Akademik Veri Yönetim Sistemi
2ND INTERNATIONAL HEALTH SCIENCES CONGRESS IN THE 21ST CENTURY, Aydın, Türkiye, 5 - 07 Kasım 2025, ss.1-13, (Tam Metin Bildiri)
Artificial
intelligence (AI) and machine learning (ML) technologies are increasingly being
applied to influenza virology, providing novel approaches for predicting viral
evolution, host adaptation, and cross-species transmission. This review
examines recent developments in AI-driven modeling and their applications in
monitoring antigenic drift, forecasting genetic variation, and assessing
zoonotic risks associated with influenza viruses. Despite substantial progress,
influenza viruses remain difficult to predict due to high mutation rates,
frequent genome segment reassortment, and subtle molecular adaptations that
challenge traditional surveillance and vaccine design strategies. Recent
advances in computational modeling now allow the integration of large-scale
genomic datasets to identify evolutionary patterns and detect host-adaptive
mutations earlier than conventional laboratory-based methods. The 2024
emergence of highly pathogenic avian influenza (H5N1) in U.S. dairy cattle
highlights the urgent need for predictive analytical tools to enable early
detection and risk assessment. Although challenges such as limited data quality
and interpretability persist, AI-based approaches are establishing new
frameworks for proactive disease management. The incorporation of advanced AI
architectures and multi-omics integration is expected to shape the next
generation of adaptive surveillance systems capable of continuous learning from
genomic, ecological, and host-related information. Embedding these
computational approaches within One Health frameworks could significantly
enhance surveillance, inform vaccine design, and strengthen preparedness
against future zoonotic influenza outbreaks.