Versions Compared

Old Version 3

changes.mady.by.user Unknown User (bleeker)

Saved on

compared with

New Version 4

changes.mady.by.user Unknown User (bleeker)

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
Section
Column
width65%


Panel
titleContents of this Page
Table of Contents
minLevel2


Column
Include Page
CTAKES:Menu cTAKES 2.6 to Include
CTAKES:Menu cTAKES 2.6 to Include

These
instructions are for end users. With these instructions you can install
cTAKES, configure it, and use it to process text (typically text
associated with a medical record). If you were planning to expand,
change, or modify the code within cTAKES, refer to the cTAKES 2.5 6 Developer Install InstructionsGuide.

These instructions will cover installation and a test of the main product including trained models for sentence detection and tagging parts of speech, dictionaries from a subset of the UMLS, a very small subset of the full LVG resource, etc. Optional components will also be described.

...

Step

Example

1. Navigate to the source downloads for a released version on SourceForge

2. Download the cTAKES-2.56.zip file.
Save the file to a temporary location on your machine.

Image Modified

3.
Unzip (extract the contents of) the compressed file you downloaded into
a directory that you want to be the cTAKES install location.
For example, Windows:

Code Block
languagenone
c:\cTAKES-2.56

Linux:

Code Block
languagenone
/usr/bin/cTAKES-2.56

This folder we will call <cTAKES_HOME>. You will need to refer to the directory later.

Image Modified

Process documents using cTAKES

...

Step

Example

1. Open a command prompt and change to the cTAKES_HOME directory.
Windows:

Code Block
languagenone
cd \cTAKES-2.56

Linux:

Code Block
languagenone
cd /usr/bin/cTAKES-2.56


Note
titleNote

cTAKES_HOME must be your current directory unless you are skilled at setting paths on your machine.

2. Start the CAS Visual Debugger by running this command:
Windows:

Code Block
languagenone
runctakesCVD.bat

Linux:

Code Block
languagenone
runctakesCVD.sh

The application may take a minute to start on slower hardware.

3. An analysis engine (AE) needs to be loaded in order to process text.
Use the Run-> *Load AE*menu bar command. Navigate to the file

Code Block
languagenone
<cTAKES_HOME>/cTAKESdesc/cdpdesc/analysis_engine/AggregatePlaintextProcessor.xml

Click Open.

4. Copy the text in the example at the right (next cell) and paste the
contents into the Text section of CVD, replacing the text that is
already there.
This example file can also be found in test data:

Code Block
languagenone
<cTAKES_HOME>/testdata/cdptest/testinput/plaintext/testpatient_plaintext_1.txt

Dr. Nutritious

Medical Nutrition Therapy for Hyperlipidemia

Referral from: Julie Tester, RD, LD, CNSD
Phone contact: (555) 555-1212
Height: 144 cm Current Weight: 45 kg Date of current weight: 02-29-2001
Admit Weight: 53 kg BMI: 18 kg/m2
Diet: General
Daily Calorie needs (kcals): 1500 calories, assessed as HB + 20% for activity.
Daily Protein needs: 40 grams, assessed as 1.0 g/kg.
Pt has been on a 3-day calorie count and has had an average intake of 1100 calories.
She was instructed to drink 2-3 cans of liquid supplement to help promote weight gain.
She agrees with the plan and has my number for further assessment. May want a Resting
Metabolic Rate as well. She takes an aspirin a day for knee pain.

3. From the menu bar, click Run -> Run AggregatePlaintextProcessor.
You'll get a list of all the annotations in the Analysis Results frame.

4. Named entities are now recognized in this clinical document.
Annotations of MedicationEventMention and EntityMention are created. To
find one, in the Analysis Results frame, click on the key in front of:
AnnotationIndex
uima.tcas.Annotation
edu.mayo.bmi.uima.core.type.textsem.IdentifiedAnnotation
edu.mayo.bmi.uima.core.type.textsem.EntityMention
and
edu.mayo.bmi.uima.core.type.textsem.EventMention
edu.mayo.bmi.uima.core.type.textsem.EventMention.MedicationEventMention

Then select edu.mayo.bmi.uima.core.type.textsem.EntityMention*or *edu.mayo.bmi.uima.core.type.textsem.EventMention.MedicationEventMention.This
will show an Annotation Index in the lower frame. Select any
annotation in that lower frame and you will see the text discovered in
the Text frame on the right. You may close CVD if you wish.

...

Step

Example

1. Open a command prompt and change to the cTAKES_HOME directory:
Windows:

Code Block
languagenone
cd C:\cTAKES2.56

Linux:

Code Block
languagenone
cd /usr/bin/cTAKES2.56


Note
titleNote

Note that cTAKES_HOME must be your current directory unless you are skilled at setting paths on your machine.

...

2. Start the collection processing engine by running this command:
Windows:

Code Block
languagenone
runctakesCPE.bat

Linux:

Code Block
languagenone
runctakesCPE.sh

The application may take a minute to start on slower hardware.

3. This will bring up the Collection Processing Engine Configurator. In the Menu bar click File >Open CPE Descriptor

4. Navigate to the file

Code Block
languagenone
<cTAKES_HOME>/cTAKESdesc/cdpdesc/collection_processing_engine/test_plaintext.xml

Click Open.

5. Click the Play button (green/blue play arrow near the bottom).

6. You should see that one document was processed. You did process a collection of documents. In this case the collection only contained one just to show how to do it. Close the results window.

7. Close the CPE application. You may be prompted to save changes. Since this was just a test you may click the No button.

8. Open a new command prompt and change to the <cTAKES_HOME>

No example.

9. To test the results there is a comparison tool that will help show that the results match expectations with the following syntax:

Code Block
languagenone
java -cp cTAKES.jar edu.mayo.bmi.utils.xcas_comparison.Compare
<First File> <Second File> <diff-html>

Where: <First File> is the first file to compare; <Second File> is the second file to compare; <diff-html> is where the results are written to
Copy and paste the example at the right (next cell) which has had our
example files already substituted into a command prompt to run. In this
case we have shipped an example of what the output should be for you to
compare against.

Windows:

Code Block
languagenone
java -cp cTAKES.jar edu.mayo.bmi.utils.xcas_comparison.Compare ^
"testdata\cdptest\testoutput\plaintext\sample_note_plaintext.xml" ^
"testdata\cdptest\testsampleoutput\plaintext\sample_note_plaintext.xml" ^
c:\stuff\diff-html.html

Linux:

Code Block
languagenone
java edu.mayo.bmi.utils.xcas_comparison.Compare \
"/usr/bin/cTAKES2.56/testdata/cdptest/testoutput/plaintext\sample_note_plaintext.xml" \
"/usr/bin/cTAKES2.56/testdata/cdptest/testsampleoutput/plaintext/sample_note_plaintext.xml" \
/tmp/diff-html.html

10. The resulting file will open for you. Look at the comparison to see the annotations resulting from this pipeline.
Windows:

Code Block
languagenone
c:\stuff\diff-html.html

Linux:

Code Block
languagenone
/tmp/diff-html.html

...

Annotator

Description

Abbreviated

Example Analysis Engine (AE)

Example Collection processing Engine (CPE)

Example test data

Clinical Document Pipeline

the complete cTAKES pipeline to obtain majority of cTAKES annotations

cdp

cTAKES_HOME/cTAKESdesc/cdpdesc/analysis_engine/AggregatePlaintextProcessor.xml

cTAKES_HOME/cTAKESdesc/cdpdesc/collection_processing_engine/test_plaintext.xml

cTAKES_HOME/testdata/cdptest

Chunker

obtain cTAKES chunking annotations

chunker

cTAKES_HOME/cTAKESdesc/chunkerdesc/analysis_engine/ChunkerAggregate.xml

cTAKES_HOME/cTAKESdesc/chunkerdesc/collection_processing_engine/ChunkerCPE.xml

cTAKES_HOME/testdata/chunkertest

Dependency Parser

obtain dependency parsing tree

dp

cTAKES_HOME/cTAKESdesc/dpdesc/analysis_engine/ClearParserTokenizedInfPosAggregate.xml

cTAKES_HOME/cTAKESdesc/dpdesc/collection_processing_engine/ClearParserCPE.xml

cTAKES_HOME/testdata/dptest

Drug NER

the annotator to obtain drug annotations

drugner

cTAKES_HOME/cTAKESdesc/drugnerdesc/analysis_engine/DrugAggregatePlaintextProcesor.xml

cTAKES_HOME/cTAKESdesc/drugnerdesc/collection_processing_engine/DrugNER_PlainText_CPE.xml

cTAKES_HOME/testdata/drugnertest

Dictionary Lookup

mapping cTAKES annotations to dictionaries (e.g., SNOMED_CT or RxNorm

lookup

cTAKES_HOME/cTAKESdesc/lookupdesc/analysis_engine/TestAggregateTAE.xml

cTAKES_HOME/cTAKESdesc/lookupdesc/collection_processing_engine/LookupCPE.xml

cTAKES_HOME/testdata/lookuptest

PAD Term Spotter

identifying terms related to PAD

pad

cTAKES_HOME/cTAKESdesc/paddesc/analysis_engine/Radiology_TermSpotterAnnotatorTAE.xml

cTAKES_HOME/cTAKESdesc/paddesc/collection_processing_engine/Radiology_Sample.xml

cTAKES_HOME/testdata/padtest

Smoking Status

the annotator to obtain document or patient-level smoking status

smoking

cTAKES_HOME/cTAKESdesc/smokingdesc/analysis_engine/SimulatedProdSmokingTAE.xml

cTAKES_HOME/cTAKESdesc/smokingdesc/collection_processing_engine/Sample_SmokingStatus_output_flatfile.xml

cTAKES_HOME/testdata/smokingtest

Side Effect

the annotator to find side effect mentions and sentences from clinical documents

sideeffect

cTAKES_HOME/cTAKESdesc/sideeffectdesc/analysis_engine/SideEffectAggregateTAE.xml

cTAKES_HOME/cTAKESdesc/sideeffectdesc/collection_processing_engine/SideEffectCPE.xml

cTAKES_HOME/testdata/sideeffecttest


Next Steps

The cTAKES 2.5 6 Component Use Guide will help you to understand in great detail each of the cTAKES components that have been installed. In some cases you can learn how to improve the components. However, before you go on to process text in production you will need to consider dictionaries and models.

...

Some models included in cTAKES may not represent your data distribution well. If you want to build or train your own models, please read the cTAKES 2.5 6 Component Use Guide, particularly:

  • Training a sentence detector model
  • Training a Part of Speech (POS) tagger model (Building a model Obtaining training data)
  • Creating a Part of Speech (POS) tag dictionary (Building a tag dictionary)
  • Training a chunker model (Building a model - Prepare GENIA training data)
  • Training a dependency parser (Dependency Parser)