<![CDATA[The rapid emergence of global pandemics necessitates accurate and adaptive predictive systems to support public health decision-making. This study aims to systematically review Artificial Intelligence techniques for predicting pandemic diseases and to evaluate the methodological quality and potential bias of existing empirical research. The research employed a Systematic Literature Review approach guided by PRISMA, with database searches conducted in Scopus, Web of Science, ScienceDirect, and Google Scholar. The selection process yielded ten empirical quantitative and qualitative studies, which were assessed using the Joanna Briggs Institute critical appraisal criteria to evaluate methodological rigor and risk of bias. The findings indicate that machine learning, deep learning, and transformer-based architectures achieve high predictive accuracy in forecasting infection probability, disease severity, and epidemic trends. Most studies demonstrated robust validation strategies, including cross-validation and clearly reported performance metrics. Nevertheless, recurring limitations such as data bias, limited population generalizability, and temporal bias remain significant methodological challenges in AI-based pandemic prediction research. Overall, Artificial Intelligence techniques demonstrate substantial potential in strengthening global pandemic preparedness and enhancing evidence-based public health responses.]]>
Copyrights © 2026
