Digital epidemiology: Utilizing big data for public health surveillance and disease outbreak prediction

Digital epidemiology represents a transformative approach to public health surveillance and disease outbreak prediction by leveraging big data from diverse digital sources, including social media, search engine queries, wearable devices, mobile health applications, environmental sensors, and electronic health records. Unlike traditional epidemiological methods that rely primarily on structured clinical or administrative datasets, digital epidemiology uses real-time, high-volume, and often unstructured data streams to monitor population health dynamics and detect emerging threats with improved temporal and spatial resolution. This study was conducted as a structured literature review guided by PRISMA principles. A comprehensive search of PubMed, Scopus, Web of Science, and IEEE Xplore identified studies published between 1 January 2014 and 1 January 2026. The review synthesizes evidence on methodological foundations, analytical techniques such as machine learning and natural language processing, and applications in outbreak detection, syndromic surveillance, behavioral risk monitoring, and health system responsiveness. Included studies showed that digital signals can improve forecas