Data-Driven Real-Time Surveillance System for Tracking Disease Outbreaks: A Case Study of Lassa Fever Outbreak

Efficient surveillance systems have become a viable tool in the global fight against disease outbreaks, prevention, and management. In most cases, these systems predict changes and transmission patterns of fast-changing disease outbreaks. Data from these surveillance apps can also be used for efficient emergency response preparatory logistics, as well as early containment. In this paper, we present a comprehensive GIS-enabled surveillance system for Lassa Fever outbreaks that is capable of visualizing and identifying epidemiological patterns for these events in real time. These visualizations can be in the form of GIS maps, charts, and other metrics to track certain indicators. Data from these dashboards provides real-time input for the section on machine learning prediction models. These models can predict the possible occurrence of Lassa Fever in the communities and regions under investigation. Public health practitioners and community-based groups can leverage on, and adapt this system to monitor the spread of any quick-onset disease outbreak as wells as prediction of such events.