New technology could be used to predict outbreaks of dengue fever
The PRedicting Infectious Disease Scalable Model, known as PRISM, establishes relationships between climatic, socio-political, clinical and meteorological data sets in Peru and the Philippines, though the model can be used in any geographical region. The new model is designed to help health officials and other public health planners assess the risk of a future outbreak in a particular area at a given time, News Medical reports.
"By predicting disease outbreaks when no disease is present, PRISM has the potential to save lives by allowing early public health intervention and decreasing the impact of an outbreak," Sheri Lewis, the global disease surveillance program manager at the APL, said, according to News Medical.
PRISM uses Fuzzy Association Rule Mining-known as FARM-to identify relationship between numerous variables in a data set. The relationships between the variables form rules, and after the best set of rules is chosen, a classifier is formed. The classifier is then used to predict future outbreaks of diseases.
"PRISM is designed to help public health leaders make informed decisions, mitigate threats and more effectively protect their populations," Lewis said, News Medical reports. "Ideally, decision-makers want to learn about a disease outbreak before it spreads, and PRISM will provide them with highly accurate information to protect our military forces deployed in at-risk areas."
Though the PRISM was piloted to the study of dengue fever, a mosquito-borne illness, in Peru, APL scientists have expanded the method to predict dengue outbreaks in the Philippines and are working to expand its capabilities to predict other infection diseases. PRISM will also complement other disease surveillance systems, including the Electronic Surveillance System for the Early Notification of Community-based Epidemics-or ESSENCE-and the Suite of Automated Global Electronic bioSurveillance, known as SAGES.