cTAKES Tutorial and GUI Demo Pei Chen

Report
cTAKES
Part 1: cTAKES GUI (demo)
Part 2: cTAKES Tutorial
Pei J Chen
Children’s Hospital Boston /
Harvard Medical School
GUI: Key Features
Default Clinical Processing Pipeline
Default Central Store of cTAKES output
Abstraction from UIMA concepts
Dynamic Configuration
Centrally Managed Experiments
Preview Single Doc
Preview Output
Batch Processing
Dynamic Data Sources
Dynamic NLP Pipeline
Dynamic Processors
Centrally Stored Output
Sample output on GUI
Centrally Stored Output
RDMS (hypersonic DB)
Easily export results: select * from ctakes_experiment_result;
Technologies Used
Front-End
Middleware
Back-End
Web GUI
Web Services
cTAKES
– ExtJS
– JavaScript
 JAVA
 ExtDirect Spring
 JSON
– JAVA
– UIMA
– umiaFIT
Beta release available
 https://ohnlp.svn.sourceforge.net/svnroot/ohnlp/branche
s/cTAKES-GUI-0.0.1/ctakes-gui-0.0.1.zip
 Prerequisite:
– Java JDK (not JRE) 1.6+ installed
 Instructions:
– Unzip and run startup.sh or startup.bat
Thoughts?
Part 2: cTAKES Tutorial
 Technical Details
 cTAKES components
 Where to download cTAKES
 Documentation
cTAKES Technical Details
• Open source
• Apache v2.0 license
• Java 1.6
• Dependency on UMLS which requires a UMLS license (free)
• Framework
• IBM’s Unstructured Information Management Architecture (UIMA) open
source framework, Apache project
• Methods
• Natural Language Processing methods (NLP)
• Based on standards and conventions to foster interoperability
• Application
• High-throughput system
cTAKES: Components
•
•
•
•
•
•
Sentence boundary detection (OpenNLP technology)
Tokenization (rule-based)
Morphologic normalization (NLM’s LVG)
POS tagging (OpenNLP technology)
Shallow parsing (OpenNLP technology)
Named Entity Recognition
• Dictionary mapping (lookup algorithm)
• types: diseases/disorders, signs/symptoms, anatomical sites, procedures, medications
•
•
•
•
•
•
•
Assertion module
Dependency parser
Constituency parser
Semantic Role Labeler
Coreference resolver
Drug Profile module
Smoking status classifier
Download cTAKES
cTAKES (currently 2.5):


http://sourceforge.net/projects/ohnlp/files/cTAKES
svn co “https://ohnlp.svn.sourceforge.net/svnroot/ohnlp/branches/SHARPn-cTAKES/”
UIMA Core (2.3.1)

http://uima.apache.org/downloads.cgi
UIMA Eclipse IDE Plugin
Thoughts?

similar documents