Visual Analytics for Command, Control, and Interoperability Environments

Given a set of hospital admittance and death records, the VAST 2010 Mini Challenge 2 was to characterize the spread of a pandemic in terms of the attack and mortality rates, spatiotemporal patterns of onset and the recovery time. We began the analysis by preprocessing the hospital admittance records using the University of Pittsburgh’s CoCo classifier that takes hospital admittance text fields and classifies them into chief complaint categories.  Once the data was classified, we utilized and extended the work done by the Purdue University Visual Analytics Center on healthcare analysis. Our system consisted of a combination of linked views, showing time series views of syndromes and death rates through line graph views, stacked graph views showing deaths, geographical map views showing the impact by country, and summary windows providing statistical breakdowns of the data. All views are linked through an interactive time slider that allows users to explore the data over time. Extensions to our previous work include the stacked graph view, summary windows, new control chart methods, and an interactive ‘tape measure’ tool.

Our system won an award in the Support for Future Detection Category.  Our team members included Abish Malik, Shehzad Afzal, Dr. David S. Ebert and Dr. Ross Maciejewski from Purdue University and Erin Hodgess from the University of Houston - Downtown.