flaw in the dictionary
> creator tool.
>
> Time for a rebuild with the 5.0 release ...
>
> Thanks for the report,
>
> Sean
>
>
> From: Kean Kaufmann
> Sent: Wednesday, December 6, 2023 4:12 PM
> To: dev@ctakes.apache.org
> Su
cal terms that are in PREFTERM but not CUI_TERMs. Off the top:
C0017168 gastroesophageal reflux disease, C0018802 congestive heart
failure, C0022104 irritable bowel syndrome, ...
We've been adding these to a supplementary BSV file as they come up, but
there are many more. This HSQL query f
hoice (UMLS CUI:
C1298669)
> Any resources I can use to help me with other similar questions?
UMLS Metathesaurus Browser: https://uts.nlm.nih.gov/uts/umls/home
Signup is free.
_____
*Kean Kaufmann*
NLP Architect
RecordsOne
nSight Driven | *
t, extracting tumor info from
tables, etc.
The cTAKES RegexSectionizer might work for you.
https://ctakes.apache.org/apidocs/4.0.0/org/apache/ctakes/core/ae/RegexSectionizer.html
_
*Kean Kaufmann*
NLP Architect
RecordsOne
nSight Driven |
Is Git LFS an option?
https://www.atlassian.com/git/tutorials/git-lfs#installing-git-lfs
Needs an LFS-aware host e.g. Bitbucket; I don't know what the Apache
hosting setup is like.
On Fri, Jun 3, 2022 at 9:31 AM Finan, Sean
wrote:
> Hi Tim,
>
> >we ran into issues in previous attempts at migrat
ommunity can apply ruta rules to their project.
> >
> > When I looked at it a few years ago it was for reason 2b. In the end we
> went for different annotators like Peter and Kean outlined and just use
> piper file changes to satisfy #2 as that is definitely much easier.
> However, it do
> yes, the line between "lookup" and rule execution is a little blurry
sometimes.
Sure is. I blur it with a set of annotators that extend dictionary
annotations based on words or annotations covered by the same Chunk, e.g.
DiseaseDisorderMention + /screen(ing)?/i = ProcedureMention
MedicationMe
t; script and use it to massage the dictionary I created using the creator.
>
> Peter
>
>
>
> On Mon, Feb 15, 2021 at 4:16 PM Kean Kaufmann wrote:
>
> > FWIW, rather than editing the HSQLDB script, we use Sean's
> > BsvRareWordDictionary to
FWIW, rather than editing the HSQLDB script, we use Sean's
BsvRareWordDictionary to add phrases with a BSV file:
cTakesHsql.xml:
AddPhrases
org.apache.ctakes.dictionary.lookup2.dictionary.BsvRareWordDictionary
tory"; for outpatient radiology, "History" maps to "Reason for
Exam".
A lot of people in the community don't dream in java
I do, sometimes... but then I wake up screaming. ;-)
Kean Kaufmann
Chief Architect - NLP
RecordsOne, Inc.
On Sat, Jan 30, 2021 at 10:01 AM Fi
> I've attached the Junit test based off your unit test and its debug
output. You'll have to change the package name, though.
Hi Peter -- Yes, that does sound weird. Not seeing an attachment. Send it
along and I'll give troubleshooting a shot.
Happy holidays, everybody.
On Thu, Dec 24, 2020 at
>
> 3. for 4.0.0 users that compile their own, provide a tar file containing
> the sources plus instructions for modifying xml files and removing obsolete
> Junit file.
Is it worth a quick email poll of 4.0.0 users?
+1 for Option 3! Thanks Peter (and everybody)...
On Wed, Dec 9, 2020 at 8:
Peter says:
the LabValueFinder. It has settings that allow it to clone procedures into
> lab values or vice versa (I can't remember).
The former... at least, when I contributed it. For potential lab values,
it filters by TUIs: some procedures, others medications.
Sean says:
The only immediat
Hi Peter,
I believe I've encountered this too; I never got around to tracking it down
to the root cause, and didn't have the civic-mindedness to report it as you
have. Thanks!
To shut it up I implemented a brutal brute-force workaround, enclosed for
your possible amusement.
But it occurred to me
>
> my question is whether there's a place where one can register specific two
> character terms, for example BP or PT which will be found even with a
> window size set to three.
My brute-force approach is pretty brutal: Change the window size to two,
annotate terms, then remove all two-letter an
Gandhi, at first blush, I can't replicate your result using the code I
submitted...
but my code and config differ from trunk, so Sean is probably the best
person to ask.
I included unit tests with a mini-dictionary for ProcedureMentions, but
they probably didn't play nicely with the rest of the fra
out.
> That is very strange. I have no idea why adding an entry would change the
> behavior. I will have to look at the code and run your examples. By the
> way, thank you for the explicit examples!
>
> >Is this expected behavior?
> No, and thanks for letting me know about it.
P.S. Extra config bit: I also removed "CD" from the exclusionTags in the
UmlsOverlapLookupAnnotator.
On Wed, Mar 7, 2018 at 10:58 AM, Kean Kaufmann wrote:
> Hi Sean,
>
> I'm perplexed. It seems as if the number of tokens that the
> UmlsOverlapLookupAnnotator will s
Hi Sean,
I'm perplexed. It seems as if the number of tokens that the
UmlsOverlapLookupAnnotator will skip varies with the content of the
RareWordDictionary.
Here's my setup. I think I've included enough information to replicate my
perplexity, if you have time/inclination to do that; let me know
same.
>
> 28 Feb 2018 15:04:04 INFO LabValueFinder - Set to value:
> LabMention(349-352): HCT
>
> 28 Feb 2018 15:04:04 INFO LabValueFinder - Set to value:
> RangeAnnotation(365-370): 42-52
>
> 28 Feb 2018 15:04:04 INFO LabValueFinder - Set to value:
> MeasurementA
Oops, forgot to cc: dev. Happy Monday...
-- Forwarded message --
From: Kean Kaufmann
Date: Mon, Feb 12, 2018 at 10:14 AM
Subject: Re: Lab Value - Range finder
To: abilash.mat...@cognizant.com
> I could see setReferenceRangeNarrative method in LabMention class. Is
that the
Hi Abilash,
By design, the Lab Value annotator avoids ranges if possible:
https://svn.apache.org/repos/asf/ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/ae/LabValueFinder.java
// prefer non-range values, if any
> value = candidateList.stream()
>
In my experience, the quick answer is: Certainly not all, but probably
many. Different institutions will have different formats for lab reports,
different panels they typically perform, and different labels.
On Tue, Dec 19, 2017 at 8:21 AM, wrote:
> Hi ,
>
> Based on the experience , can anyon
I wrote a lab annotator that will be checked into the trunk at some point.
Source, unit tests and description attached to this issue:
https://issues.apache.org/jira/browse/CTAKES-441
On Mon, Nov 13, 2017 at 6:09 AM, wrote:
> Hi All,
>
> Can CTAKES process LAB reports and able to extract key fin
+1
I point it at an engine descriptor .xml file (using the command-line option
-desc) that refers to the type system file, but that's a hack...
On Wed, Oct 25, 2017 at 1:49 PM, Dligach, Dmitriy wrote:
> +1
>
> Also, I’d love to be able to point CVD to a directory containing XMI files
> at start
Sean, thanks! Blacklisting is essential, and making it category-specific
is a really nice touch.
Dispatch from the trenches, FWIW:
a) The blacklist can get quite big, e.g. when mining common wordlists. To
reduce bloat, might you allow comma-separated lists of semantic groups in
the first field?
Hi A.S.,
Does the "Show Selected Annotations" menu item serve your purposes?
https://uima.apache.org/d/uimaj-current/tools.html#cvd.toolsMenu
On Mon, Jul 17, 2017 at 4:31 AM, Lacey A.S. wrote:
> Hi - I spend a lot of time showing doctors the output of cTakes via what I
> have parsed during po
ecise PrecisionTermConsumer or do I need to
> make my own custom TermConsumer? I also tried the
> SemanticCleanupTermConsumer, but it gave the same results.
>
> Here's the code I'm using to extract phrases:
>
> JCas jcas = JCasFactory.createJCas();
> jcas.setDocumentText(note);
> AggregateBuild
tomization; and I've
skimmed the NLM documentation, but it doesn't seem to be intended for
developers. Can anyone point me to more detailed docs?
And: Has anyone tried plugging in another stemmer? To play nicely with the
ctakes-dictionary-lookup-fast annotators, it seems as if all it would have
to do would be to populate canonicalForm.
Happy Friday, and thanks for any help you can provide!
Kean Kaufmann
NLP Developer
RecordsOne, Inc.
I'd think LVG would come up with "fall" as the canonicalForm of "fell" and
"fallen", but apparently it doesn't.
The only terms associated with C0085639 in my custom-built dictionary are:
sql> select cui, tui, text, prefterm from cui_terms c join tui t on t.cui =
> c.cui join prefterm p on p.cui =
>
> On Fri, Apr 28, 2017 at 9:53 PM, Finan, Sean <
> sean.fi...@childrens.harvard.edu> wrote:
>
Hey Kean,
>
> It is great to know that your project is out there!
>
Hey Sean! Very kind of you. Speaking of which, our BizDevVeep would like
to see RecordsOne listed under "Companies" on the "Users of
> > For further information, please visit the project website at
> > http://ctakes.apache.org/
> >
> > -- The Apache cTAKES Team
> >
>
--
_
*Kean Kaufmann*
NLP Developer
RecordsOne
nSight Dri
t; Has anybody tried to run a cTAKES pipeline without having a local cTAKES
> installation? In other words, is it possible to set up a maven project that
> will use cTAKES as an external dependency?
>
> Dima
>
>
>
>
--
_
mmitter the code or have somebody review it remotely? The
> "tweaks" may be something useful to ctakes, but if not I'm sure that we can
> create a decent interfacing.
> >
> > Cheers,
> > Sean
> >
> > -Original Message-
> > From: Kean
sure that people would love to see lab values in ctakes! Could you
> please write a small summary of what it does? Maybe an example or two
> could suffice.
>
> We can definitely put it into ctakes in release 4.1 - maybe next quarter?
>
> Cheers,
> Sean
>
> -Origin
dev list a couple of years ago; did anything come of it? Happy
to contribute if it's helpful.
--
_____
*Kean Kaufmann*
NLP Developer
RecordsOne
nSight Driven | *Priority. Clarity. Integrity. *
*mobile* |
240-401-6131
*Twitter: **@R1
To: dev@ctakes.apache.org
> Subject: 2016AB UMLS (ctakessnorx)
>
> Hi,
>
> I've been using cTAKES for a bit now, but I still can't figure
> out how to upgrade the UMLS version to the most recent one.
> If I create my
the time being.
Thanks,
Kean
--
_____
*Kean Kaufmann*
NLP Developer
RecordsOne
nSight Driven | *Priority. Clarity. Integrity. *
*mobile* |
240-401-6131
*Twitter: **@R1_RecordsOne*
---
*Confidentiality N
38 matches
Mail list logo