You are viewing a plain text version of this content. The canonical link for it is here.
Posted to notifications@ctakes.apache.org by "alina shapira (JIRA)" <ji...@apache.org> on 2015/11/24 17:53:11 UTC
[jira] [Commented] (CTAKES-369) UmlsConcept subject is not
recognized propely
[ https://issues.apache.org/jira/browse/CTAKES-369?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15024841#comment-15024841 ]
alina shapira commented on CTAKES-369:
--------------------------------------
I think this is the same issue I found few weeks ago and opened another item for this.
take a look here:
https://issues.apache.org/jira/browse/CTAKES-390?jql=project%20%3D%20CTAKES%20AND%20resolution%20%3D%20Unresolved%20AND%20priority%20%3D%20Major%20ORDER%20BY%20key%20DESC
I did the research and found the bug. The fix should take no more than a few minutes.
I added all the info to the item
> UmlsConcept subject is not recognized propely
> ---------------------------------------------
>
> Key: CTAKES-369
> URL: https://issues.apache.org/jira/browse/CTAKES-369
> Project: cTAKES
> Issue Type: Bug
> Components: ctakes-assertion, ctakes-clinical-pipeline
> Affects Versions: 3.2.2
> Environment: Linux
> Reporter: Tomasz Oliwa
> Attachments: family_history.txt
>
>
> Hi,
> I think there is a regression in the way cTAKES discovers the subject status ("patient", "familiy_member", etc.) of an UmlsConcept. Using cTAKES 3.2.2 and the AggregatePlaintextFastUMLSProcessor of the clinical pipeline in the CVD:
> 1. "Patient's brother has a myocardial infarction."
> "myocardial infarction" and "infarction" have subject = "patient"
> 2. "Father had a myocardial infarction."
> "myocardial infarction" and "infarction" have subject = "patient"
> 3. "Sister was diagnosed with a myocardial infarction."
> "myocardial infarction" and "infarction" have subject = "patient"
> 4. "Family member had a myocardial infarction."
> "myocardial infarction" and "infarction" have subject = "family_member" (this is correct)
> I am looking at the code of the SubjectCleartkAnalysisEngine. It looks like this is the code the pipeline calls to inferr the subject. How can this be fixed?
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)