Stephanie W. Haas
Information and Library Science
of North Carolina at Chapel Hill
||shaas at email dot unc dot edu
||111 Manning Hall
3360, 100 Manning Hall,
Chapel Hill, NC 27599-3360
Teaching -- Recent
INLS 512, Applications of
Natural Language Processing, Spring
INLS 523, Database 1,
Introduction to Database, Fall
INLS 582, Systems
and Triage Notes in the Emergency Department Patient Record
When you go to the emergency room, the triage nurse asks why you are
there. The chief complaint data element of your
patient record briefly records the major problem. The triage
note provides more detail, including symptoms, events (such
as a fall or accident), and other potentially relevant information. The
North Carolina Disease Event Tracking and Epidemiologic Collection
Tool, NC DETECT,
uses information from these data elements for public health
surveillance. Extracting useful information from the clinical
notes of the patient record for surveillance and other purposes is an
- Chief Complaint (2003 - 2008)
In a series of projects,
Travers, UNC School of Nursing, who developed the Emergency
Processor (EMT-P), Anna Waller, PI of NC DETECT,
Judith Tintinalli, both of UNC Department of Emergency
Medicine, and I
the form and content of chief complaints, with the eventual goal of
developing a standardized vocabulary.
Vocabulary Control for Chief Complaint: A National Symposium ,
held October 18, 2006, resulted in a white paper (Haas et al., 2008)
outlining specific recommendations for achieving this goal. Other
related papers are listed on my CV.
- Travers, D. A. & Haas, S. W. (2003). Using
nurses’ natural language entries to build a concept-oriented
terminology for patients’ chief complaints in the emergency department.
Journal of Biomedical Informatics, 36(4-5), 260-270.
- Travers, D. A. & Haas, S. W. (2004). Evaluation
of Emergency Medical Text Processor, a system for cleaning chief
complaint text data. Academic Emergency Medicine, 11(11), 1170-1176.
Haas, S. W. & Travers, D. A. (2004). Issues in the development
of a thesaurus for patients’ chief complaints in the hospital emergency
department. Proceedings of the 2004 Annual Meeting of the American
Society for Information Science and Technology, 411-417.
- Haas, S. W., Travers, D. A., Tintinalli, J. E., Pollock,
D., Waller, A., Barthell, E., et al. (2008). Towards Vocabulary Control
for Chief Complaint. Academic Emergency Medicine, 15(5), 476-482.
- Interpretation of Temporal Expressions in Triage
Notes (2007 - present)
The triage note tells the story of what happened before you came to the
emergency department. Time plays an important role in the story: How
long have you had the rash? When was the accident? Which started first,
the cough or the fever? In this project, we are studying how time is
expressed in the triage note, with the goal of developing rules extract
temporal expressions and place the associated events on a timeline.
Other related papers are listed on my CV.
- Irvine, A. K., Haas, S. W., & Sullivan, T. (2008)
TN-TIES: A system for extracting temporal information from Emergency
Department triage notes. Proceedings of the American Medical
Sullivan, T., Irvine, A., & Haas, S. W. (2008). It's all
relative: Usage of relative temporal expressions in triage notes.
Proceedings of the 2008 Annual Meeting of the American Society for
Information Science and Technology.
- Adapting Natural Language Processing Tools for
Biosurveillance (2009 - present)
The goal of this project is to incorporate information from the triage
note into syndrome classification algorithms. The challenge is
identifying relevant concepts in the triage note regardless of how they
are expressed. For example, presence of fever may be indicated by a
measured temperature, or the phrase skin feels hot to touch.
We are developing the Emergency Medical Text Classifier (EMT-C) to
improve classification of patient records into syndromes such as Gastro-Intestinal Severe
or Respiratory Illness.
Other related papers are listed on my CV.
D., Mostafa, J., Travers, D., Haas, SW, Waller, A. (2012). Automated
Syndrome Classification using Early Phase Emergency Department Data.
ACM SIGHIT International Health Informatics Symposium (poster).
D., Medlin, R., Travers, D., Haas, SW. (2011). Temporal Information
Extractor: Identifying Symptom Onset Date from Emergency Department
Notes. AMIA 2011 Annual Symposium.
Haas, S. W., Waller, A., Crouch, J., Mostafa, J., Schwartz, T. (2010).
Identifying evidence of fever in emergency department text. AMIA 2010
Annual Symposium, November 13-17, 2010, Washington, D.C. (poster)
- Haas, S.
Travers, D., Mahalingam, D., Crouch, J., Mostafa, J., Waller, A.
(2010). Burning up: Finding fever expressions in triage notes.
Proceedings of the 2010 Annual Meeting of the American Society for
Information Science and Technology., October 22-27, 2010, Pittsburgh,
Carolina Preparedness and Emergency Response Research Center
(NC PERRC) (2008 - present)
Director of the NC Institute for Public
The North Carolina Preparedness and Emergency Response Research Center
is one of seven centers at schools of public health funded by the
Centers for Disease Control and Prevention (CDC) to strengthen and
improve public health preparedness capacity through systems and
services research. NCPERRC focuses on North Carolina public health
systems and capabilities to develop and maintain sustainable
preparedness and response systems.
I am working on the
The goal of the surveillance project is to systematically assess the
performance of timely, electronic public health surveillance systems in
North Carolina and, based on the assessments, develop, implement and
analyze interventions for system performance improvement. My focus is
on studying the workflows and lines of communications of public health
- Samoff, E.,
Waller, A., Fleischauer, A, Ising, A., Davis, M. K., Park, M., Haas, S.
W., DiBiase, L., MacDonald, P. (2012). Integration of syndromic
surveillance data into public health practice at state and local levels
in North Carolina. Public Health Reports, 127(3), 310-317.
Communication Links Among Public Health Emergency Preparedness
Officials Using Social Network Analysis: A Pilot Study (2009 - present)
NC PERRC, we have been
conducting a pilot study investigating the feasibility and utility of
social network analysis (SNA) for
understanding existing patterns of
communication in the public health preparedness arena. Using the 2009
H1N1 as a case study, we are comparing communication patterns
and use of NC
DETECT during the outbreak with "normal"
- Bevc, CA,
Christopherson, L., Samoff, E., Haas SW. (2011). Understanding and
comparing patterns of communication in H1N1: Applying social network
analysis. Academy Health 2011 Annual Research Meeting, June 14-15,
Seattle, WA. (poster).
Christopherson, L, Haas, SW. (2011). Addressing Public Health Issues
with Social Network Analysis. NC PERRC Research Brief. Available from
GovStat (2000 -
The GovStat Project,
Gary Marchionini, UNC School of Information and Library
Science, co-PI (formally known as Integration of Data and Interfaces to
Enhance Human Understanding of Government Statistics: Toward the
National Statistical Knowledge Network),
"seeks to create an integrated model of user access to and use of US
government statistical information that is rooted in realistic data
models and innovative user interfaces."
Our project motto is find what you need, understand what you find.
My work on this project focused on the Statistical Interactive Glossary
(SIG), metadata for statistical tasks, and envisioning new kinds of
help for supporting users of statistics.
Papers and Presentations
the Bureau of Labor Statistics
This page was last
modified on January 7, 2013, by Stephanie W. Haas.
Address questions and comments about this page to Stephanie W. Haas at
shaas at email dot unc dot edu
© Stephanie W. Haas. All rights reserved.