A Bayesian system to detect and characterize overlapping outbreaks.

Aronis JM, Millett NE, Wagner MW, Tsui F, Ye Y, Ferraro JP, Haug PJ, Gesteland PH, Cooper GF. A Bayesian system to detect and characterize overlapping outbreaks. Journal of Biomedical Informatics 2017 Sep;73:171-181. doi: 10.1016/j.jbi.2017.08.003. Epub 2017 Aug 7. PMID: 28797710 PMC5604259

Outbreaks of infectious diseases such as influenza are a significant threat to human health. Because there
are different strains of influenza which can cause independent outbreaks, and influenza can affect demographic
groups at different rates and times, there is a need to recognize and characterize multiple outbreaks
of influenza. This paper describes a Bayesian system that uses data from emergency
department patient care reports to create epidemiological models of overlapping outbreaks of influenza.
Clinical findings are extracted from patient care reports using natural language processing. These findings
are analyzed by a case detection system to create disease likelihoods that are passed to a multiple outbreak
detection system. We evaluated the system using real and simulated outbreaks. The results show
that this approach can recognize and characterize overlapping outbreaks of influenza. We describe several
extensions that appear promising.

Publication Year: 
2017
Faculty Author: 
Publication Credits: 
1. Aronis JM, Millett NE, Wagner MW, Tsui F, Ye Y, Ferraro JP, Haug PJ, Gesteland PH, Cooper GF.
Publication Download: 
AttachmentSize
PDF icon John Aronis.pdf632.55 KB
^