A Data-Driven Approach to Food Safety Surveillance and Response
N.P. Greis and M.L. Nogueira
University of North Carolina at Chapel Hill, Chapel Hill, NC, United States
INTRODUCTION
Maintaining a safe and secure food supply is critical to the well-being of millions around the world. An increasingly global food chain—in which products are sourced from locales far from the end consumer—has increased the potential for contamination. These pressures have only increased the sense of urgency in addressing gaps in the food safety system. In particular, early detection and rapid response are challenges that must be met to minimize the impact of a contamination event—whether due to unintentional failure of the food chain or due to an intentional terrorist act. This chapter explores the potential of data-driven informatics tools to provide situational awareness and decision-making intelligence for an intrinsically complex and dynamic process—the detection of and response to a foodborne illness outbreak. A data-driven approach is introduced that builds situational awareness by coalescing real-time data fusion of both traditional and nontraditional sources, analytics based on tools of data science, visualization using a Common Operating Picture (COP), and real-time collaboration across stakeholders of the system to reduce the latency in detecting an emerging contamination event. By reducing the latency of detection, responses such as medical alerts and product recalls can be accelerated, thereby saving lives and cost. These principles of situational awareness were used to develop a prototype software tool for the State of North Carolina, the North Carolina Foodborne Events Data Analysis Tool or NCFEDA. Latencies reductions in surveillance and response are illustrated using a typical example—a cluster of unspecified illness cases reported with symptoms of gastrointestinal distress that may (or may not) indicate a possible foodborne disease outbreak.
Food Protection and Security. DOI: http://dx.doi.org/10.1016/B978-1-78242-251-8.00005-9
© 2017 Elsevier Ltd. All rights reserved.
