Multi-Source Data Fusion in Pandemic Early Warning
Year: 2025
Type: article
Abstract: This position paper makes the case for an integrated, multi-source approach to pandemic early warning, emphasizing that early detection is key to mitigating the spread of emerging infectious diseases. By synthesizing evidence from traditional epidemiological surveillance and modern data streams—such as environmental sensors, digital media, healthcare records, genomic sequencing, and wearable device data—the publication argues that fusing these diverse indicators can reveal subtle signals of outbreaks long before they escalate. Drawing on case studies from COVID-19, H1N1, Ebola, and other health crises, the paper reviews a range of analytical methodologies including time-series analysis, machine learning fusion models, network analysis, and natural language processing. It examines both the opportunities and challenges—such as data interoperability, noise reduction, and privacy concerns—associated with integrating disparate data sources. Ultimately, the work offers a forward-looking roadmap for developing robust AI-driven biosurveillance systems that not only enhance public health response capabilities but also strengthen national biodefense by providing actionable, early insights into emerging pandemic threats.
Author: Zaharnytskyi, Dmytro
Language: English
Subfield: Epidemiology
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W6912040524
FWCI:
Cites:
Cited by:
Related to: