RAPID: Modeling Ebola Spread and Developing Decision Support System Using Big Data Analytics

Florida Atlantic University, Boca Raton FL

Investigators

Abstract

This project aims to help address urgent public health problems (specifically the spread of the Ebola virus) of national and global significance by advancing the state of the art in computer science, big data analytics, data visualization techniques, and decision support systems. Specifically, the effort, developing computational models to predict the spread of Ebola utilizing both 'forward simulation' from a given patient and the propagation of the infection into the community and backwards, aims to trace a number of the verified infections to patient 'zero.' The work utilizes big data analytic techniques, data about underlying personal relationships, health center locations, and the known mechanisms for the spread of the Ebola virus. The project connects directly to the Florida International University (FIU)?s TerraFly system, a web-enabled system designed to aid in the visualization of spatial and remotely sensed data. The system allows users to ?fly? with fine resolution over the surface of the earth to explore various kinds of data (e.g., local information, street maps, aerial photography, satellite imagery, etc.). The Ebola spread patterns are then fed into a Decision Support System (DDS). These inputs also consist of information about social groups or individual persons. Based on spread patterns, the DSS will then calculate probabilities for a social group or a given person to get infected with Ebola. The system will be able to present data mashups to operators responding to hotline calls and field workers encountering patients and deciding about triage. The data will also be presented in report form to responsible government agencies. This time-sensitive project necessitates prompt collection and analysis of the spread of the Ebola virus in order to enable the development of the correct models.