2019 n2c2/OHNLP Shared-Task and Workshop
Announcement and Call for Participation
We are pleased to announce the 2019 n2c2/OHNLP Shared Task on Challenges in Natural Language Processing for Clinical Data.
This year, National NLP Clinical Challenges (n2c2, formerly known as i2b2 NLP Shared Tasks) has teamed up with the Open Health Natural Language Processing (OHNLP) Initiative at Mayo Clinic to bring you two tasks:
- Track 1: n2c2/OHNLP Track on Clinical Semantic Textual Similarity
This task extends the BioCreative/OHNLP 2018 task on the same topic to new synthetic clinical notes.
- Track 2: n2c2/OHNLP Track on Family History Extraction
This task extends the BioCreative/OHNLP 2018 task on family history information extraction from synthetic notes.
In addition, we are happy to share with you the first community-led n2c2-spinoff shared task organized by University of Massachusetts at Lowell:
- Track 3: n2c2/UMass Track on Clinical Concept Normalization
Finally, we have added a new task for participants to submit any work they have done on past or current n2c2 data:
- Track 4: Novel Data Use
The four tracks will run on similar timelines and will be coordinated with respect to their dissemination efforts and the accompanying workshop.
Rough timeline is as follows:
- Registration begins: April 2019
- Training Data Release: May–June 2019
- Test Data Release: July 2019
- Abstracts due: August 2019
- Workshop: November 2019 [ Schedule | Registration ]
- Ozlem Uzuner, PhD, FACMI, George Mason University
- Yanshan Wang, PhD, Mayo Clinic
- Feichen Shen, PhD, Mayo Clinic
- Anna Rumshisky, PhD, University of Massachusetts at Lowell
- Yen-Fu Luo, PhD, University of Massachusetts at Lowell
The i2b2 Center (Informatics for Integrating Biology and the Bedside), funded by the National Institutes of Health (NIH) from 2004 to 2014 and based at Partners HealthCare System in Boston, was led by Principal Investigator Isaac Kohane, MD, PhD, and Executive Director Susanne Churchill, PhD. The i2b2 NLP Shared Task challenges/workshops and resulting research data sets were designed and led by Co-Investigator Ozlem Uzuner, MEng, PhD, originally at MIT CSAIL and subsequently at SUNY Albany.
Drs. Kohane and Churchill are now the inaugural Chair and Executive Director, respectively, of the Harvard Medical School Department of Biomedical Informatics (DBMI) , where the NLP Data Sets will remain under their stewardship. The NLP Shared Task challenges and workshops continue to be directed by Dr. Uzuner , now Associate Professor of Information Sciences and Technology in the Volgenau School of Engineering at George Mason University and Visiting Associate Professor of Biomedical Informatics at HMS DBMI.
The software development component of the former i2b2 Center is now under the direction of the i2b2 tranSMART Foundation , a member-driven non-profit foundation developing an open-source / open-data community around the i2b2, tranSMART and OpenBEL translational research platforms.