Return-Path: X-Original-To: apmail-ctakes-user-archive@www.apache.org Delivered-To: apmail-ctakes-user-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id B8CB210DFC for ; Fri, 6 Dec 2013 02:04:10 +0000 (UTC) Received: (qmail 23642 invoked by uid 500); 6 Dec 2013 02:04:10 -0000 Delivered-To: apmail-ctakes-user-archive@ctakes.apache.org Received: (qmail 23540 invoked by uid 500); 6 Dec 2013 02:04:10 -0000 Mailing-List: contact user-help@ctakes.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: user@ctakes.apache.org Delivered-To: mailing list user@ctakes.apache.org Received: (qmail 23533 invoked by uid 99); 6 Dec 2013 02:04:09 -0000 Received: from nike.apache.org (HELO nike.apache.org) (192.87.106.230) by apache.org (qpsmtpd/0.29) with ESMTP; Fri, 06 Dec 2013 02:04:09 +0000 X-ASF-Spam-Status: No, hits=2.2 required=5.0 tests=HTML_MESSAGE,RCVD_IN_DNSWL_NONE,SPF_PASS X-Spam-Check-By: apache.org Received-SPF: pass (nike.apache.org: domain of cybersation@hotmail.com designates 65.55.90.216 as permitted sender) Received: from [65.55.90.216] (HELO snt0-omc4-s13.snt0.hotmail.com) (65.55.90.216) by apache.org (qpsmtpd/0.29) with ESMTP; Fri, 06 Dec 2013 02:04:01 +0000 Received: from SNT148-W56 ([65.55.90.199]) by snt0-omc4-s13.snt0.hotmail.com with Microsoft SMTPSVC(6.0.3790.4675); Thu, 5 Dec 2013 18:03:39 -0800 X-TMN: [M09szmPsiidgKxHw8JJmazJuUMpECsei] X-Originating-Email: [cybersation@hotmail.com] Message-ID: Content-Type: multipart/alternative; boundary="_c38e4b16-05e7-4ee9-b80e-fef8192f9c98_" From: digital paula To: "user@ctakes.apache.org" Subject: RE: cTAKES Sectionizer: how to integrate it with clinical pipeline - Solved Date: Thu, 5 Dec 2013 21:03:39 -0500 Importance: Normal In-Reply-To: <924DE05C19409B438EB81DE683A942D910615C4C@CHEXMBX1A.CHBOSTON.ORG> References: ,<924DE05C19409B438EB81DE683A942D910614C7C@CHEXMBX1A.CHBOSTON.ORG>,,<924DE05C19409B438EB81DE683A942D910615C4C@CHEXMBX1A.CHBOSTON.ORG> MIME-Version: 1.0 X-OriginalArrivalTime: 06 Dec 2013 02:03:39.0933 (UTC) FILETIME=[61D52CD0:01CEF227] X-Virus-Checked: Checked by ClamAV on apache.org --_c38e4b16-05e7-4ee9-b80e-fef8192f9c98_ Content-Type: text/plain; charset="Windows-1252" Content-Transfer-Encoding: quoted-printable Pei=2C =20 =20 I appreciate you mentioning the preferredText feature for getting section h= eadings to render=2C the first column in the mapping file should suffice. =20 In a previous post=2C Tim stated that the sectionizer would be a huge benef= it to the research community once it's working or something along those lin= es. What was the problem with getting it to work? I ask because I didn't= encounter any issues during my preliminary testing. All I did was an inte= gration and minor configuration=2C as stated in my previous post. The rea= son why I'd like to know is so I'm cognizant of any known issues in case I = encounter them once I get back to using the sectionizer...should be in a fe= w days.=20 =20 Thanks. =20 Regards=2C Paula =20 From: Pei.Chen@childrens.harvard.edu To: user@ctakes.apache.org Subject: RE: cTAKES Sectionizer: how to integrate it with clinical pipelin= e - Solved Date: Thu=2C 5 Dec 2013 14:26:56 +0000 =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= Paula=2C=0A= Glad to hear it=92s working for you. Please feel free to let us know how i= t works out for you in your use case and dataset.=0A= =0A= >I didn't see it in the trunk so I manually added the text file ccda_secti= ons.txt taken from the sandbox. I added it under src/main/resources in c= takes-core:=0A= org/apache/ctakes/core/sections/ccda_sections.txt=0A= Check out: http://svn.apache.org/r1547576 ctakes/trunk/ctakes-core-res/src/= main/resources/org/apache/ctakes/core/sections/ccda_sections.txt (with pr= ops)=0A= =0A= >This would be good to have too: segmentHeading: HISTORY OF PRESENT ILLNES= S:=0A= =0A= There is a field called Segment.preferredText. Which should display the fi= rst text column in the mappings file=85 =0A= =0A= =0A= Thanks=2C=0A= Pei=0A= =0A= =0A= =0A= =0A= From: digital paula [mailto:cybersation@hotmail.com]=0A= =0A= Sent: Wednesday=2C December 04=2C 2013 8:59 PM =0A= To: user@ctakes.apache.org =0A= Subject: RE: cTAKES Sectionizer: how to integrate it with clinical pipeline= - Solved=0A= =0A= =0A= =0A= =0A= =0A= Pei=2C =0A= =0A= =0A= =0A= Okay=2C the sectionizer is now integrated in the clinical pipeline and I di= d some preliminary testing to confirm. I added the CDASegmentAnnotator lin= es that you stated to the Aggregate Descriptor and commented the simple ann= otator in the=0A= flow. In addition=2C I also had to comment out this in order for the Aggr= egate descriptor to save with no error:=0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= I didn't see it in the trunk so I manually added the text file ccda_sectio= ns.txt taken from the sandbox. I added it under src/main/resources in ct= akes-core:=0A= =0A= =0A= org/apache/ctakes/core/sections/ccda_sections.txt=0A= =0A= =0A= I tested on a few narratives and I'm attaching what returned using CVD tool= for one of them. The segmentID was populated with segmentID: 1.3.6.1.4= .1.19376.1.5.3.1.3.4. I looked in the ccda_sections.txt file and this w= as it:=0A= =0A= =0A= =0A= =0A= =0A= 1.3.6.1.4.1.19376.1.5.3.1.3.4=2C10164-2=2CHISTORY OF PRESENT ILLNESS=2Cbrie= f history of physical illness=2Chistory of present illness=2Chistory of the= present illness=0A= =0A= =0A= =0A= =0A= =0A= I looked back in the narrative and the heading was: =0A= HISTORY OF PRESENT ILLNESS: The patient..... =0A= =20 =0A= I just tested on a few narratives and though that hardly constitutes testi= ng because I need to resolve a more urgent issue for my research but will r= eturn to this for full testing entailing the application to all of my narra= tives. However=2C from a preliminary=0A= perspective=2C it looks good....only thing I'd like to see is the actual t= ext as well for the segment heading as another feature. For example what d= isplays is this: =0A= =0A= segmentID: 1.3.6.1.4.1.19376.1.5.3.1.3.4=20 =0A= This would be good to have too: =0A= segmentHeading: HISTORY OF PRESENT ILLNESS:=20 =0A= =20 =0A= Thanks. =20 =0A= =0A= =0A= Regards=2C =0A= Paula=0A= =0A= =20 =0A= =20 =0A= =0A= =0A= > From: Pei.Chen@childrens.harvard.edu =0A= > To: user@ctakes.apache.org =0A= > Subject: RE: cTAKES Sectionizer: how to integrate it with clinical pipeli= ne =0A= > Date: Tue=2C 3 Dec 2013 20:38:22 +0000 =0A= >=20 =0A= > Paula=2C =0A= > I moved the sectionizer to trunk now and added the xml descriptor for it. =0A= >=20 =0A= > In your Aggregate Descriptor=2C just add: =0A= > =0A= > =0A= > =20 =0A= > . =0A= > CDASegmentAnnotator=20 =0A= >=20 =0A= > If you would like to see it wired together via uimaFIT=2C check out the t= est case: =0A= > ctakes-core/src/test/java/org/apache/ctakes/core/ae/TestCDASegmentAnnotat= or.java =0A= >=20 =0A= > Hope that helps. =0A= > It might be even worthwhile defaulting to this instead of the SimpleSegme= nt (since simple segment does nothing more than span the entire document...= ) =0A= > --Pei =0A= >=20 =0A= >=20 =0A= >=20 =0A= > From: digital paula [mailto:cybersation@hotmail.com]=0A= =0A= > Sent: Tuesday=2C December 03=2C 2013 1:51 PM =0A= > To: user@ctakes.apache.org =0A= > Subject: cTAKES Sectionizer: how to integrate it with clinical pipeline =0A= >=20 =0A= > Hi Pei=2C =0A= > =20 =0A= > Last week we discussed briefly the sectionizer and now that I have it loa= ded successfully I just need to integrate it in the clinical pipeline. =0A= =0A= > =20 =0A= > The sectionizer doesn't have a desc folder with associated XML descriptor= and I understand that things are moving towards UIMAfit so that's probably= the reason why it doesn't. Can you provide some guidance on what you'd re= commend for testing the sectionizer? =0A= That is=2C should I just create the XML Descriptor using one of the refere= nce materials from the UIMA website for creating descriptors or would you r= ecommend using UIMAfit? If the latter=2C can you provide assistance of ho= w to integrate the sectionizer into=0A= the AggregatePlaintext AE using UIMAfit. =0A= > =20 =0A= > Thanks. =0A= > =20 =0A= > Regards=2C =0A= > Paula=0A= =0A= =0A= =0A= = --_c38e4b16-05e7-4ee9-b80e-fef8192f9c98_ Content-Type: text/html; charset="Windows-1252" Content-Transfer-Encoding: quoted-printable
Pei=2C =3B =3B
 = =3B
I =3Bappreciate you mentioning the preferredText feature for get= ting section headings to render=2C the first column in the mapping =3B = file should suffice.
 =3B
In a =3Bprevious post=2C Tim stated=  =3Bthat the sectionizer would be a huge benefit to the =3Bresearch= community once it's working or something along those lines. =3B = =3B What was the problem with getting it =3Bto work? =3B =3BI a= sk because I didn't encounter any issues during my preliminary testing.&nbs= p=3B All I =3Bdid =3Bwas =3Ban integration and minor configurat= ion=2C as stated in my previous post. =3B =3B The reason why I'd li= ke to know is so I'm cognizant of =3Bany =3Bknown issues in case I = encounter them =3Bonce I get back to using the sectionizer...should be = in a few days.
 =3B
Thanks.
 =3B
Regards=2C
Paula =3B
From: Pei.Chen@childrens.harvard= .edu
To: user@ctakes.apache.org
Subject: RE: cTAKES Sectionizer: how= to integrate it with clinical pipeline - Solved
Date: Thu=2C 5 Dec 2013= 14:26:56 +0000

=0A= =0A= =0A= =0A= =0A= =0A= =0A=
=0A=

Paula=2C=0A=

Glad to hear it= =92s working for you. =3B Please feel free to let us know how it works = out for you in your use case and dataset.

=0A=

 =3B=0A=

>=3BI didn't see it in the trunk so =3BI&nb= sp=3B manually added the text file ccda_sections.txt taken from the sandbox= . =3B =3B =3B =3BI added it under src/main/resources in cta= kes-core:

=0A=

org/apache/ctakes/core/sections/ccda_sections.txt=

=0A=

Check out: http://svn.apache.org/r1547576 ctakes/trunk/ctak= es-core-res/src/main/resources/org/apache/ctakes/core/sections/ccda_section= s.txt =3B =3B (with props)

=0A=

 =3B=0A=

>=3BThis wou= ld be good to have too: segmentHeading: =3B HISTORY OF PRESENT ILLNESS:= =0A=

=0A=

There is a fie= ld called Segment.preferredText. =3B Which should display the first tex= t column in the mappings file=85
=0A=
=0A=

=0A=

Thanks=2C<= /p>=0A=

Pei

=0A=

 =3B=0A=

=0A=
=0A=
=0A=

From: digital paula [mailto:cybersa= tion@hotmail.com]=0A=
=0A= Sent: Wednesday=2C December 04=2C 2013 8:59 PM
=0A= To: user@ctakes.apache.org
=0A= Subject: RE: cTAKES Sectionizer: how to integrate it with clinical p= ipeline - Solved

=0A=
=0A=
=0A=

 =3B

=0A=
=0A=
=0A=

Pei=2C
=0A=  =3B

=0A=
=0A=
=0A=

Okay=2C the sectionizer is now integrated in the = clinical pipeline and I did some preliminary testing to confirm. =3B I&= nbsp=3Badded the CDASegmentAnnotator lines that you stated to the Aggregate= Descriptor and =3Bcommented the =3Bsimple annotator in the=0A= flow. =3B In addition=2C I also had to comment out this in order for t= he Aggregate descriptor =3Bto save with no error:

=0A=
=0A= <=3B!--
=0A=
=0A=

<=3BconfigurationParameter>=3B
=0A= <=3Bname>=3BSegmentID<=3B/name>=3B
=0A= <=3Bdescription/>=3B
=0A= <=3Btype>=3BString<=3B/type>=3B
=0A= <=3BmultiValued>=3Bfalse<=3B/multiValued>=3B
=0A= <=3Bmandatory>=3Bfalse<=3B/mandatory>=3B
=0A= <=3Boverrides>=3B
=0A= <=3Bparameter>=3BSimpleSegmentAnnotator/SegmentID<=3B/parameter>=3B=  =3B
=0A= <=3B/overrides>=3B
=0A= <=3B/configurationParameter>=3B
=0A= -->=3B

=0A=
=0A=
=0A=

 =3B

=0A=
=0A=
=0A=

I didn't see it in the trunk so =3BI =3B = manually added the text file ccda_sections.txt taken from the sandbox. = =3B =3B =3B =3BI added it under src/main/resources in ctakes-co= re:

=0A=
=0A=
=0A=

org/apache/ctakes/core/sections/ccda_sections.txt=

=0A=
=0A=
=0A=

I tested on a few =3Bnarratives and I'm attac= hing what returned using CVD tool for one of them. =3B =3B =3B = The segmentID was populated with segmentID: =3B 1.3.6.1.4.1.19376.1.5.3= .1.3.4. =3B =3B =3B  =3BI looked in the ccda_sections.txt f= ile and this was it:

=0A=
=0A=
=0A=

 =3B

=0A=
=0A=
=0A=

1.3.6.1.4.1.19= 376.1.5.3.1.3.4=2C10164-2=2CHISTORY OF PRESENT ILLNESS=2Cbrief history of p= hysical illness=2Chistory of present illness=2Chistory of the present illne= ss

=0A=
=0A=
=0A=

 =3B

=0A=
=0A=
=0A=

I looked back in the narrative and the heading wa= s: =3B =0A= HISTORY OF PRESENT ILLNESS: The patient.....
=0A=  =3B
=0A= I just tested on =3Ba few =3Bnarratives and though that =3Bhard= ly =3Bconstitutes =3B testing because I need to resolve a more urge= nt issue for my research =3Bbut will return to this for full testing en= tailing the application to all of my narratives. =3B =3B However=2C= from a preliminary=0A= perspective=2C it looks good....only thing I'd like to see is the actual t= ext as well for the segment heading as another feature. =3B For example= what displays is this: =3B=0A=
=0A= segmentID: =3B 1.3.6.1.4.1.19376.1.5.3.1.3.4
=0A= This would be good to have too:
=0A= segmentHeading: =3B HISTORY OF PRESENT ILLNESS:
=0A=  =3B
=0A= Thanks. =3B
=0A=  =3B

=0A=
=0A=

Regards=2C
=0A= Paula

=0A=
=0A=  =3B
=0A=  =3B
=0A=
=0A=
=0A=

>=3B From: Pei.Chen@childrens.harvard.edu
= =0A= >=3B To: user@ctakes.apache.org
=0A= >=3B Subject: RE: cTAKES Sectionizer: how to integrate it with clinical p= ipeline
=0A= >=3B Date: Tue=2C 3 Dec 2013 20:38:22 +0000
=0A= >=3B
=0A= >=3B Paula=2C
=0A= >=3B I moved the sectionizer to trunk now and added the xml descriptor fo= r it.
=0A= >=3B
=0A= >=3B In your Aggregate Descriptor=2C just add:
=0A= >=3B <=3BdelegateAnalysisEngine key=3D"CDASegmentAnnotator">=3B
= =0A= >=3B <=3Bimport location=3D"../../../ctakes-core/desc/analysis_engine/C= DASegmentAnnotator.xml"/>=3B
=0A= >=3B <=3B/delegateAnalysisEngine>=3B
=0A= >=3B .
=0A= >=3B <=3Bnode>=3BCDASegmentAnnotator<=3B/node>=3B
=0A= >=3B
=0A= >=3B If you would like to see it wired together via uimaFIT=2C check out = the test case:
=0A= >=3B ctakes-core/src/test/java/org/apache/ctakes/core/ae/TestCDASegmentAn= notator.java
=0A= >=3B
=0A= >=3B Hope that helps.
=0A= >=3B It might be even worthwhile defaulting to this instead of the Simple= Segment (since simple segment does nothing more than span the entire docume= nt...)
=0A= >=3B --Pei
=0A= >=3B
=0A= >=3B
=0A= >=3B
=0A= >=3B From: digital paula [mailto:cybersation@hotmail.com]=0A=
=0A= >=3B Sent: Tuesday=2C December 03=2C 2013 1:51 PM
=0A= >=3B To: user@ctakes.apache.org=
=0A= >=3B Subject: cTAKES Sectionizer: how to integrate it with clinical pipel= ine
=0A= >=3B
=0A= >=3B Hi Pei=2C
=0A= >=3B  =3B
=0A= >=3B Last week we discussed briefly the sectionizer and now that I have i= t loaded successfully I just need to integrate it in the clinical pipeline.=  =3B =3B=0A=
=0A= >=3B  =3B
=0A= >=3B The sectionizer doesn't have a desc folder with associated =3BXM= L descriptor and I understand that things are moving towards UIMAfit so tha= t's probably the reason why it doesn't. =3B Can you provide some guidan= ce on what you'd recommend for testing the sectionizer? =3B=0A= That is=2C should I just create the XML Descriptor using one of the refere= nce materials from the UIMA website for creating descriptors or would you r= ecommend =3B using UIMAfit? =3B If the latter=2C can you provide as= sistance of how to integrate the sectionizer into=0A= the AggregatePlaintext AE using UIMAfit.
=0A= >=3B  =3B
=0A= >=3B Thanks.
=0A= >=3B  =3B
=0A= >=3B Regards=2C
=0A= >=3B Paula

=0A=
=0A=
=0A=
=0A=
= --_c38e4b16-05e7-4ee9-b80e-fef8192f9c98_--