Now seems like as good a time as any for an introduction. It is great to hear
about other organizations working to install cTAKES.
I'm a radiologist at UC Davis in Sacramento, and came across cTAKES back in
July. I have it up and running on a personal Windows laptop where I've used it
for some
See discussion in this thread:
https://www.mail-archive.com/dev@ctakes.apache.org/msg02873.html
I got around the ScalaObject error by changing from
AggregatePlaintextUMLSProcessor to AggregatePlaintextUMLSProcessorMinimal.
Tom
-Original Message-
From: shahid ashraf [mailto:sha...@trial
First off, thank you all and congratulations on this major release milestone.
I went through the dev install on a clean Ubuntu 17.04 desktop VM and while
things went pretty smoothly I had a few comments to add in case others are
going through the same process:
1. I received an error message
I'm having trouble changing the DefaultTermConsumer to my preferred
SemanticCleanupTermConsumer.
I followed the Dev install in Eclipse for cTAKES 4.0.
I'm referencing the cTAKES 4.0 Component Use Guide>Fast Dictionary Lookup>Most
Precise Terms Persistence, and I understand that I have to edit s
nary/lookup/fast/
Let me know if you don't see it after performing a mvn compile as that would
indicate a bug.
Thanks,
Sean
-----Original Message-
From: Thomas W Loehfelm [mailto:twloehf...@ucdavis.edu]
Sent: Tuesday, May 09, 2017 3:30 PM
To: dev@ctakes.apache.org
Subject: Issues chan
I've been banging my head against the all for a few weeks now and reaching out
for help.
I'm trying to do a fresh dev installation so I can finally move from developing
on my personal laptop to my work computer, and am not having any luck getting
up and running.
Here's what I'm doing:
1) Ne
I was very excited to find the ctakes-tiny-rest package in the svn repo, but
have not been able to get it stood up.
What I have tried:
1. Cloning the svn repo
2. mvn package
3. java -cp target/ctakes-tiny-rest-4.0.1-SNAPSHOT.jar
org.apache.ctakes.rest.service.TinyController
* Er
ot;umls", "cui", or
"xmi". "pretty" and "property" are works in progress. The default is fhir
json.
Sean
From: Thomas W Loehfelm
Sent: Friday, June 26, 2020 5:04 PM
To: dev@ctakes.apache.org
d symbol
[ERROR] symbol: class PostConstruct
[ERROR] location: package javax.annotation
What version of java are you using? ctakes requires version 8.
javax.annotation -should- be standard in java 8. You can try running "javac
-version".
Sean
_
out there has a quick answer, please speak up.
Sean
____
From: Thomas W Loehfelm
Sent: Wednesday, July 1, 2020 3:14 PM
To: dev@ctakes.apache.org
Subject: RE: ctakes-tiny-rest - any guidance on running? [EXTERNAL]
* External Email - Caution *
Not b
https://repository.apache.org/content/groups/snapshots/
false
true
That may help. Let me know if it does then I will add it to the pom in
trunk.
Sean
__
al.
I will test some more tonight and see what comes up.
Sean
________
From: Thomas W Loehfelm
Sent: Wednesday, July 1, 2020 7:34 PM
To: dev@ctakes.apache.org
Subject: Re: ctakes-tiny-rest - any guidance on running? [EXTERNAL]
[SUSPICIO
fix you submitted?
Yep. You did some great detective work.
Thanks for the additional info.
____
From: Thomas W Loehfelm
Sent: Monday, July 6, 2020 3:02 PM
To: dev@ctakes.apache.org
Subject: Re: ctakes-tiny-rest - any guidance on
If you have downloaded and created a local UMLS installation using the
MetamorphoSys tool you should end up with a directory structure something like:
../../umls/2020AA/META/{all of the various .RRF files}
In that case, you want to point the DictionaryCreator tool to the 2020AA
directory, i.e. t
I have a CTakes API endpoint based on the REST API and I am trying to specifiy
a different BSV file depending on the type of text.
My idea is to instantiate two different analysis engine pools, and direct text
one or the other depending on which type of report it is. This seems simpler to
me th
problem.
And to further clarify, the general concept works – both AE pools are created,
and both can process text, it is literally just that the SectionsBsv param
setting persists between the two so that the second pool ends up using the same
BSV file as the first one.
From: Thomas W Loehfelm
X_TO_A_SECTIONS = new HashMap<>()
> Map X_TO_B_SECTIONS = new HashMap<>()
> initRenameMaps() {
>X_TO_A_SECTIONS.put( "Stern", "Sternum" );
>X_TO_B_SECTIONS.put( "Stern", "Tough Guy" );
> }
> void adjustSectionInfo( String
For parallel processing, consider using the ctakes-dockhand component. You can
run ctakes as a docker service and then scale it using docker swarm to
replicate that service across many nodes to expand processing capacity.
I can am happy to share my experience doing it and the code I use, althoug
Thanks for the BERT negation classifier Tim - I tested it on a small sample of
radiology notes and didn't see a big improvement in accuracy (kudos to the
original ctakes pipeline!) but your framework of a FastAPI component that can
loosely interface with cTAKES was really interesting.
@Peter -
…or should it be spacyTAKES? Horrible name, but potentially useful tool. Thanks
again to Tim for the inspiration.
Proof-of-principle FastAPI tool here:
https://github.com/twloehfelm/ctakescy
This stands up a FastAPI endpoint to which you send a cTAKES CAS XMI file
(output from the clinical pipe
I use the BsvRegexSectionizer like so:
//This goes in your piper file
add BsvRegexSectionizer SectionsBsv=resources/your_regex_file.bsv
your_regex_file.bsv is a text file where each line is a bar-separated set of:
section_name||(regex statement to identify the section header)
I work in radiolog
Depending on the configuration of the dictionary lookup
(https://cwiki.apache.org/confluence/display/CTAKES/cTAKES+4.0+-+Fast+Dictionary+Lookup),
I think it is entirely possible that you will get some CUI differences under
your scenario. For example, if you are:
* comparing dictionary A + B
22 matches
Mail list logo
