DIMACS Working Group on Adverse Event/Disease Reporting, Surveillance, and Analysis I
DIMACS Subgroup on Adverse Event/Disease Reporting, Surveillance, and Analysis
Analytical methods for detecting unusual events and/or changepoints in univariate data streams have attracted considerable attention over the last several decades. In the context of syndromic surveillance, for example, methods based on control charts, scan statistics, Bayesian models, sequential probability ratio tests, etc., are common. Recently, however, practitioners face the new challenge of monitoring multidimensional data streams, often involving heterogenous data types and varying time scales. For example, a bioterrorism detection application might simultaneously monitor 911 call volume, syndromic codes from emergency room chief complaints, over-the-counter medications, and absenteeism.
This workshop will bring together researchers working on analytic methods in this area. The first morning will feature panels and talks on existing activities in multivariate surveillance. The afternoon will feature presentations on relevant analytical methods from other areas such as statistical process control, visualization, and temporal Bayesian networks. The second (half-day) will attempt to summarize the state-of-the-art and propose a research agenda.
See http://dimacs.rutgers.edu/Workshops/AdverseEvent