We propose new research into detection algorithms for BioSense that better exploit the unprecedented? multiplicity of data sources in the Biosense program. The proposal describes how many public health threats? can be detected earlier and more accurately through carefully designed methods for combining data. These? threats include natural outbreaks (e.g. new forms of influenza, bacterial outbreaks in water supplies) and? intentional biological attacks (e.g. airborne anthrax, food supply tampering). We have seven specific aims.? First, multivariate Bayesian spatial scanning for regions in which multiple data sources 'agree' on evidence of? such a threat. Second, algorithms that infer the state of a city's health from dozens of pieces of tiny evidence? over many weeks of data. Third, algorithms that search for meaningful similarites in detailed case summaries? that might be currently overlooked. Fourth, underlying data structures to make it tractable for other? algorithms to search over millions of time series in seconds. Fifth, methods to generate a thousand? sufficiently realistic synthetic datasets for algorithm testing. Sixth, collaboration with six external? biosurveillance enterprises (identified in the proposal) for real-world evaluation of and improvements to new? algorithms, and seventh, deployment of the new algorithms within BioSense. These will be achieved using a? combination of new algorithmic approaches, recent developments in probabilistic reasoning systems and? recent accelerations of spatial scan. Our research group has experience in basic research and in systems? deployment in these three areas. We will also use domain experts from whom we will elicit the probabilistic? knowledge for some of the algorithms. All algorithms will be published, implemented, evaluated, delivered to? BioSense and also distributed freely for general use in Public Health surveillance.? This research aids Public Health by developing better ways for computers to combine the wide variety of? data sources in CDC's BioSense program. We will discover the extent to which smart algorithms that? continuously search through millions of potential hidden threats can efficiently identify times, places and atrisk? populations for which multiple independent signals indicate there is evidence of a threat.?
| Hoyt D'Anna, Laura; Nguyen, Hannah-Hanh D; Reynolds, Grace L et al. (2012) The Relationship between Sexual Minority Verbal Harassment And Utilization of Health Services: Results from Countywide Risk Assessment Survey (CRAS) 2004. J Gay Lesbian Soc Serv 24:119-139 |
