Seminars

General Departmental Seminar Series

Bayesian Alarm Functions and Health Surveillance

Andrew Lawson, Ph.D.,
Dept. of Epidemiology and Biostatistics, University of South Carolina

September 24, 2004, 12-1 pm in 5275 Medical Sciences Center, 1300 University Ave.

ABSTRACT

Since 9/11 counter terrorism surveillance has become a major research effort in the US. In public health this has led to extensive funding for State agencies to establish health surveillance systems. The technical issues in the development of methods and deployment of these systems are of major importance. Many systems have poorly developed statistical capabilities.

Recently much attention has been paid to temporal methods such as optimal surveillance and the use of cusum technology. When large databases of health data are to be mined for unusual events special methods need to be used. These methods will combine time series and spatial mapping to provide early detection (syndromic) capability.

This talk will discuss many of these issues and explore the development of Bayesian alarm functions for syndromic surveillance.

Reference: Lawson, A. B. and Kleinman, K. (2005) Spatial and Syndromic Surveillance for Public Health, Wiley

Return to seminar list