<![CDATA[Intensifying global mobility, climate variability, and urban density have increased the frequency and complexity of infectious disease outbreaks, prompting the need for more accurate and timely epidemiological surveillance. Big Data analytics has emerged as a transformative approach capable of integrating heterogeneous datasets to detect patterns that traditional surveillance systems often miss. This study aims to examine the effectiveness of predictive modeling techniques leveraging Big Data sources such as social media activity, electronic health records, mobility data, and environmental indicators in forecasting potential infectious disease outbreaks. A mixed-methods analytical design was employed, combining machine learning based predictive modeling with retrospective epidemiological validation using multi-country datasets covering the past ten years. The results show that ensemble learning models, especially random forest and gradient boosting algorithms, significantly outperform conventional statistical models in predicting outbreak onset and trajectory, achieving higher accuracy, sensitivity, and early-warning lead time. The findings demonstrate that Big Data driven predictive models can enhance public health preparedness by providing earlier and more reliable outbreak alerts. The study concludes that integrating Big Data analytics into national and global epidemiological systems is essential for strengthening proactive disease prevention, although ethical governance and data privacy protections must be prioritized.]]>
Copyrights © 2025
