ctakes-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Geise, Brandon D." <bdge...@geisinger.edu>
Subject RE: Fast Dictionary Update
Date Wed, 16 Sep 2015 19:37:32 GMT
Sorry for not being clearer in my question.

All 3 run when the command is issued, but when anat and snomed run nothing is output to the
bsv file whereas with RXNorm 74,421 CUIs are written.  So my dictionary only ends up being
RXNorm CUIs and doesn't include snomed.

Does that clarify?

Thanks,
Brandon

-----Original Message-----
From: Finan, Sean [mailto:Sean.Finan@childrens.harvard.edu] 
Sent: Wednesday, September 16, 2015 3:34 PM
To: dev@ctakes.apache.org
Subject: RE: Fast Dictionary Update

I'm not sure that I understand your question.  As I sent it, the anat, snomed and rxnorm are
not separate runs.  The args line I sent earlier is for a single run that will create a dictionary
with snomed and rxnorm terms.  The anatomy tui list has a special use in correctly processing
snomed codes. 

-----Original Message-----
From: Geise, Brandon D. [mailto:bdgeise@geisinger.edu] 
Sent: Wednesday, September 16, 2015 3:27 PM
To: dev@ctakes.apache.org
Subject: RE: Fast Dictionary Update

Ok, hopefully one last question.

Based on your example everything runs, however the Anat and Snomed runs don't produce any
valid CUIs but RXNorm does.  I'm not sure if this has anything to do with it but every UMLS
source read is against MRSTY.  

Here's my command

java -cp dictionarytool.jar;lib/* org.apache.ctakes.dictionarytool.DictionaryCreator2 -umls
/path/to/UMLS/META -fd ./data/tiny -atui ./data/tiny/CtakesAnatTuis.txt -tui ./data/tiny/CtakesSnomedTuis.txt
-ol \path\to\file\Umls2015.bsv

Any suggestions?

Thanks again,
Brandon


-----Original Message-----
From: Finan, Sean [mailto:Sean.Finan@childrens.harvard.edu] 
Sent: Wednesday, September 16, 2015 3:05 PM
To: dev@ctakes.apache.org
Subject: RE: Fast Dictionary Update

Yes, that will make the rare word dictionary in a memory-based hsql database - the same as
the default for the dictionary-lookup-fast module.

-----Original Message-----
From: Geise, Brandon D. [mailto:bdgeise@geisinger.edu] 
Sent: Wednesday, September 16, 2015 2:42 PM
To: dev@ctakes.apache.org
Subject: RE: Fast Dictionary Update

Thanks Sean, much appreciated.  To clarify the example below would create the dictionary for
use for the rare word approach?

Thanks,
Brandon

-----Original Message-----
From: Finan, Sean [mailto:Sean.Finan@childrens.harvard.edu] 
Sent: Wednesday, September 16, 2015 2:16 PM
To: dev@ctakes.apache.org
Subject: RE: Fast Dictionary Update

Hi Brandon,

I just checked in a bin/dictionarytool.zip It should have everything that you need (.jar,
lib/, data/).
java -cp dictionarytool.jar;lib/* org.apache.ctakes.dictionarytool.DictionaryCreator2 [args]
Should do the trick.

To recreate a 2015 version of the current ctakes dictionary, the arguments are: 
-umls my/path/to/2015AA/META -fd ./data/tiny -atui ./data/tiny/CtakesAnatTuis.txt -tui ./data/tiny/CtakesSnomedTuis.txt
-db jdbc:hsqldb:file:my/path/to/snorx2015 -tbl CUI_TERMS

Create my/path/to/snorx2015 by copying resources/memdbtemplate/ctakesumls.properties to my/path/to/snorx2015.properties
  - there is a resources/README about this.

Before populating a DB, I usually do a trial run first, writing to a flat file.  Replace "-db
... -tbl ..." with "-ol my/path/to/testout.bsv"


Sean

-----Original Message-----
From: Geise, Brandon D. [mailto:bdgeise@geisinger.edu]
Sent: Wednesday, September 16, 2015 1:49 PM
To: dev@ctakes.apache.org
Subject: RE: Fast Dictionary Update

Hi Sean,

That'd be great.

I think I'm building it incorrectly because after I build the jar and try to run specifying
DictionaryCreator2 as the main class it says it can't find it.  I'm not too familiar with
Java and building projects/jars so it could be my ignorance causing the problem.

Thanks,
Brandon

-----Original Message-----
From: Finan, Sean [mailto:Sean.Finan@childrens.harvard.edu]
Sent: Wednesday, September 16, 2015 1:45 PM
To: dev@ctakes.apache.org
Subject: RE: Fast Dictionary Update

Hi Brandon,

I can send you a jar or commit one pre-built.  What goes wrong when you try to build the tool?

Sean

-----Original Message-----
From: Geise, Brandon D. [mailto:bdgeise@geisinger.edu]
Sent: Wednesday, September 16, 2015 1:23 PM
To: 'dev@ctakes.apache.org'
Subject: Fast Dictionary Update

Does someone have the DictionaryTool jar available?  I'm having trouble creating the jar file
from the project and would like to be able to create an updated UMLS fast dictionary for 2015.

Thanks,
Brandon


IMPORTANT WARNING: The information in this message (and the documents attached to it, if any)
is confidential and may be legally privileged. It is intended solely for the addressee. Access
to this message by anyone else is unauthorized. If you are not the intended recipient, any
disclosure, copying, distribution or any action taken, or omitted to be taken, in reliance
on it is prohibited and may be unlawful. If you have received this message in error, please
delete all electronic copies of this message (and the documents attached to it, if any), destroy
any hard copies you may have created and notify me immediately by replying to this email.
Thank you.

Geisinger Health System utilizes an encryption process to safeguard Protected Health Information
and other confidential data contained in external e-mail messages. If email is encrypted,
the recipient will receive an e-mail instructing them to sign on to the Geisinger Health System
Secure E-mail Message Center to retrieve the encrypted e-mail.





Mime
View raw message