Input: Two files (priimary and secondary) comprising annotations from clinical information extraction systems or manually-annotated reports. The files must map to the Workbench Information Model.
Action: Calculates outcome measures for all secondary file annotations when compared against the primary file annotations (considered correct answers)
Output: A visualization of all annotations and their outcome measures
Funded by ONC SHARP Area 4 and VA Consortium for Healthcare Informatics Research
Intended user type:
10/17/11 - Beta system available - only reads output of Topaz and medication annotations from cTAKES in progress. Next version will read in output of any system using a UIMA pipeline.
3/2012 - Can now read in UIMA type system to assist user in mapping annotations made by their UIMA system and the workbench information model. Can also read in Knowtator (and eHOST) input.
7/1/2012 - Release of the first version here: http://idash.ucsd.edu/nlpew-evaluation-workbench
Has demo data for viewing output of Topaz system. Can read in UIMA data. Working on being able to read in Knowtator output.