BCIG SPEAKER EVENT:
“Information Visualization: Discovering Temporal Event Patterns in
Electronic Health Records”
Clinical
Center (Building 10) Medical Board Room (Room 2C116)
Abstract: After a general overview of information visualization and examples of
visualizations, we will focus on interfaces for Discovering Temporal Event
Patterns in Electronic Health Records. Specifying event sequence queries is
challenging even for skilled computer professionals familiar with SQL. We will
demonstrate our interactive search strategies that allow for aligning records on
important events, ranking, and filtering combined with grouping of results to
find common or rare events. A second design uses query-by-example, in which
users specify a pattern and see a similarity-ranked list of results. The
similarity measure can be customized by four decision criteria, with controls to
reduce the impact of missing, extra, or swapped events or the impact of time
shifts. We will report on our collaboration with
Washington
Hospital
Center
clinicians and administrators on case studies illustrating how these
visualization tools can help lead to important medical and operational insights.
For example we have studied temporal patterns in heparin-induced
thrombocytopenia, or adverse reactions to radiology contrast administration, and
monitored the incidence of bounce-back between floor and ICU. For more
information see:
www.cs.umd.edu/hcil/lifelines2 and
www.cs.umd.edu/hcil/similan
|
 |
3:30 - 5:00 pm February 11, 2009
Professor Catherine Plaisant
Associate Director of Research of the
Human-Computer Interaction Lab of the
University of Maryland Institute for
Advanced Computer Studies
The NIH Biomedical Computing Interest Group (BCIG) 2010 Distinguished Lecture
Series with the theme “The Interface of Computer Science, Statistics,
Informatics & Translational Medicine” continues Thursday, February 11 with a
lecture by Professor Catherine Plaisant entitled “Information Visualization:
Discovering Temporal Event Patterns in Electronic Health Records.” Dr. Plaisant
is Associate Director of Research of the
Human-Computer Interaction Lab of the
University of Maryland Institute for Advanced Computer Studies. She earned a
Doctorat d'Ingenieur degree in France in 1982 and has written over 100 refereed
technical publications on diverse subjects such as information visualization,
digital libraries, universal access, image browsing, help, digital humanities,
technology for families, or evaluation methodologies. She is a co-author with
Ben Shneiderman of "Designing the User Interface: Strategies for Effective
Human-Computer Interaction" (5th ed. March 2009)
http://www.pearsonhighered.com/dtui5einfo/. David Wang and Krist
Wongsuphasawat are Computer Science PhD students working with Catherine Plaisant
and Ben Shneiderman. The title of her BCIG presentation is “What Is Pattern
Recognition?” The lecture is 3:30 – 5:00 p.m. and will start at 3:30 p.m. sharp
at the Medical Board Room (Room 2C116), Building 10.
|
