Structural models may aid in bioterror threat tracking
The research team used a computer modeling scenario in which Miami was the target of a terrorist anthrax attack. The structural model proved effective in identifying that an anthrax attack was underway and achieved perfect detection when less than 0.03 percent of the population was infected, BMJ.com reports.
"Using a combination of real and simulated data, we have constructed a data set that represents a plausible time series resulting from surveillance of a large scale bioterrorist anthrax attack in Miami," the report said, according to BMJ.com. "We show that these techniques provide a method for predicting the level of the outbreak valid for approximately two weeks, post-alarm."
The model used simulated data of an attack superimposed on a real medical dataset from Miami including patient-level information such as chief complaints and symptoms.
By detecting potential terrorist attacks in the early stages, health officials can act quickly to save lives. Biosurveillance officials can utilize structural models for anomaly detection to help them make informed decisions when responding to crises.
"Structural models provide an effective tool for the analysis of biosurveillance data, in particular for time series with noisy, non-stationary background and missing data," the researchers said, according to BMJ.com.
The study was published in October in the Journal of the American Medical Informatics Association under the title "Structural models used in real-time biosurveillance outbreak detection and outbreak curve isolation from noisy background morbidity levels."