Before and after Scrubber de-identification
1. XML formatted input
- Before: testcase.xml
- After: scrubbed_testcase.xml
2. Unstructured text input
- Before: testcase.txt
- After: scrubbed_testcase.txt
Scrubber 2.8 was used to scrub the examples cases.
Scrubber 3.0 has significantly better performance
Before and after cTAKES annotations
Automated concept retrieval : Medical vocabularies and data dictionary
Scrubber 3.X is being donated and ported to the Apache cTAKES project.
We are concentrating our efforts on this transition.