RE: false positive [EXTERNAL]

[Abilash.Mathew]

Thanks Sean for the help. The information provided below are really helpful for 
addressing our challenges.

Regards,
Abilash Mathew

-Original Message-
From: Finan, Sean [mailto:sean.fi...@childrens.harvard.edu]
Sent: Wednesday, October 25, 2017 7:17 PM
To: dev@ctakes.apache.org
Subject: RE: false positive [EXTERNAL]

Hi Gandhi, Abilash Mathew,

This is a common problem stemming from the nature of the umls and automated 
dictionary creation.  I am still (ever so slowly) improving the dictionary 
creator code.  If anybody can devote some time to help that would be great.

Anyway, if you are using ctakes trunk there is a new capability of the -fast 
dictionary lookup.  Basically, you can "blacklist" texts that you do not want.

1. Create a bar-separated value (bsv) file containing the ctakes numeric code 
for a semantic group and the text that you don't want.
2. Set the parameter "Blacklist" to point to the file.

The ctakes numeric semantic group codes can be found in the CONST class in 
ctakes-type-system.  The pertinent codes:
1 = medication
2 = disease / disorder
3 = sign / symptom
5 = procedure
6 = anatomical site
9 = lab
0 = unknown

Example:

// My Blacklist File.
# double-slash and hash indicate comment lines.
3|Finding
5|test
5|Procedure
1|Page
5|treatment
1|medicine
1|Drug
// Not sure what "finicky thing" belongs to, so I'll just add a bunch:
1|finicky thing
2|finicky thing
3|finicky thing
5|finicky thing
6|finicky thing

The semantic group codes are there so that you can (for instance) make ctakes 
ignore "1|Drug" as a generic indication some medication but keep "drug" as a 
procedure.  For instance "aspirin is a drug" versus "the patient was drugged 
before proceeding".

Once you have the file, set "Blacklist" to point to the file as you would other 
ctakes pipeline parameters.

Use of the texts in the blacklist is case insensitive.  There is no difference 
between adding "1|DRUG" and "1|drug".
If you do want case sensitivity ...  you can use a blacklist file pointed to by 
the parameter "CsBlacklist".

I think that is about it.

Sean

-Original Message-
From: Gandhi Rajan Natarajan [mailto:gandhi.natara...@arisglobal.com]
Sent: Wednesday, October 25, 2017 9:14 AM
To: dev@ctakes.apache.org
Subject: RE: false positive [EXTERNAL]

Hi Abilash,

I'm not sure how much it will make sense. But in our custom annotator we wrote 
on top of cTAKES, we resolved this false positives to an extent by using 
commonly used English words metadata available from OpenNLP.

Regards,
Gandhi

-Original Message-
From: abilash.mat...@cognizant.com [mailto:abilash.mat...@cognizant.com]
Sent: Wednesday, October 25, 2017 3:57 PM
To: dev@ctakes.apache.org
Subject: false positive

Hi all,

We are seeing some false positives identified by CTAKES after we tested couple 
of medical records samples. Can anyone help us on how to ignore these words 
from tagging incorrectly?

Word

Finding

test

Procedure

Page

Procedure

treatment

Procedure

medicine

Drug

medication

Drug

attachments

Procedure

RELEASE

Procedure

reconstruction

Procedure

DOB

Drug

Procedure

Procedure

Division

Procedure


Thanks,
Abilash Mathew
This e-mail and any files transmitted with it are for the sole use of the 
intended recipient(s) and may contain confidential and privileged information. 
If you are not the intended recipient(s), please reply to the sender and 
destroy all copies of the original message. Any unauthorized review, use, 
disclosure, dissemination, forwarding, printing or copying of this email, 
and/or any action taken in reliance on the contents of this e-mail is strictly 
prohibited and may be unlawful. Where permitted by applicable law, this e-mail 
and other e-mail communications sent to and from Cognizant e-mail addresses may 
be monitored.
This email and any files transmitted with it are confidential and intended 
solely for the use of the individual or entity to whom they are addressed. If 
you are not the named addressee you should not disseminate, distribute or copy 
this e-mail. Please notify the sender or system manager by email immediately if 
you have received this e-mail by mistake and delete this e-mail from your 
system. If you are not the intended recipient you are notified that disclosing, 
copying, distributing or taking any action in reliance on the contents of this 
information is strictly prohibited and against the law.
This e-mail and any files transmitted with it are for the sole use of the 
intended recipient(s) and may contain confidential and privileged information. 
If you are not the intended recipient(s), please reply to the sender and 
destroy all copies of the original message. Any unauthorized review, use, 
disclosure, dissemination, forwarding, printing or copying of this email, 
and/or any action taken in reliance on the contents of this e-mail is strictly 
prohibited and may be unlawful. Where permitted by applicable law, this e-mail 
and other e-mail communications 

RE: cTAKES as REST service

[Gandhi Rajan Natarajan]

Hi Matthew,

Big thanks for the response. Actually in our case we are trying to integrate 
cTAKES with our application and it's our application which will invoke the rest 
calls and get back the response for further processing.

Also I have not worked on Docker before but would love to. So if you feel I may 
be of some help in your project, please keep me posted. As you said I would be 
more than happy to contribute for the open source. Cheers.

Regards,
Gandhi


-Original Message-
From: Matthew Vita [mailto:matthewvit...@gmail.com]
Sent: Wednesday, October 25, 2017 9:57 PM
To: dev@ctakes.apache.org
Subject: Re: cTAKES as REST service

Gandhi,

I am actually working on a series of Docker containers that expose an HTTP 
endpoint to send clinical text to and then it POSTs the results back to your 
application's HTTP endpoint in JSON. Please let me know if this approach 
interests you and we can schedule a Google Hangouts to talk about what work is 
left (I estimate that I will be done in a month and a half).

Please do note that this solution is 100% free/open source :)


Thanks,

Matthew Vita
www.matthewvita.com

On Wed, Oct 25, 2017 at 6:20 AM, Gandhi Rajan Natarajan < 
gandhi.natara...@arisglobal.com> wrote:

> Hi All,
>
> We have extended the cTAKES web application available under
> https://github.com/healthnlp/examples/tree/master/ctakes-temporal-demo
> and added our custom annotator. We have tested the same and it works
> fine with CVD. But we are facing problems while trying to expose this
> as rest service.
>
> cTAKES uses Spring 3.1.2 version internally which don't have out of
> the box support for rest controller. Can we go ahead and update the
> spring version to 4x in cTAKES? Will it have any impact in the cTAKES 
> behavior?
> Also is there a better way to expose cTAKES as rest service apart from
> spring?
>
> Please advise.
>
> Regards,
> Gandhi
>
> This email and any files transmitted with it are confidential and
> intended solely for the use of the individual or entity to whom they are 
> addressed.
> If you are not the named addressee you should not disseminate,
> distribute or copy this e-mail. Please notify the sender or system
> manager by email immediately if you have received this e-mail by
> mistake and delete this e-mail from your system. If you are not the
> intended recipient you are notified that disclosing, copying,
> distributing or taking any action in reliance on the contents of this
> information is strictly prohibited and against the law.
>
This email and any files transmitted with it are confidential and intended 
solely for the use of the individual or entity to whom they are addressed. If 
you are not the named addressee you should not disseminate, distribute or copy 
this e-mail. Please notify the sender or system manager by email immediately if 
you have received this e-mail by mistake and delete this e-mail from your 
system. If you are not the intended recipient you are notified that disclosing, 
copying, distributing or taking any action in reliance on the contents of this 
information is strictly prohibited and against the law.

Re: CAS Visual Debugger - [EXTERNAL]

[Melvin Ma]

Thanks.

On Wed, Oct 25, 2017 at 11:26 AM, James Masanz 
wrote:

> Cool. Thanks
>
> On Oct 25, 2017 1:24 PM, "Finan, Sean" 
> wrote:
>
> > Ok, there is a kludge ...
> >
> > 1.  Start the CVD
> > 2.  Go to File > load Type System
> > 3.  Select your type system
> > 4.  Exit
> > 5.  Go to your home directory
> > 6.  Look at the file named annotViewer.pref
> > There should be a line starting with " dir.open.xcas=" that points to
> your
> > type system.
> > 7.  Make a copy of the annotViewer.pref file (MyTypesCVD.pref)
> >
> > 8.  Next time you launch the cvd, specify -ini MyTypesCVD.pref
> > The cvd should load your type system on startup.
> >
> > Good luck,
> > Sean
> >
> >
> > -Original Message-
> > From: Melvin Ma [mailto:ma.qian...@gmail.com]
> > Sent: Wednesday, October 25, 2017 1:34 PM
> > To: dev@ctakes.apache.org
> > Subject: CAS Visual Debugger - [EXTERNAL]
> >
> > This is more of a question. I am fully aware that CAS Visual Debugger is
> > maintained in UIMA project.
> >
> > For me for now, I will frequently need to use CVD to view .xmi file. It
> > would be really nice if I could put the type system xml as an input to
> CVD
> > startup argument (instead of manully lookup this file and load it). Do
> you
> > know anyway to do it? I checked the documents multiple times and was not
> > able to find anything.
> >
> > Thanks.
> >
> > Melvin
> >
>

RE: Piper File - [EXTERNAL]

[Finan, Sean]

Hi Melvin,

This was a bug.  I just checked in a fixed pom file.

Thanks,
Sean 

-Original Message-
From: Melvin Ma [mailto:ma.qian...@gmail.com] 
Sent: Wednesday, October 25, 2017 12:45 PM
To: dev@ctakes.apache.org
Subject: Piper File - [EXTERNAL]

Sean - I am actually replying your earlier email. I have deleted the email by 
an accident. So here is a new thread.


I searched up all the .piper files in the source and only 
"DictionarySubPipe.piper" file was not included in the *-res*.jar file 
downloaded from maven repo. It appears that pom.xml was quite different in 
ctakes-dictionary-lookup-fast-res project. Should we make a small change the 
pom.xml file in ctakes-dictionary-lookup-fast-res project to include the 
DictionarySubPipe.piper file? Thanks!


-
contains / project name / piper file name

xx - found in the project jar file
?? -- missing
-

xx  ctakes-assertion-resAssertionSubPipe.piper
xx  ctakes-assertion-resAttributeCleartkSubPipe.piper
xx  ctakes-chunker-res  ChunkerSubPipe.piper
xx  ctakes-clinical-pipeline-resDefaultFastPipeline.piper
xx  ctakes-coreference-res  CorefSubPipe.piper
xx  ctakes-core-res DefaultTokenizerPipeline.piper
xx  ctakes-core-res AdvancedTokenizerPipeline.piper
??  ctakes-dictionary-lookup-fast-res   DictionarySubPipe.piper

RE: CAS Visual Debugger - [EXTERNAL]

[James Masanz]

Cool. Thanks

On Oct 25, 2017 1:24 PM, "Finan, Sean" 
wrote:

> Ok, there is a kludge ...
>
> 1.  Start the CVD
> 2.  Go to File > load Type System
> 3.  Select your type system
> 4.  Exit
> 5.  Go to your home directory
> 6.  Look at the file named annotViewer.pref
> There should be a line starting with " dir.open.xcas=" that points to your
> type system.
> 7.  Make a copy of the annotViewer.pref file (MyTypesCVD.pref)
>
> 8.  Next time you launch the cvd, specify -ini MyTypesCVD.pref
> The cvd should load your type system on startup.
>
> Good luck,
> Sean
>
>
> -Original Message-
> From: Melvin Ma [mailto:ma.qian...@gmail.com]
> Sent: Wednesday, October 25, 2017 1:34 PM
> To: dev@ctakes.apache.org
> Subject: CAS Visual Debugger - [EXTERNAL]
>
> This is more of a question. I am fully aware that CAS Visual Debugger is
> maintained in UIMA project.
>
> For me for now, I will frequently need to use CVD to view .xmi file. It
> would be really nice if I could put the type system xml as an input to CVD
> startup argument (instead of manully lookup this file and load it). Do you
> know anyway to do it? I checked the documents multiple times and was not
> able to find anything.
>
> Thanks.
>
> Melvin
>

RE: CAS Visual Debugger - [EXTERNAL]

[Finan, Sean]

Ok, there is a kludge ...

1.  Start the CVD
2.  Go to File > load Type System
3.  Select your type system
4.  Exit
5.  Go to your home directory
6.  Look at the file named annotViewer.pref
There should be a line starting with " dir.open.xcas=" that points to your type 
system.
7.  Make a copy of the annotViewer.pref file (MyTypesCVD.pref)

8.  Next time you launch the cvd, specify -ini MyTypesCVD.pref
The cvd should load your type system on startup.

Good luck,
Sean


-Original Message-
From: Melvin Ma [mailto:ma.qian...@gmail.com] 
Sent: Wednesday, October 25, 2017 1:34 PM
To: dev@ctakes.apache.org
Subject: CAS Visual Debugger - [EXTERNAL]

This is more of a question. I am fully aware that CAS Visual Debugger is
maintained in UIMA project.

For me for now, I will frequently need to use CVD to view .xmi file. It
would be really nice if I could put the type system xml as an input to CVD
startup argument (instead of manully lookup this file and load it). Do you
know anyway to do it? I checked the documents multiple times and was not
able to find anything.

Thanks.

Melvin

Re: CAS Visual Debugger - [EXTERNAL]

[Kean Kaufmann]

+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 startup.
>
> Dima
>
>
>
> On Oct 25, 2017, at 12:41, Miller, Timothy  harvard.edu> wrote:
>
> I've had the same thought, and come to the same conclusions.
> Tim
>
> 
> From: Melvin Ma >
> Sent: Wednesday, October 25, 2017 1:33 PM
> To: dev@ctakes.apache.org
> Subject: CAS Visual Debugger - [EXTERNAL]
>
> This is more of a question. I am fully aware that CAS Visual Debugger is
> maintained in UIMA project.
>
> For me for now, I will frequently need to use CVD to view .xmi file. It
> would be really nice if I could put the type system xml as an input to CVD
> startup argument (instead of manully lookup this file and load it). Do you
> know anyway to do it? I checked the documents multiple times and was not
> able to find anything.
>
> Thanks.
>
> Melvin
>
>

RE: CAS Visual Debugger - [EXTERNAL]

[Finan, Sean]

Dima,
I think that there is an -xmi option or something like that, but for individual 
files.

-Original Message-
From: Dligach, Dmitriy [mailto:ddlig...@luc.edu] 
Sent: Wednesday, October 25, 2017 1:50 PM
To: dev@ctakes.apache.org
Subject: Re: CAS Visual Debugger - [EXTERNAL]

+1

Also, I’d love to be able to point CVD to a directory containing XMI files at 
startup.

Dima



On Oct 25, 2017, at 12:41, Miller, Timothy 
>
 wrote:

I've had the same thought, and come to the same conclusions.
Tim


From: Melvin Ma >
Sent: Wednesday, October 25, 2017 1:33 PM
To: dev@ctakes.apache.org
Subject: CAS Visual Debugger - [EXTERNAL]

This is more of a question. I am fully aware that CAS Visual Debugger is 
maintained in UIMA project.

For me for now, I will frequently need to use CVD to view .xmi file. It would 
be really nice if I could put the type system xml as an input to CVD startup 
argument (instead of manully lookup this file and load it). Do you know anyway 
to do it? I checked the documents multiple times and was not able to find 
anything.

Thanks.

Melvin

Re: CAS Visual Debugger - [EXTERNAL]

[Dligach, Dmitriy]

+1

Also, I’d love to be able to point CVD to a directory containing XMI files at 
startup.

Dima



On Oct 25, 2017, at 12:41, Miller, Timothy 
>
 wrote:

I've had the same thought, and come to the same conclusions.
Tim


From: Melvin Ma >
Sent: Wednesday, October 25, 2017 1:33 PM
To: dev@ctakes.apache.org
Subject: CAS Visual Debugger - [EXTERNAL]

This is more of a question. I am fully aware that CAS Visual Debugger is
maintained in UIMA project.

For me for now, I will frequently need to use CVD to view .xmi file. It
would be really nice if I could put the type system xml as an input to CVD
startup argument (instead of manully lookup this file and load it). Do you
know anyway to do it? I checked the documents multiple times and was not
able to find anything.

Thanks.

Melvin

Re: CAS Visual Debugger - [EXTERNAL]

[Miller, Timothy]

I've had the same thought, and come to the same conclusions.
Tim


From: Melvin Ma 
Sent: Wednesday, October 25, 2017 1:33 PM
To: dev@ctakes.apache.org
Subject: CAS Visual Debugger - [EXTERNAL]

This is more of a question. I am fully aware that CAS Visual Debugger is
maintained in UIMA project.

For me for now, I will frequently need to use CVD to view .xmi file. It
would be really nice if I could put the type system xml as an input to CVD
startup argument (instead of manully lookup this file and load it). Do you
know anyway to do it? I checked the documents multiple times and was not
able to find anything.

Thanks.

Melvin

CAS Visual Debugger -

[Melvin Ma]

This is more of a question. I am fully aware that CAS Visual Debugger is
maintained in UIMA project.

For me for now, I will frequently need to use CVD to view .xmi file. It
would be really nice if I could put the type system xml as an input to CVD
startup argument (instead of manully lookup this file and load it). Do you
know anyway to do it? I checked the documents multiple times and was not
able to find anything.

Thanks.

Melvin

RE: Piper File - [EXTERNAL]

[Finan, Sean]

Hi Melvin,

There shouldn't be any change needed, but let me check ... it could be that I 
need to specifically include that piper in the .jar ... 

-Original Message-
From: Melvin Ma [mailto:ma.qian...@gmail.com] 
Sent: Wednesday, October 25, 2017 12:45 PM
To: dev@ctakes.apache.org
Subject: Piper File - [EXTERNAL]

Sean - I am actually replying your earlier email. I have deleted the email by 
an accident. So here is a new thread.


I searched up all the .piper files in the source and only 
"DictionarySubPipe.piper" file was not included in the *-res*.jar file 
downloaded from maven repo. It appears that pom.xml was quite different in 
ctakes-dictionary-lookup-fast-res project. Should we make a small change the 
pom.xml file in ctakes-dictionary-lookup-fast-res project to include the 
DictionarySubPipe.piper file? Thanks!


-
contains / project name / piper file name

xx - found in the project jar file
?? -- missing
-

xx  ctakes-assertion-resAssertionSubPipe.piper
xx  ctakes-assertion-resAttributeCleartkSubPipe.piper
xx  ctakes-chunker-res  ChunkerSubPipe.piper
xx  ctakes-clinical-pipeline-resDefaultFastPipeline.piper
xx  ctakes-coreference-res  CorefSubPipe.piper
xx  ctakes-core-res DefaultTokenizerPipeline.piper
xx  ctakes-core-res AdvancedTokenizerPipeline.piper
??  ctakes-dictionary-lookup-fast-res   DictionarySubPipe.piper

Piper File -

[Melvin Ma]

Sean - I am actually replying your earlier email. I have deleted the email
by an accident. So here is a new thread.


I searched up all the .piper files in the source and only
"DictionarySubPipe.piper" file was not included in the *-res*.jar file
downloaded from maven repo. It appears that pom.xml was quite different in
ctakes-dictionary-lookup-fast-res project. Should we make a small change
the pom.xml file in ctakes-dictionary-lookup-fast-res project to include
the DictionarySubPipe.piper file? Thanks!


-
contains / project name / piper file name

xx - found in the project jar file
?? -- missing
-

xx  ctakes-assertion-resAssertionSubPipe.piper
xx  ctakes-assertion-resAttributeCleartkSubPipe.piper
xx  ctakes-chunker-res  ChunkerSubPipe.piper
xx  ctakes-clinical-pipeline-resDefaultFastPipeline.piper
xx  ctakes-coreference-res  CorefSubPipe.piper
xx  ctakes-core-res DefaultTokenizerPipeline.piper
xx  ctakes-core-res AdvancedTokenizerPipeline.piper
??  ctakes-dictionary-lookup-fast-res   DictionarySubPipe.piper

Re: cTAKES as REST service

[Matthew Vita]

Please note that the solution will not use a request/response cycle because
my main use case is with EMRs and I am batching up requests so as to not
exhaust cTAKES :)


Thanks,

Matthew Vita
www.matthewvita.com

On Wed, Oct 25, 2017 at 9:27 AM, Matthew Vita 
wrote:

> Gandhi,
>
> I am actually working on a series of Docker containers that expose an HTTP
> endpoint to send clinical text to and then it POSTs the results back to
> your application's HTTP endpoint in JSON. Please let me know if this
> approach interests you and we can schedule a Google Hangouts to talk about
> what work is left (I estimate that I will be done in a month and a half).
>
> Please do note that this solution is 100% free/open source :)
>
>
> Thanks,
>
> Matthew Vita
> www.matthewvita.com
>
> On Wed, Oct 25, 2017 at 6:20 AM, Gandhi Rajan Natarajan <
> gandhi.natara...@arisglobal.com> wrote:
>
>> Hi All,
>>
>> We have extended the cTAKES web application available under
>> https://github.com/healthnlp/examples/tree/master/ctakes-temporal-demo
>> and added our custom annotator. We have tested the same and it works fine
>> with CVD. But we are facing problems while trying to expose this as rest
>> service.
>>
>> cTAKES uses Spring 3.1.2 version internally which don't have out of the
>> box support for rest controller. Can we go ahead and update the spring
>> version to 4x in cTAKES? Will it have any impact in the cTAKES behavior?
>> Also is there a better way to expose cTAKES as rest service apart from
>> spring?
>>
>> Please advise.
>>
>> Regards,
>> Gandhi
>>
>> This email and any files transmitted with it are confidential and
>> intended solely for the use of the individual or entity to whom they are
>> addressed. If you are not the named addressee you should not disseminate,
>> distribute or copy this e-mail. Please notify the sender or system manager
>> by email immediately if you have received this e-mail by mistake and delete
>> this e-mail from your system. If you are not the intended recipient you are
>> notified that disclosing, copying, distributing or taking any action in
>> reliance on the contents of this information is strictly prohibited and
>> against the law.
>>
>
>

Re: cTAKES as REST service

[Matthew Vita]

Gandhi,

I am actually working on a series of Docker containers that expose an HTTP
endpoint to send clinical text to and then it POSTs the results back to
your application's HTTP endpoint in JSON. Please let me know if this
approach interests you and we can schedule a Google Hangouts to talk about
what work is left (I estimate that I will be done in a month and a half).

Please do note that this solution is 100% free/open source :)


Thanks,

Matthew Vita
www.matthewvita.com

On Wed, Oct 25, 2017 at 6:20 AM, Gandhi Rajan Natarajan <
gandhi.natara...@arisglobal.com> wrote:

> Hi All,
>
> We have extended the cTAKES web application available under
> https://github.com/healthnlp/examples/tree/master/ctakes-temporal-demo
> and added our custom annotator. We have tested the same and it works fine
> with CVD. But we are facing problems while trying to expose this as rest
> service.
>
> cTAKES uses Spring 3.1.2 version internally which don't have out of the
> box support for rest controller. Can we go ahead and update the spring
> version to 4x in cTAKES? Will it have any impact in the cTAKES behavior?
> Also is there a better way to expose cTAKES as rest service apart from
> spring?
>
> Please advise.
>
> Regards,
> Gandhi
>
> This email and any files transmitted with it are confidential and intended
> solely for the use of the individual or entity to whom they are addressed.
> If you are not the named addressee you should not disseminate, distribute
> or copy this e-mail. Please notify the sender or system manager by email
> immediately if you have received this e-mail by mistake and delete this
> e-mail from your system. If you are not the intended recipient you are
> notified that disclosing, copying, distributing or taking any action in
> reliance on the contents of this information is strictly prohibited and
> against the law.
>

RE: false positive [EXTERNAL]

[Finan, Sean]

Hi again,

The blacklists should now accept comma-separated semantic group codes.

Thanks,
Sean

-Original Message-
From: Kean Kaufmann [mailto:k...@recordsone.com.INVALID] 
Sent: Wednesday, October 25, 2017 10:38 AM
To: dev@ctakes.apache.org
Subject: Re: false positive [EXTERNAL]

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? e.g.

1,2,3,4,5,6|finicky thing

b) Have you found the "disease/disorder" vs. "sign/symptom" distinction useful? 
 For CAC purposes, we've introduced a superset ProblemMention into the type 
system so we don't have to bother with it.  Maybe an extra semantic group 
("23"?) would come in similarly handy.

Appreciatively,
Kean




On Wed, Oct 25, 2017 at 9:46 AM, Finan, Sean < 
sean.fi...@childrens.harvard.edu> wrote:

> Hi Gandhi, Abilash Mathew,
>
> This is a common problem stemming from the nature of the umls and 
> automated dictionary creation.  I am still (ever so slowly) improving 
> the dictionary creator code.  If anybody can devote some time to help 
> that would be great.
>
> Anyway, if you are using ctakes trunk there is a new capability of the 
> -fast dictionary lookup.  Basically, you can "blacklist" texts that 
> you do not want.
>
> 1. Create a bar-separated value (bsv) file containing the ctakes 
> numeric code for a semantic group and the text that you don't want.
> 2. Set the parameter "Blacklist" to point to the file.
>
> The ctakes numeric semantic group codes can be found in the CONST 
> class in ctakes-type-system.  The pertinent codes:
> 1 = medication
> 2 = disease / disorder
> 3 = sign / symptom
> 5 = procedure
> 6 = anatomical site
> 9 = lab
> 0 = unknown
>
> Example:
>
> // My Blacklist File.
> # double-slash and hash indicate comment lines.
> 3|Finding
> 5|test
> 5|Procedure
> 1|Page
> 5|treatment
> 1|medicine
> 1|Drug
> // Not sure what "finicky thing" belongs to, so I'll just add a bunch:
> 1|finicky thing
> 2|finicky thing
> 3|finicky thing
> 5|finicky thing
> 6|finicky thing
>
> The semantic group codes are there so that you can (for instance) make 
> ctakes ignore "1|Drug" as a generic indication some medication but 
> keep "drug" as a procedure.  For instance "aspirin is a drug" versus 
> "the patient was drugged before proceeding".
>
> Once you have the file, set "Blacklist" to point to the file as you 
> would other ctakes pipeline parameters.
>
> Use of the texts in the blacklist is case insensitive.  There is no 
> difference between adding "1|DRUG" and "1|drug".
> If you do want case sensitivity ...  you can use a blacklist file 
> pointed to by the parameter "CsBlacklist".
>
> I think that is about it.
>
> Sean
>
> -Original Message-
> From: Gandhi Rajan Natarajan [mailto:gandhi.natara...@arisglobal.com]
> Sent: Wednesday, October 25, 2017 9:14 AM
> To: dev@ctakes.apache.org
> Subject: RE: false positive [EXTERNAL]
>
> Hi Abilash,
>
> I'm not sure how much it will make sense. But in our custom annotator 
> we wrote on top of cTAKES, we resolved this false positives to an 
> extent by using commonly used English words metadata available from OpenNLP.
>
> Regards,
> Gandhi
>
> -Original Message-
> From: abilash.mat...@cognizant.com 
> [mailto:abilash.mat...@cognizant.com]
> Sent: Wednesday, October 25, 2017 3:57 PM
> To: dev@ctakes.apache.org
> Subject: false positive
>
> Hi all,
>
> We are seeing some false positives identified by CTAKES after we 
> tested couple of medical records samples. Can anyone help us on how to 
> ignore these words from tagging incorrectly?
>
> Word
>
> Finding
>
> test
>
> Procedure
>
> Page
>
> Procedure
>
> treatment
>
> Procedure
>
> medicine
>
> Drug
>
> medication
>
> Drug
>
> attachments
>
> Procedure
>
> RELEASE
>
> Procedure
>
> reconstruction
>
> Procedure
>
> DOB
>
> Drug
>
> Procedure
>
> Procedure
>
> Division
>
> Procedure
>
>
> Thanks,
> Abilash Mathew
> This e-mail and any files transmitted with it are for the sole use of 
> the intended recipient(s) and may contain confidential and privileged 
> information. If you are not the intended recipient(s), please reply to 
> the sender and destroy all copies of the original message. Any 
> unauthorized review, use, disclosure, dissemination, forwarding, 
> printing or copying of this email, and/or any action taken in reliance 
> on the contents of this e-mail is strictly prohibited and may be 
> unlawful. Where permitted by applicable law, this e-mail and other 
> e-mail communications sent to and from Cognizant e-mail addresses may be 
> monitored.
> This email and any files transmitted with it are confidential and 
> intended solely for the use of the individual or entity to whom they are 
> addressed.
> If you are not the named addressee you should not disseminate, 
> distribute 

RE: Running Piper File [EXTERNAL] [SUSPICIOUS]

[Finan, Sean]

Hi Melvin,

This has been changed.

Thanks,
Sean

-Original Message-
From: Finan, Sean [mailto:sean.fi...@childrens.harvard.edu] 
Sent: Tuesday, October 24, 2017 6:27 PM
To: dev@ctakes.apache.org
Subject: RE: Running Piper File [EXTERNAL] [SUSPICIOUS]

Hi Melvin,
Thanks.  There was originally a reason for not crashing the run, but I think 
that this behavior can be changed.
Were you able to get the paths working correctly (piper file found)?
Sean

-Original Message-
From: Melvin Ma [mailto:ma.qian...@gmail.com] 
Sent: Tuesday, October 24, 2017 6:15 PM
To: dev@ctakes.apache.org
Subject: Running Piper File [EXTERNAL]

I am assemblying my own app and trying to run the DefaultFastPipeline.piper 
file. I noticed that the following error did not blow up the system:

*24 Oct 2017 14:56:21 ERROR PiperFileReader - No piper file found for
DictionarySubPipe.piper*
*24 Oct 2017 14:56:21 ERROR PiperFileReader - Could not read piper file:
DictionarySubPipe.piper*


Ideally, this should be an error that exit the main program. Thanks,

Melvin

RE: false positive [EXTERNAL]

[Finan, Sean]

Hi Kean,

That is a good idea regarding the comma-separated semantic codes.  Give me a 
moment ...

In the Boston Children's group we do use the differentiation between s/s and 
d/d all the time.  It is extremely important to us and combining the two would 
ruin some of our projects.  It is used in term subsumption, temporal event 
creation, relation resolution and a bunch of other things.  That being said, I 
do have a special consumer in one project that allows overlapping d/d spans to 
subsume s/s spans ...

Personally, I think that ctakes can do better than relying upon a handful of 
numeric codes, but they are what we have.  It seems that we map to codes then 
map to types ...  If there are any ideas in the trenches ...
The semantic groups are determined by the more fine-grained semantic types 
associated with concepts.  You can find the types used listed in the 
dictionary-fast class SemanticUtil.

Cheers,
Sean



-Original Message-
From: Kean Kaufmann [mailto:k...@recordsone.com.INVALID] 
Sent: Wednesday, October 25, 2017 10:38 AM
To: dev@ctakes.apache.org
Subject: Re: false positive [EXTERNAL]

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? e.g.

1,2,3,4,5,6|finicky thing

b) Have you found the "disease/disorder" vs. "sign/symptom" distinction useful? 
 For CAC purposes, we've introduced a superset ProblemMention into the type 
system so we don't have to bother with it.  Maybe an extra semantic group 
("23"?) would come in similarly handy.

Appreciatively,
Kean




On Wed, Oct 25, 2017 at 9:46 AM, Finan, Sean < 
sean.fi...@childrens.harvard.edu> wrote:

> Hi Gandhi, Abilash Mathew,
>
> This is a common problem stemming from the nature of the umls and 
> automated dictionary creation.  I am still (ever so slowly) improving 
> the dictionary creator code.  If anybody can devote some time to help 
> that would be great.
>
> Anyway, if you are using ctakes trunk there is a new capability of the 
> -fast dictionary lookup.  Basically, you can "blacklist" texts that 
> you do not want.
>
> 1. Create a bar-separated value (bsv) file containing the ctakes 
> numeric code for a semantic group and the text that you don't want.
> 2. Set the parameter "Blacklist" to point to the file.
>
> The ctakes numeric semantic group codes can be found in the CONST 
> class in ctakes-type-system.  The pertinent codes:
> 1 = medication
> 2 = disease / disorder
> 3 = sign / symptom
> 5 = procedure
> 6 = anatomical site
> 9 = lab
> 0 = unknown
>
> Example:
>
> // My Blacklist File.
> # double-slash and hash indicate comment lines.
> 3|Finding
> 5|test
> 5|Procedure
> 1|Page
> 5|treatment
> 1|medicine
> 1|Drug
> // Not sure what "finicky thing" belongs to, so I'll just add a bunch:
> 1|finicky thing
> 2|finicky thing
> 3|finicky thing
> 5|finicky thing
> 6|finicky thing
>
> The semantic group codes are there so that you can (for instance) make 
> ctakes ignore "1|Drug" as a generic indication some medication but 
> keep "drug" as a procedure.  For instance "aspirin is a drug" versus 
> "the patient was drugged before proceeding".
>
> Once you have the file, set "Blacklist" to point to the file as you 
> would other ctakes pipeline parameters.
>
> Use of the texts in the blacklist is case insensitive.  There is no 
> difference between adding "1|DRUG" and "1|drug".
> If you do want case sensitivity ...  you can use a blacklist file 
> pointed to by the parameter "CsBlacklist".
>
> I think that is about it.
>
> Sean
>
> -Original Message-
> From: Gandhi Rajan Natarajan [mailto:gandhi.natara...@arisglobal.com]
> Sent: Wednesday, October 25, 2017 9:14 AM
> To: dev@ctakes.apache.org
> Subject: RE: false positive [EXTERNAL]
>
> Hi Abilash,
>
> I'm not sure how much it will make sense. But in our custom annotator 
> we wrote on top of cTAKES, we resolved this false positives to an 
> extent by using commonly used English words metadata available from OpenNLP.
>
> Regards,
> Gandhi
>
> -Original Message-
> From: abilash.mat...@cognizant.com 
> [mailto:abilash.mat...@cognizant.com]
> Sent: Wednesday, October 25, 2017 3:57 PM
> To: dev@ctakes.apache.org
> Subject: false positive
>
> Hi all,
>
> We are seeing some false positives identified by CTAKES after we 
> tested couple of medical records samples. Can anyone help us on how to 
> ignore these words from tagging incorrectly?
>
> Word
>
> Finding
>
> test
>
> Procedure
>
> Page
>
> Procedure
>
> treatment
>
> Procedure
>
> medicine
>
> Drug
>
> medication
>
> Drug
>
> attachments
>
> Procedure
>
> RELEASE
>
> Procedure
>
> reconstruction
>
> Procedure
>
> DOB
>
> Drug
>
> Procedure
>
> Procedure
>
> Division
>
> Procedure
>
>
> Thanks,
> Abilash Mathew
> This e-mail and any files transmitted with it are for 

Re: false positive [EXTERNAL]

[Kean Kaufmann]

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? e.g.

1,2,3,4,5,6|finicky thing

b) Have you found the "disease/disorder" vs. "sign/symptom" distinction
useful?  For CAC purposes, we've introduced a superset ProblemMention into
the type system so we don't have to bother with it.  Maybe an extra
semantic group ("23"?) would come in similarly handy.

Appreciatively,
Kean




On Wed, Oct 25, 2017 at 9:46 AM, Finan, Sean <
sean.fi...@childrens.harvard.edu> wrote:

> Hi Gandhi, Abilash Mathew,
>
> This is a common problem stemming from the nature of the umls and
> automated dictionary creation.  I am still (ever so slowly) improving the
> dictionary creator code.  If anybody can devote some time to help that
> would be great.
>
> Anyway, if you are using ctakes trunk there is a new capability of the
> -fast dictionary lookup.  Basically, you can "blacklist" texts that you do
> not want.
>
> 1. Create a bar-separated value (bsv) file containing the ctakes numeric
> code for a semantic group and the text that you don't want.
> 2. Set the parameter "Blacklist" to point to the file.
>
> The ctakes numeric semantic group codes can be found in the CONST class in
> ctakes-type-system.  The pertinent codes:
> 1 = medication
> 2 = disease / disorder
> 3 = sign / symptom
> 5 = procedure
> 6 = anatomical site
> 9 = lab
> 0 = unknown
>
> Example:
>
> // My Blacklist File.
> # double-slash and hash indicate comment lines.
> 3|Finding
> 5|test
> 5|Procedure
> 1|Page
> 5|treatment
> 1|medicine
> 1|Drug
> // Not sure what "finicky thing" belongs to, so I'll just add a bunch:
> 1|finicky thing
> 2|finicky thing
> 3|finicky thing
> 5|finicky thing
> 6|finicky thing
>
> The semantic group codes are there so that you can (for instance) make
> ctakes ignore "1|Drug" as a generic indication some medication but keep
> "drug" as a procedure.  For instance "aspirin is a drug" versus "the
> patient was drugged before proceeding".
>
> Once you have the file, set "Blacklist" to point to the file as you would
> other ctakes pipeline parameters.
>
> Use of the texts in the blacklist is case insensitive.  There is no
> difference between adding "1|DRUG" and "1|drug".
> If you do want case sensitivity ...  you can use a blacklist file pointed
> to by the parameter "CsBlacklist".
>
> I think that is about it.
>
> Sean
>
> -Original Message-
> From: Gandhi Rajan Natarajan [mailto:gandhi.natara...@arisglobal.com]
> Sent: Wednesday, October 25, 2017 9:14 AM
> To: dev@ctakes.apache.org
> Subject: RE: false positive [EXTERNAL]
>
> Hi Abilash,
>
> I'm not sure how much it will make sense. But in our custom annotator we
> wrote on top of cTAKES, we resolved this false positives to an extent by
> using commonly used English words metadata available from OpenNLP.
>
> Regards,
> Gandhi
>
> -Original Message-
> From: abilash.mat...@cognizant.com [mailto:abilash.mat...@cognizant.com]
> Sent: Wednesday, October 25, 2017 3:57 PM
> To: dev@ctakes.apache.org
> Subject: false positive
>
> Hi all,
>
> We are seeing some false positives identified by CTAKES after we tested
> couple of medical records samples. Can anyone help us on how to ignore
> these words from tagging incorrectly?
>
> Word
>
> Finding
>
> test
>
> Procedure
>
> Page
>
> Procedure
>
> treatment
>
> Procedure
>
> medicine
>
> Drug
>
> medication
>
> Drug
>
> attachments
>
> Procedure
>
> RELEASE
>
> Procedure
>
> reconstruction
>
> Procedure
>
> DOB
>
> Drug
>
> Procedure
>
> Procedure
>
> Division
>
> Procedure
>
>
> Thanks,
> Abilash Mathew
> This e-mail and any files transmitted with it are for the sole use of the
> intended recipient(s) and may contain confidential and privileged
> information. If you are not the intended recipient(s), please reply to the
> sender and destroy all copies of the original message. Any unauthorized
> review, use, disclosure, dissemination, forwarding, printing or copying of
> this email, and/or any action taken in reliance on the contents of this
> e-mail is strictly prohibited and may be unlawful. Where permitted by
> applicable law, this e-mail and other e-mail communications sent to and
> from Cognizant e-mail addresses may be monitored.
> This email and any files transmitted with it are confidential and intended
> solely for the use of the individual or entity to whom they are addressed.
> If you are not the named addressee you should not disseminate, distribute
> or copy this e-mail. Please notify the sender or system manager by email
> immediately if you have received this e-mail by mistake and delete this
> e-mail from your system. If you are not the intended recipient you are
> notified that disclosing, copying, distributing or taking any action in
> reliance on the contents of this 

RE: cTAKES as REST service [EXTERNAL]

[Gandhi Rajan Natarajan]

Hi Sean,

Thanks for the instant response. Will try to upgrade to Spring 4 and keep you 
posted about the progress.

Regards,
Gandhi


-Original Message-
From: Finan, Sean [mailto:sean.fi...@childrens.harvard.edu]
Sent: Wednesday, October 25, 2017 7:28 PM
To: dev@ctakes.apache.org
Subject: RE: cTAKES as REST service [EXTERNAL]

Hi Gandhi,

You can always build ctakes in your sandbox with spring 4 and see if it works.  
This may require some "maven magic"(overrides) on your part.  If it does seem 
to work please create a jira item to upgrade the spring version.  Then 
hopefully before the next release somebody will thoroughly test an update.

Offhand I don't know if or why spring is needed for ctakes itself.  At a quick 
search it looks like uimafit requires it.  Does anybody out there know what 
spring capabilities are used, directly or indirectly, by ctakes modules?

Thanks,
Sean

-Original Message-
From: Gandhi Rajan Natarajan [mailto:gandhi.natara...@arisglobal.com]
Sent: Wednesday, October 25, 2017 9:20 AM
To: dev@ctakes.apache.org
Subject: cTAKES as REST service [EXTERNAL]

Hi All,

We have extended the cTAKES web application available under 
https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_healthnlp_examples_tree_master_ctakes-2Dtemporal-2Ddemo=DwIFAg=qS4goWBT7poplM69zy_3xhKwEW14JZMSdioCoppxeFU=fs67GvlGZstTpyIisCYNYmQCP6r0bcpKGd4f7d4gTao=e5GMRO_5OwQhQrkfpV5fwBp7uG07tZVd1u_xJRo9wDs=meOj7MzEliqIQEhU_FeQwEnsUrWFSzgk5ihSEzoGRCI=
 and added our custom annotator. We have tested the same and it works fine with 
CVD. But we are facing problems while trying to expose this as rest service.

cTAKES uses Spring 3.1.2 version internally which don't have out of the box 
support for rest controller. Can we go ahead and update the spring version to 
4x in cTAKES? Will it have any impact in the cTAKES behavior? Also is there a 
better way to expose cTAKES as rest service apart from spring?

Please advise.

Regards,
Gandhi

This email and any files transmitted with it are confidential and intended 
solely for the use of the individual or entity to whom they are addressed. If 
you are not the named addressee you should not disseminate, distribute or copy 
this e-mail. Please notify the sender or system manager by email immediately if 
you have received this e-mail by mistake and delete this e-mail from your 
system. If you are not the intended recipient you are notified that disclosing, 
copying, distributing or taking any action in reliance on the contents of this 
information is strictly prohibited and against the law.
This email and any files transmitted with it are confidential and intended 
solely for the use of the individual or entity to whom they are addressed. If 
you are not the named addressee you should not disseminate, distribute or copy 
this e-mail. Please notify the sender or system manager by email immediately if 
you have received this e-mail by mistake and delete this e-mail from your 
system. If you are not the intended recipient you are notified that disclosing, 
copying, distributing or taking any action in reliance on the contents of this 
information is strictly prohibited and against the law.

RE: cTAKES as REST service [EXTERNAL]

[Finan, Sean]

Hi Gandhi,

You can always build ctakes in your sandbox with spring 4 and see if it works.  
This may require some "maven magic"(overrides) on your part.  If it does seem 
to work please create a jira item to upgrade the spring version.  Then 
hopefully before the next release somebody will thoroughly test an update.

Offhand I don't know if or why spring is needed for ctakes itself.  At a quick 
search it looks like uimafit requires it.  Does anybody out there know what 
spring capabilities are used, directly or indirectly, by ctakes modules?

Thanks,
Sean

-Original Message-
From: Gandhi Rajan Natarajan [mailto:gandhi.natara...@arisglobal.com] 
Sent: Wednesday, October 25, 2017 9:20 AM
To: dev@ctakes.apache.org
Subject: cTAKES as REST service [EXTERNAL]

Hi All,

We have extended the cTAKES web application available under 
https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_healthnlp_examples_tree_master_ctakes-2Dtemporal-2Ddemo=DwIFAg=qS4goWBT7poplM69zy_3xhKwEW14JZMSdioCoppxeFU=fs67GvlGZstTpyIisCYNYmQCP6r0bcpKGd4f7d4gTao=e5GMRO_5OwQhQrkfpV5fwBp7uG07tZVd1u_xJRo9wDs=meOj7MzEliqIQEhU_FeQwEnsUrWFSzgk5ihSEzoGRCI=
 and added our custom annotator. We have tested the same and it works fine with 
CVD. But we are facing problems while trying to expose this as rest service.

cTAKES uses Spring 3.1.2 version internally which don't have out of the box 
support for rest controller. Can we go ahead and update the spring version to 
4x in cTAKES? Will it have any impact in the cTAKES behavior? Also is there a 
better way to expose cTAKES as rest service apart from spring?

Please advise.

Regards,
Gandhi

This email and any files transmitted with it are confidential and intended 
solely for the use of the individual or entity to whom they are addressed. If 
you are not the named addressee you should not disseminate, distribute or copy 
this e-mail. Please notify the sender or system manager by email immediately if 
you have received this e-mail by mistake and delete this e-mail from your 
system. If you are not the intended recipient you are notified that disclosing, 
copying, distributing or taking any action in reliance on the contents of this 
information is strictly prohibited and against the law.

RE: false positive [EXTERNAL]

[Finan, Sean]

Hi Gandhi, Abilash Mathew,

This is a common problem stemming from the nature of the umls and automated 
dictionary creation.  I am still (ever so slowly) improving the dictionary 
creator code.  If anybody can devote some time to help that would be great.

Anyway, if you are using ctakes trunk there is a new capability of the -fast 
dictionary lookup.  Basically, you can "blacklist" texts that you do not want.

1. Create a bar-separated value (bsv) file containing the ctakes numeric code 
for a semantic group and the text that you don't want.
2. Set the parameter "Blacklist" to point to the file.

The ctakes numeric semantic group codes can be found in the CONST class in 
ctakes-type-system.  The pertinent codes:
1 = medication
2 = disease / disorder
3 = sign / symptom
5 = procedure
6 = anatomical site
9 = lab
0 = unknown

Example:

// My Blacklist File.
# double-slash and hash indicate comment lines.
3|Finding
5|test
5|Procedure
1|Page
5|treatment
1|medicine
1|Drug
// Not sure what "finicky thing" belongs to, so I'll just add a bunch:
1|finicky thing
2|finicky thing
3|finicky thing
5|finicky thing
6|finicky thing

The semantic group codes are there so that you can (for instance) make ctakes 
ignore "1|Drug" as a generic indication some medication but keep "drug" as a 
procedure.  For instance "aspirin is a drug" versus "the patient was drugged 
before proceeding".

Once you have the file, set "Blacklist" to point to the file as you would other 
ctakes pipeline parameters.  

Use of the texts in the blacklist is case insensitive.  There is no difference 
between adding "1|DRUG" and "1|drug".
If you do want case sensitivity ...  you can use a blacklist file pointed to by 
the parameter "CsBlacklist".

I think that is about it.

Sean

-Original Message-
From: Gandhi Rajan Natarajan [mailto:gandhi.natara...@arisglobal.com] 
Sent: Wednesday, October 25, 2017 9:14 AM
To: dev@ctakes.apache.org
Subject: RE: false positive [EXTERNAL]

Hi Abilash,

I'm not sure how much it will make sense. But in our custom annotator we wrote 
on top of cTAKES, we resolved this false positives to an extent by using 
commonly used English words metadata available from OpenNLP.

Regards,
Gandhi

-Original Message-
From: abilash.mat...@cognizant.com [mailto:abilash.mat...@cognizant.com]
Sent: Wednesday, October 25, 2017 3:57 PM
To: dev@ctakes.apache.org
Subject: false positive

Hi all,

We are seeing some false positives identified by CTAKES after we tested couple 
of medical records samples. Can anyone help us on how to ignore these words 
from tagging incorrectly?

Word

Finding

test

Procedure

Page

Procedure

treatment

Procedure

medicine

Drug

medication

Drug

attachments

Procedure

RELEASE

Procedure

reconstruction

Procedure

DOB

Drug

Procedure

Procedure

Division

Procedure


Thanks,
Abilash Mathew
This e-mail and any files transmitted with it are for the sole use of the 
intended recipient(s) and may contain confidential and privileged information. 
If you are not the intended recipient(s), please reply to the sender and 
destroy all copies of the original message. Any unauthorized review, use, 
disclosure, dissemination, forwarding, printing or copying of this email, 
and/or any action taken in reliance on the contents of this e-mail is strictly 
prohibited and may be unlawful. Where permitted by applicable law, this e-mail 
and other e-mail communications sent to and from Cognizant e-mail addresses may 
be monitored.
This email and any files transmitted with it are confidential and intended 
solely for the use of the individual or entity to whom they are addressed. If 
you are not the named addressee you should not disseminate, distribute or copy 
this e-mail. Please notify the sender or system manager by email immediately if 
you have received this e-mail by mistake and delete this e-mail from your 
system. If you are not the intended recipient you are notified that disclosing, 
copying, distributing or taking any action in reliance on the contents of this 
information is strictly prohibited and against the law.

cTAKES as REST service

[Gandhi Rajan Natarajan]

Hi All,

We have extended the cTAKES web application available under 
https://github.com/healthnlp/examples/tree/master/ctakes-temporal-demo and 
added our custom annotator. We have tested the same and it works fine with CVD. 
But we are facing problems while trying to expose this as rest service.

cTAKES uses Spring 3.1.2 version internally which don't have out of the box 
support for rest controller. Can we go ahead and update the spring version to 
4x in cTAKES? Will it have any impact in the cTAKES behavior? Also is there a 
better way to expose cTAKES as rest service apart from spring?

Please advise.

Regards,
Gandhi

This email and any files transmitted with it are confidential and intended 
solely for the use of the individual or entity to whom they are addressed. If 
you are not the named addressee you should not disseminate, distribute or copy 
this e-mail. Please notify the sender or system manager by email immediately if 
you have received this e-mail by mistake and delete this e-mail from your 
system. If you are not the intended recipient you are notified that disclosing, 
copying, distributing or taking any action in reliance on the contents of this 
information is strictly prohibited and against the law.

RE: false positive

[Gandhi Rajan Natarajan]

Hi Abilash,

I'm not sure how much it will make sense. But in our custom annotator we wrote 
on top of cTAKES, we resolved this false positives to an extent by using 
commonly used English words metadata available from OpenNLP.

Regards,
Gandhi

-Original Message-
From: abilash.mat...@cognizant.com [mailto:abilash.mat...@cognizant.com]
Sent: Wednesday, October 25, 2017 3:57 PM
To: dev@ctakes.apache.org
Subject: false positive

Hi all,

We are seeing some false positives identified by CTAKES after we tested couple 
of medical records samples. Can anyone help us on how to ignore these words 
from tagging incorrectly?

Word

Finding

test

Procedure

Page

Procedure

treatment

Procedure

medicine

Drug

medication

Drug

attachments

Procedure

RELEASE

Procedure

reconstruction

Procedure

DOB

Drug

Procedure

Procedure

Division

Procedure


Thanks,
Abilash Mathew
This e-mail and any files transmitted with it are for the sole use of the 
intended recipient(s) and may contain confidential and privileged information. 
If you are not the intended recipient(s), please reply to the sender and 
destroy all copies of the original message. Any unauthorized review, use, 
disclosure, dissemination, forwarding, printing or copying of this email, 
and/or any action taken in reliance on the contents of this e-mail is strictly 
prohibited and may be unlawful. Where permitted by applicable law, this e-mail 
and other e-mail communications sent to and from Cognizant e-mail addresses may 
be monitored.
This email and any files transmitted with it are confidential and intended 
solely for the use of the individual or entity to whom they are addressed. If 
you are not the named addressee you should not disseminate, distribute or copy 
this e-mail. Please notify the sender or system manager by email immediately if 
you have received this e-mail by mistake and delete this e-mail from your 
system. If you are not the intended recipient you are notified that disclosing, 
copying, distributing or taking any action in reliance on the contents of this 
information is strictly prohibited and against the law.

false positive

[Abilash.Mathew]

Hi all,

We are seeing some false positives identified by CTAKES after we tested couple 
of medical records samples. Can anyone help us on how to ignore these words 
from tagging incorrectly?

Word

Finding

test

Procedure

Page

Procedure

treatment

Procedure

medicine

Drug

medication

Drug

attachments

Procedure

RELEASE

Procedure

reconstruction

Procedure

DOB

Drug

Procedure

Procedure

Division

Procedure


Thanks,
Abilash Mathew
This e-mail and any files transmitted with it are for the sole use of the 
intended recipient(s) and may contain confidential and privileged information. 
If you are not the intended recipient(s), please reply to the sender and 
destroy all copies of the original message. Any unauthorized review, use, 
disclosure, dissemination, forwarding, printing or copying of this email, 
and/or any action taken in reliance on the contents of this e-mail is strictly 
prohibited and may be unlawful. Where permitted by applicable law, this e-mail 
and other e-mail communications sent to and from Cognizant e-mail addresses may 
be monitored.