incubator-ctakes-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Tim Miller <timothy.mil...@childrens.harvard.edu>
Subject Re: Section Tagging Clinical Notes
Date Fri, 22 Feb 2013 20:01:29 GMT
For the record, there is a class called CONST in the type-system module 
that defines the polarity types (along with other attributes) -- if you 
are writing code you should use those constants 
(NE_POLARITY_NEGATION_ABSENT vs. NE_POLARITY_NEGATION_PRESENT). If 
you're not writing code then this is just a public service message to 
everyone else on the list!
Tim

On 02/22/2013 02:28 PM, Deepal Dhariwal wrote:
> Thanks for your quick reply.
>
> Regards
> Deepal Dhariwal
>
> On Fri, Feb 22, 2013 at 2:26 PM, Masanz, James J. <Masanz.James@mayo.edu>wrote:
>
>> Polarity = -1 means negated
>>
>> -- James Masanz
>>
>>> -----Original Message-----
>>> From: ctakes-dev-return-1278-Masanz.James=mayo.edu@incubator.apache.org
>>> [mailto:ctakes-dev-return-1278-
>>> Masanz.James=mayo.edu@incubator.apache.org] On Behalf Of Deepal Dhariwal
>>> Sent: Friday, February 22, 2013 11:58 AM
>>> To: ctakes-dev@incubator.apache.org
>>> Cc: ctakes-user@incubator.apache.org
>>> Subject: Re: Section Tagging Clinical Notes
>>>
>>> Hello Chen,
>>>
>>> Thanks a lot for informing. I'll follow the jira issue.
>>>
>>> Further I had also doubt regarding the assertion annotator. I have been
>>> using ctakes document processor on i2b2 data set. However even for terms
>>> such as "no shortness of breath" , the assertion results are as follows:
>>> confidence = 1.0
>>> polarity = -1
>>> uncertainty = 0
>>> conditional = false
>>> generic = false
>>> subject = patient
>>> entity = null
>>>
>>> Kindly let me know how to detect negation using ctakes assertion
>>> annotator.
>>> Identifying whether the condition is present or absent is important in
>>> my work.
>>>
>>> Regards
>>> Deepal Dhariwal
>>>
>>> On Fri, Feb 22, 2013 at 12:47 PM, Chen, Pei
>>> <Pei.Chen@childrens.harvard.edu>wrote:
>>>
>>>> Hi Deepal,
>>>> Just an FYI:
>>>> It looks like SectionSegmentAnnotator.java is in core, but the sample
>>>> SectionSegmentAnnotator.xml descriptor is in ctakes-clinical-pipeline.
>>>> https://issues.apache.org/jira/browse/CTAKES-169 has been opened to
>>>> fix this.
>>>>
>>>> --Pei
>>>>
>>>>> -----Original Message-----
>>>>> From: Chen, Pei [mailto:Pei.Chen@childrens.harvard.edu]
>>>>> Sent: Saturday, February 16, 2013 6:01 PM
>>>>> To: <ctakes-dev@incubator.apache.org>
>>>>> Cc: ctakes-dev@incubator.apache.org;
>>>>> ctakes-user@incubator.apache.org
>>>>> Subject: Re: Section Tagging Clinical Notes
>>>>>
>>>>> No. There should be one called SectionSegmentAnnotator.
>>>>>
>>>>> Sent from my iPhone
>>>>>
>>>>> On Feb 16, 2013, at 5:57 PM, "Deepal Dhariwal"
>>>>> <deepaldhariwal@gmail.com> wrote:
>>>>>
>>>>>> Hello Pei,
>>>>>>
>>>>>> Thanks for your quick reply. Are you referring to Simple Segment
>>>>>> Annotator from ctakes coredesc / analysis engine ?
>>>>>> Reference:
>>>>>> https://wiki.nci.nih.gov/display/VKC/cTAKES+2.5+-+Core#cTAKES25-Co
>>>>>> re-S
>>>>>> impleSegmentAnnotatorxml
>>>>>>
>>>>>> Regards
>>>>>> Deepal Dhariwal
>>>>>>
>>>>>>
>>>>>> On Sat, Feb 16, 2013 at 5:23 PM, Chen, Pei
>>>>>> <Pei.Chen@childrens.harvard.edu>wrote:
>>>>>>
>>>>>>> Hi Deepal,
>>>>>>> Check out the SectionSegmentAnnotator from ctakes-core project
>>>>>>> which was contributed by the MIT folks. There is a simple XML
>>>>>>> config for heading names.
>>>>>>>
>>>>>>> --Pei
>>>>>>>
>>>>>>> On Feb 16, 2013, at 1:58 PM, "Deepal Dhariwal"
>>>>>>> <deepaldhariwal@gmail.com>
>>>>>>> wrote:
>>>>>>>
>>>>>>>> Hello all,
>>>>>>>>
>>>>>>>> I was looking at
>>>>>>>> SecTag<
>>>>>>> http://knowledgemap.mc.vanderbilt.edu/research/content/sectag-
>>>>> tagging
>>>>>>> -clinical-note-section-headers
>>>>>>>> and
>>>>>>>> I was wondering whether ctakes has a provision or are planning
>>>>>>>> to have a Section Tag annotator. i.e. it annotates "History
of
>>>>>>>> Previous Illness", "Medications on Admission" as section
headers
>>>>>>>> in clinical
>>>>> documents.
>>>>>>>> Regards
>>>>>>>> Deepal Dhariwal


Mime
View raw message