[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[eu_members at aclweb dot org] Washington, DC: Challenges in NLP for Clinical Data: 4th i2b2/VA Shared Task & Workshop



****Sample data and annotation guidelines have been released****

*** http://www.i2b2.org/NLP ***

Announcement of Data Release and Call for Participation

Fourth i2b2/VA Shared-Task and Workshop
Challenges in Natural Language Processing for Clinical Data
Data Release: 15 April, 2010
Evaluation: 22-24 July, 2010
Paper Submission: 1 September, 2010
Workshop: November, 2010 in Washington, DC

*** http://www.i2b2.org/NLP ***

The fourth i2b2/VA challenge is a three tiered challenge that studies:
- extraction of medical problems, tests, and treatments
- classification of assertions made on medical problems
- relations of medical problems, tests, and treatments

The data for this challenge includes discharge summaries from Partners 
HealthCare and from Beth Israel Deaconess Medical Center (MIMIC II 
Database), as well as discharge summaries and progress notes from 
University of Pittsburgh Medical Center. All records have been fully 
de-identified and manually annotated for concept, assertion, and 
relation information. Participants of the Fourth i2b2/VA Challenge can 
choose to tackle any subset of the tiers. There is no limitation on 
the number of tiers a team can participate in.

The challenge registration started on March 15, 2010. Training data 
for the challenge will be released in installments starting April 15, 
2010. Test data are scheduled to be released in July 2010. The results 
of the challenge will be presented at the workshop organized by i2b2 
and VA.
Data for the Fourth i2b2/VA Challenge will be released under a Data 
Use Agreement and are to be used for research only. Obtaining the data 
requires completing a registration and signing the Data Use Agreement.

Evaluation Dates, File Formats, and Evaluation Metrics.
The Fourth i2b2/VA Challenge evaluation will be conducted using 
withheld test data. Participating teams are asked to stop development 
as soon as they download the test data. Each team is allowed to upload 
(through this website) up to three system runs for each of the tiers 
of the challenge. System output is expected in the form of standoff 
annotations, following the exact format of the ground truth 
annotations provided by the organizers. Precision, recall, and 
f-measure will be used as evaluation metrics.

Participants are asked to submit a short paper describing their system 
and analyzing their performance. Papers should be in AMIA style and 
should not exceed five pages. Authors of top performing systems and of 
particularly novel approaches will be invited to present or demo their 
systems at the workshop.

Tentative Schedule
March 15, 2010 Registration Opens
April 15, 2010 Training Data Release
July 22, 2010 Test Data Release
September 1, 2010 Short Papers Due
October 1, 2010 Invitations to Present at the Workshop
November, 2010 Workshop

Organizing Committee:
Ozlem Uzuner, co-chair, SUNY at Albany and Middle East Technical 
University Northern Cyprus Campus
Scott L DuVall, co-chair, VA Salt Lake City Health Care System
Imre Solti, University of Washington
Leonard D'Avolio, VA Boston Healthcare System, Center for Surgery and 
Public Health, Brigham and Women's Hospital, Harvard School of Medicine
Wendy Chapman, Department of Biomedical Informatics, University of Pittsburgh
Shuying Shen, VA Salt Lake City Health Care System
Norris Harber Heintzelman, Lockheed Martin, IS&GS
Brett R South, VA Salt Lake City Health Care System, University of 
Utah, Department of Internal Medicine
Jennifer Hornung Garvin, VA Salt Lake City Health Care System and the 
University of Utah School of Medicine
Charlene Weir, VA Salt Lake City Health Care System, GRECC

Please see the FAQs and announcements for more information. Questions 
on the challenge can be addressed to Ozlem Uzuner, i2b2nlp at albany dot edu.