breast" is
positive.








*my sample text:A Regional Med Center This should not interfere with ROS
section: denies fatigue, malaise, fever, weight lossMDM/ED
CourseImaging:The patient underwent an ultrasound-guilded core needle
biopsy with clip pacement of the 2.3cm mass in the upper outer quadrant of
the right breast.ROS: Heme/Lymphatic: denies easy or excessive bruising,
history of blood transfusions, anemia, bleeding disorders, adenopathy,
chills, sweatsAllergic/Immunologic: denies urticaria, hay fever, frequent
UTIs; denies HIV high risk behaviors*
Here's how I run it.  Is there a better way to run it?

I made a copy of runPipeFile.bat and added:

@rem -
set *FAST_PIPER*
=resources\org\apache\ctakes\clinical\pipeline\FastPipeline1.piper
java -Dctakes.umlsuser="myUser" -Dctakes.umlspw="myPW" -cp "%CLASS_PATH%"
%LOG4J_PARM% -Xms512M -Xmx3g %PIPE_RUNNER% -p %*FAST_PIPER*% %* -i
C:\Projects\NLPinbound --xmiOut C:\Projects\NLPoutbound  -l
org/apache/ctakes/dictionary/lookup/fast/aa_5.xml
:end


I am thrill with this discovery.
Thanks for your help.
Kathy


On Tue, Nov 28, 2017 at 2:05 PM, Finan, Sean <
sean.fi...@childrens.harvard.edu> wrote:

> Thanks Tim,
>
> "Negation's Not Solved" :^)
>
> -Original Message-
> From: Miller, Timothy [mailto:timothy.mil...@childrens.harvard.edu]
> Sent: Tuesday, November 28, 2017 2:01 PM
> To: dev@ctakes.apache.org
> Subject: Re: polarity tag in output for mention/concept. [EXTERNAL]
> [SUSPICIOUS] [SUSPICIOUS]
>
> I'll just point out -- the kind of examples Kathy gave were the bane of
> our existence while working on the ML-based assertion system. Even though
> it is obvious what is going on to a human it was hard to encode as a
> feature in a way that was learnable. But I think most rule-based algorithms
> will also run into problems with this type of example eventually if they
> have a hard-coded scoping mechanism (e.g., scope extends up to 10 words to
> the right). If you make it larger than you may increase the number of false
> positives your algorithm finds (confusingly, here a false positive is an
> example the algorithm calls negated that is not actually being negated).
> Tim
>
>
> On Tue, 2017-11-28 at 17:22 +, Finan, Sean wrote:
> > Hi Kathy,
> >
> > I am glad that you checked the wiki!  I should have pointed to it ...
> >
> > In the example I sent the "relevant distance" between trigger terms
> > and events would be 10.  There isn't any maximum as far as I know, but
> > I think that 10 is the most that I've ever used.  The default is 7,
> > and you can try with that (remove "*=*") before increasing the
> > number(s).
> >
> > The piper files aren't source code, they are just plain text and don't
> > require compiling, etc.  How are you running the pipeline right now?
> > From a binary with a bin/run* script?
> >
> > Sean
> >
> >
> > -Original Message-
> > From: Kathy Ferro [mailto:healthcare1...@gmail.com]
> > Sent: Tuesday, November 28, 2017 12:11 PM
> > To: dev@ctakes.apache.org
> > Subject: Re: polarity tag in output for mention/concept. [EXTERNAL]
> >
> > Sean,
> >
> > Thank you for information.
> >
> > I was reading the document.  So, the MaxLeftScopeSize and
> > MaxRightScopeSize are limit up to 10?  Is there anyway to adjust it
> > without modify the source code?
> >
> > https://urldefense.proofpoint.com/v2/url?u=https-3A__cwiki.apache.org
> > _confluence_display_CTAKES_cTAKES-2B4.0-2B-2D-2BNE-
> > 2BContexts=DwIBaQ=qS4goWBT7poplM69zy_3xhKwEW14JZMSdioCoppxeFU=f
> > s67GvlGZstTpyIisCYNYmQCP6r0bcpKGd4f7d4gTao=4K9fxMmBiI0QZB0UhriFp_Yv
> > XDL8rmXtGRiKVgxMCPE=hsCB9xPXLC8fpiwrGXuEW9snw_WZbY0e-E-mhPOO9N8=
> >
> >
> > Thanks again,
> > Kathy
> >
> >
> >
> > On Tue, Nov 28, 2017 at 9:31 AM, Finan, Sean < Sean.Finan@childrens.h
> > arvard.edu> wrote:
> >
> > >
> > > Hi Kathy,
> > >
> > > The negation annotator used in the default clinical pipeline is
> > > based upon machine learning and trained on real data.  It is
> > > possible that such "denies" lists were underrepresented in the
> > > training data.  One thing that you can try is adding another
> > > negation annotator.  The ContextAnnotator in ctakes-ne-contexts will
> > > add negation to terms without removing existing negation.  It also
> > > has configurable scope/distance that may be helpful.
> > >
> > > To use this, create a new piper file containing the two lines
> > >
> > > load DefaultFastPipeline
> > > add ContextAnnotator MaxLeftScopeSize=10 MaxRightScopeSize=10
> > >
> > > The default scope sizes are 7, but increasing  the MaxRight* might
> > > help with your "denies" discoveries.  7 might be ok for the left, so
> > > feel free to remove "MaxLeftScopeSize=10" from the line.
> > >
> > > Then run your piper file (command line, 

RE: polarity tag in output for mention/concept. [EXTERNAL] [SUSPICIOUS] [SUSPICIOUS]

[Finan, Sean]

Thanks Tim,

"Negation's Not Solved" :^)

-Original Message-
From: Miller, Timothy [mailto:timothy.mil...@childrens.harvard.edu] 
Sent: Tuesday, November 28, 2017 2:01 PM
To: dev@ctakes.apache.org
Subject: Re: polarity tag in output for mention/concept. [EXTERNAL] 
[SUSPICIOUS] [SUSPICIOUS]

I'll just point out -- the kind of examples Kathy gave were the bane of our 
existence while working on the ML-based assertion system. Even though it is 
obvious what is going on to a human it was hard to encode as a feature in a way 
that was learnable. But I think most rule-based algorithms will also run into 
problems with this type of example eventually if they have a hard-coded scoping 
mechanism (e.g., scope extends up to 10 words to the right). If you make it 
larger than you may increase the number of false positives your algorithm finds 
(confusingly, here a false positive is an example the algorithm calls negated 
that is not actually being negated).
Tim


On Tue, 2017-11-28 at 17:22 +, Finan, Sean wrote:
> Hi Kathy,
> 
> I am glad that you checked the wiki!  I should have pointed to it ...
> 
> In the example I sent the "relevant distance" between trigger terms 
> and events would be 10.  There isn't any maximum as far as I know, but 
> I think that 10 is the most that I've ever used.  The default is 7, 
> and you can try with that (remove "*=*") before increasing the 
> number(s).
> 
> The piper files aren't source code, they are just plain text and don't 
> require compiling, etc.  How are you running the pipeline right now?  
> From a binary with a bin/run* script?
> 
> Sean
> 
> 
> -Original Message-
> From: Kathy Ferro [mailto:healthcare1...@gmail.com]
> Sent: Tuesday, November 28, 2017 12:11 PM
> To: dev@ctakes.apache.org
> Subject: Re: polarity tag in output for mention/concept. [EXTERNAL]
> 
> Sean,
> 
> Thank you for information.
> 
> I was reading the document.  So, the MaxLeftScopeSize and 
> MaxRightScopeSize are limit up to 10?  Is there anyway to adjust it 
> without modify the source code?
> 
> https://urldefense.proofpoint.com/v2/url?u=https-3A__cwiki.apache.org
> _confluence_display_CTAKES_cTAKES-2B4.0-2B-2D-2BNE-
> 2BContexts=DwIBaQ=qS4goWBT7poplM69zy_3xhKwEW14JZMSdioCoppxeFU=f
> s67GvlGZstTpyIisCYNYmQCP6r0bcpKGd4f7d4gTao=4K9fxMmBiI0QZB0UhriFp_Yv
> XDL8rmXtGRiKVgxMCPE=hsCB9xPXLC8fpiwrGXuEW9snw_WZbY0e-E-mhPOO9N8=
> 
> 
> Thanks again,
> Kathy
> 
> 
> 
> On Tue, Nov 28, 2017 at 9:31 AM, Finan, Sean < Sean.Finan@childrens.h 
> arvard.edu> wrote:
> 
> > 
> > Hi Kathy,
> > 
> > The negation annotator used in the default clinical pipeline is 
> > based upon machine learning and trained on real data.  It is 
> > possible that such "denies" lists were underrepresented in the 
> > training data.  One thing that you can try is adding another 
> > negation annotator.  The ContextAnnotator in ctakes-ne-contexts will 
> > add negation to terms without removing existing negation.  It also 
> > has configurable scope/distance that may be helpful.
> > 
> > To use this, create a new piper file containing the two lines
> > 
> > load DefaultFastPipeline
> > add ContextAnnotator MaxLeftScopeSize=10 MaxRightScopeSize=10
> > 
> > The default scope sizes are 7, but increasing  the MaxRight* might 
> > help with your "denies" discoveries.  7 might be ok for the left, so 
> > feel free to remove "MaxLeftScopeSize=10" from the line.
> > 
> > Then run your piper file (command line, gui, maven profile, etc.) 
> > https://urldefense.proofpoint.com/v2/url?u=https-3A__cwiki.apache.o
> > rg_
> > confluence_display_CTAKES_Piper-
> > 2BFiles=DwIBaQ=qS4goWBT7poplM69zy_
> > 3xhKwEW14JZMSdioCoppxeFU=fs67GvlGZstTpyIisCYNYmQCP6r0bcpKGd4f7d4g
> > Tao
> > =4K9fxMmBiI0QZB0UhriFp_YvXDL8rmXtGRiKVgxMCPE=rXqsHq_poDXmwkCf3L
> > 2M5
> > ZlsByCbUHcSWD84JQQuh5A=
> > 
> > Sean
> > 
> > -Original Message-
> > From: Kathy Ferro [mailto:healthcare1...@gmail.com]
> > Sent: Monday, November 27, 2017 8:10 PM
> > To: dev@ctakes.apache.org
> > Subject: polarity tag in output for mention/concept. [EXTERNAL]
> > 
> > Good evening,
> > 
> > I ran a few sentences through default clinical pipeline.
> > 
> > It really reliable if it's only one term after negative, but I am 
> > get in-consistent value for polarity for the list of terms.  Please 
> > see example below.
> > 
> > 1.   denies fatigue, malaise, fever, weight loss
> > SignSymthomMention:
> > polarity = -1:  fatigue, malaise,fever polarity = 1: weight loss.
> > Why does weight loss got single out?
> > 
> > 2.   denies ear pain or discharge, nasal obstruction or discharge, 
> > sore throat polarity = -1: ear pain or discharge polarity = 1: nasal 
> > obstruction or discharge, obstruction, sore throat Doesn't even 
> > acknowledge the list.
> > 
> > 3.   denies back pain, joint swelling, joint stiffness, joint pain 
> > polarity = -1: back pain, Swelling polarity = 1: Joint swelling, 
> > Stiffness, pain What! totally messy the pattern.
> > 
> > 4.   denied back pain, 

Re: polarity tag in output for mention/concept. [EXTERNAL] [SUSPICIOUS]

[Miller, Timothy]

I'll just point out -- the kind of examples Kathy gave were the bane of
our existence while working on the ML-based assertion system. Even
though it is obvious what is going on to a human it was hard to encode
as a feature in a way that was learnable. But I think most rule-based
algorithms will also run into problems with this type of example
eventually if they have a hard-coded scoping mechanism (e.g., scope
extends up to 10 words to the right). If you make it larger than you
may increase the number of false positives your algorithm finds
(confusingly, here a false positive is an example the algorithm calls
negated that is not actually being negated).
Tim


On Tue, 2017-11-28 at 17:22 +, Finan, Sean wrote:
> Hi Kathy,
> 
> I am glad that you checked the wiki!  I should have pointed to it ...
> 
> In the example I sent the "relevant distance" between trigger terms
> and events would be 10.  There isn't any maximum as far as I know,
> but I think that 10 is the most that I've ever used.  The default is
> 7, and you can try with that (remove "*=*") before increasing the
> number(s).
> 
> The piper files aren't source code, they are just plain text and
> don't require compiling, etc.  How are you running the pipeline right
> now?  From a binary with a bin/run* script?
> 
> Sean
> 
> 
> -Original Message-
> From: Kathy Ferro [mailto:healthcare1...@gmail.com] 
> Sent: Tuesday, November 28, 2017 12:11 PM
> To: dev@ctakes.apache.org
> Subject: Re: polarity tag in output for mention/concept. [EXTERNAL]
> 
> Sean,
> 
> Thank you for information.
> 
> I was reading the document.  So, the MaxLeftScopeSize and
> MaxRightScopeSize are limit up to 10?  Is there anyway to adjust it
> without modify the source code?
> 
> https://urldefense.proofpoint.com/v2/url?u=https-3A__cwiki.apache.org
> _confluence_display_CTAKES_cTAKES-2B4.0-2B-2D-2BNE-
> 2BContexts=DwIBaQ=qS4goWBT7poplM69zy_3xhKwEW14JZMSdioCoppxeFU=f
> s67GvlGZstTpyIisCYNYmQCP6r0bcpKGd4f7d4gTao=4K9fxMmBiI0QZB0UhriFp_Yv
> XDL8rmXtGRiKVgxMCPE=hsCB9xPXLC8fpiwrGXuEW9snw_WZbY0e-E-mhPOO9N8=
> 
> 
> Thanks again,
> Kathy
> 
> 
> 
> On Tue, Nov 28, 2017 at 9:31 AM, Finan, Sean < Sean.Finan@childrens.h
> arvard.edu> wrote:
> 
> > 
> > Hi Kathy,
> > 
> > The negation annotator used in the default clinical pipeline is
> > based 
> > upon machine learning and trained on real data.  It is possible
> > that 
> > such "denies" lists were underrepresented in the training
> > data.  One 
> > thing that you can try is adding another negation annotator.  The 
> > ContextAnnotator in ctakes-ne-contexts will add negation to terms 
> > without removing existing negation.  It also has configurable
> > scope/distance that may be helpful.
> > 
> > To use this, create a new piper file containing the two lines
> > 
> > load DefaultFastPipeline
> > add ContextAnnotator MaxLeftScopeSize=10 MaxRightScopeSize=10
> > 
> > The default scope sizes are 7, but increasing  the MaxRight* might 
> > help with your "denies" discoveries.  7 might be ok for the left,
> > so 
> > feel free to remove "MaxLeftScopeSize=10" from the line.
> > 
> > Then run your piper file (command line, gui, maven profile, etc.) 
> > https://urldefense.proofpoint.com/v2/url?u=https-3A__cwiki.apache.o
> > rg_
> > confluence_display_CTAKES_Piper-
> > 2BFiles=DwIBaQ=qS4goWBT7poplM69zy_
> > 3xhKwEW14JZMSdioCoppxeFU=fs67GvlGZstTpyIisCYNYmQCP6r0bcpKGd4f7d4g
> > Tao
> > =4K9fxMmBiI0QZB0UhriFp_YvXDL8rmXtGRiKVgxMCPE=rXqsHq_poDXmwkCf3L
> > 2M5
> > ZlsByCbUHcSWD84JQQuh5A=
> > 
> > Sean
> > 
> > -Original Message-
> > From: Kathy Ferro [mailto:healthcare1...@gmail.com]
> > Sent: Monday, November 27, 2017 8:10 PM
> > To: dev@ctakes.apache.org
> > Subject: polarity tag in output for mention/concept. [EXTERNAL]
> > 
> > Good evening,
> > 
> > I ran a few sentences through default clinical pipeline.
> > 
> > It really reliable if it's only one term after negative, but I am
> > get 
> > in-consistent value for polarity for the list of terms.  Please
> > see 
> > example below.
> > 
> > 1.   denies fatigue, malaise, fever, weight loss
> > SignSymthomMention:
> > polarity = -1:  fatigue, malaise,fever polarity = 1: weight loss.
> > Why does weight loss got single out?
> > 
> > 2.   denies ear pain or discharge, nasal obstruction or discharge,
> > sore
> > throat
> > polarity = -1: ear pain or discharge
> > polarity = 1: nasal obstruction or discharge, obstruction, sore
> > throat 
> > Doesn't even acknowledge the list.
> > 
> > 3.   denies back pain, joint swelling, joint stiffness, joint pain
> > polarity = -1: back pain, Swelling
> > polarity = 1: Joint swelling, Stiffness, pain What! totally messy
> > the 
> > pattern.
> > 
> > 4.   denied back pain, joint swelling, joint stiffness, joint pain
> > Ok, may be it doesn't like the word denies; I changed to denied,
> > deny, 
> > etc..
> > polarity = -1 : Swelling
> > everything else is 1.
> > 
> > 
> > My question is:
> > How do I handle the negative claims in the document?

RE: Interpret context out of clinical note [EXTERNAL]

[Finan, Sean]

Hi Bhagwat,

I will try to answer this over the next day or two.  Somebody else may have 
some free time and get to you first ...

Sean 

-Original Message-
From: Bhagwat Posane [mailto:bhagwat.pos...@gmail.com] 
Sent: Tuesday, November 28, 2017 12:11 AM
To: dev@ctakes.apache.org
Subject: Re: Interpret context out of clinical note [EXTERNAL]

Hello Sean,

Thank you very much for your patience and bare with my basic queries.

1) What information you are trying to obtain from a note.  An example sentence 
would help.

>> Here are some example sentence from which I want to make out weather 
>> cystoscopy
is done or not.
>> ex:
Note 1:
In addition he has bilateral stones, non-obstructing and bilateral renal
cysts. I have been recommended that he
obtain a CT scan for staging, office cystoscopy for diagnosis,  and 
subsequently a bladder biopsy excision of the bladder tumor.
> cystoscopy not done


Note 2:
He has incidental bilateral renal stones 4.4 mm on the right and 2 mm on
the left.Cystoscopy showed a bladder
tumor on the floor of the bladder right side sessile 3 cm. suspicious for 
invasion  .  Biopsy showed no invasion but high grade.
---> cystoscopy done


Note 3:
Cystoscopy 2/10/16 shows the fistula, BPH, and no bladder lesions.Will
proceed with the fistula closure.CT
DONE IN THE HOSPITAL 2/24/16 SHOWED  INVASIVE BLADDER CANCER INTRA-MURAL 
OBSTRUCTING BOTH KIDNEYS.  PATIENT WILL REQURIE A CYSTECTOMY AND URINARY  
DIVERSION.
---> Cystoscopy done / CYSTECTOMY  not done


Note 4:
Other medical history in this patient includes diabetes, high blood pressure.  
Surgical history includes gallbladder,
liver biopsy, bladder tumor resection as stated above.Return in 12 mos.
for repeat cystoscopy.
---> cystoscopy done


Note 5:
Medical history in this patient is left blank except for thyroid disease.
  Surgical history includes some hand
surgery. He also had some kind of eye surgery in 1987.Plan will be
cystoscopy, resection of bladder tumor for staging and retrograde pyelogram.  
This is scheduled to be done at Medical City on July 20 at 7:30 in the morning.
> cystoscopy done





2) What you have already done to successfully or unsuccessfully obtain the 
information.

>> I had checked outputs on web api of ctakes by giving some notes, I
suspected TLINK must be helpful component to get the above work done.
>> so I followed the path how to get the TLINK statement output  and I
achieved it using piper file.





3) What you do understand at this point in time.
>> I understood only how to run particular pipeline using piper file and
get the output in HTML file.
>> I have gone through the ctakes-wiki, I have brief idea about each module.





4) What you think is missing from your understanding.
>>Till now I had thought of using TLINKS to capture the context out of
note. I think so because of categories in TLINKS. After fetching TLINKS in HTML 
format, while interpreting context, I feel mere TLINK wont help and I need 
something else to get my work done.
>>At present I think I am lost somewhere and not able to figure out the
pipeline that needs to be used to get my work done




5) What you really need from us.  A workflow?  A pipeline?  Pointers toward 
existing code?  Pointers toward datatypes?  A deeper explanation of existing 
code (pick 1 class)?  Help writing new ctakes code of your own?

>> More precisely, I need a pipeline to do above task, and deeper
explanation of code of this pipeline. Having code insight I will have a better 
control on the output, i.e. instead of having output in xmi/html, I can prepare 
collection or so for the output. This may need to write new
cTakescode, not sure though.



On 27 November 2017 at 19:02, Finan, Sean 
wrote:

> Hi Bhagwat.
>
> You wrote:
> > Now coming back to our original question for which this thread has 
> > been
> initiated.
> > I was trying to get the context out of clinical notes. for ex. If 
> > any
> procedure is happened or not on patient.
> >  ...
> > By following this clues, I am nowhere.
> > Could you please provide information on which pipeline I should have 
> > to
> run to achieve this goal, and how?
>
> Your snippet of my previous 

Re: polarity tag in output for mention/concept. [EXTERNAL]

[Kathy Ferro]

Sean,

Thank you for information.

I was reading the document.  So, the MaxLeftScopeSize and MaxRightScopeSize
are limit up to 10?  Is there anyway to adjust it without modify the source
code?

https://cwiki.apache.org/confluence/display/CTAKES/cTAKES+4.0+-+NE+Contexts


Thanks again,
Kathy



On Tue, Nov 28, 2017 at 9:31 AM, Finan, Sean <
sean.fi...@childrens.harvard.edu> wrote:

> Hi Kathy,
>
> The negation annotator used in the default clinical pipeline is based upon
> machine learning and trained on real data.  It is possible that such
> "denies" lists were underrepresented in the training data.  One thing that
> you can try is adding another negation annotator.  The ContextAnnotator in
> ctakes-ne-contexts will add negation to terms without removing existing
> negation.  It also has configurable scope/distance that may be helpful.
>
> To use this, create a new piper file containing the two lines
>
> load DefaultFastPipeline
> add ContextAnnotator MaxLeftScopeSize=10 MaxRightScopeSize=10
>
> The default scope sizes are 7, but increasing  the MaxRight* might help
> with your "denies" discoveries.  7 might be ok for the left, so feel free
> to remove "MaxLeftScopeSize=10" from the line.
>
> Then run your piper file (command line, gui, maven profile, etc.)
> https://cwiki.apache.org/confluence/display/CTAKES/Piper+Files
>
> Sean
>
> -Original Message-
> From: Kathy Ferro [mailto:healthcare1...@gmail.com]
> Sent: Monday, November 27, 2017 8:10 PM
> To: dev@ctakes.apache.org
> Subject: polarity tag in output for mention/concept. [EXTERNAL]
>
> Good evening,
>
> I ran a few sentences through default clinical pipeline.
>
> It really reliable if it's only one term after negative, but I am get
> in-consistent value for polarity for the list of terms.  Please see example
> below.
>
> 1.   denies fatigue, malaise, fever, weight loss
> SignSymthomMention:
> polarity = -1:  fatigue, malaise,fever
> polarity = 1: weight loss.
> Why does weight loss got single out?
>
> 2.   denies ear pain or discharge, nasal obstruction or discharge, sore
> throat
> polarity = -1: ear pain or discharge
> polarity = 1: nasal obstruction or discharge, obstruction, sore throat
> Doesn't even acknowledge the list.
>
> 3.   denies back pain, joint swelling, joint stiffness, joint pain
> polarity = -1: back pain, Swelling
> polarity = 1: Joint swelling, Stiffness, pain What! totally messy the
> pattern.
>
> 4.   denied back pain, joint swelling, joint stiffness, joint pain
> Ok, may be it doesn't like the word denies; I changed to denied, deny,
> etc..
> polarity = -1 : Swelling
> everything else is 1.
>
>
> My question is:
> How do I handle the negative claims in the document?
>
> Thank you
> Kathy
>

RE: polarity tag in output for mention/concept. [EXTERNAL]

[Finan, Sean]

Hi Kathy,

The negation annotator used in the default clinical pipeline is based upon 
machine learning and trained on real data.  It is possible that such "denies" 
lists were underrepresented in the training data.  One thing that you can try 
is adding another negation annotator.  The ContextAnnotator in 
ctakes-ne-contexts will add negation to terms without removing existing 
negation.  It also has configurable scope/distance that may be helpful.

To use this, create a new piper file containing the two lines

load DefaultFastPipeline
add ContextAnnotator MaxLeftScopeSize=10 MaxRightScopeSize=10

The default scope sizes are 7, but increasing  the MaxRight* might help with 
your "denies" discoveries.  7 might be ok for the left, so feel free to remove 
"MaxLeftScopeSize=10" from the line.

Then run your piper file (command line, gui, maven profile, etc.)
https://cwiki.apache.org/confluence/display/CTAKES/Piper+Files

Sean

-Original Message-
From: Kathy Ferro [mailto:healthcare1...@gmail.com] 
Sent: Monday, November 27, 2017 8:10 PM
To: dev@ctakes.apache.org
Subject: polarity tag in output for mention/concept. [EXTERNAL]

Good evening,

I ran a few sentences through default clinical pipeline.

It really reliable if it's only one term after negative, but I am get 
in-consistent value for polarity for the list of terms.  Please see example 
below.

1.   denies fatigue, malaise, fever, weight loss
SignSymthomMention:
polarity = -1:  fatigue, malaise,fever
polarity = 1: weight loss.
Why does weight loss got single out?

2.   denies ear pain or discharge, nasal obstruction or discharge, sore
throat
polarity = -1: ear pain or discharge
polarity = 1: nasal obstruction or discharge, obstruction, sore throat Doesn't 
even acknowledge the list.

3.   denies back pain, joint swelling, joint stiffness, joint pain
polarity = -1: back pain, Swelling
polarity = 1: Joint swelling, Stiffness, pain What! totally messy the pattern.

4.   denied back pain, joint swelling, joint stiffness, joint pain
Ok, may be it doesn't like the word denies; I changed to denied, deny, etc..
polarity = -1 : Swelling
everything else is 1.


My question is:
How do I handle the negative claims in the document?

Thank you
Kathy

Re: uimafit version and commit messages

[Richard Eckart de Castilho]

The uimaFIT releases mainly fix bugs and add smaller features.
It should be pretty safe to update to 2.4.0. I didn't face
any problems upgrading e.g. DKPro Core which is pretty large
and uses uimaFIT intensively.

Cheers,

-- Richard (atm maintaining uimaFIT)

> On 28.11.2017, at 01:45, David Kincaid  wrote:
> 
> Thanks for upgrading uimafit. I was thinking of giving it a try myself when
> I had a chance. I see that you upgrades to 2.30, but the most recent
> version is 2.4.0. Was there a problem with 2.4.0?
> 
> - Dave