PREDICTING OUTBREAKS AND DISEASE SPREAD USING AI MODELING

• Rahmatilla Amirqulov

  Tashkent State Medical University, Tashkent, Uzbekistan

  Author

• Akbarshoh Abdusalomov

  Tashkent State Medical University, Tashkent, Uzbekistan

  Author

• Qodirbek Isoqov

  Tashkent State Medical University, Tashkent, Uzbekistan

  Author

• Abdullo Ganiboyev

  Tashkent State Medical University, Tashkent, Uzbekistan

  Author

• Mirabbos Jafaraliyev

  Tashkent State Medical University, Tashkent, Uzbekistan

  Author

Accurate prediction of infectious disease outbreaks is an essential component of global health security and epidemic preparedness. The rapid proliferation of digital health data, advances in computational power, and the evolution of artificial intelligence (AI) methods have transformed the landscape of epidemiological forecasting. This article examines contemporary AI-based approaches for predicting outbreaks and modeling disease spread, focusing on machine learning, deep learning, and hybrid mechanistic-AI frameworks. A systematic discussion of data sources, methodological principles, evaluation metrics, and real-world applications is provided. Special emphasis is placed on the integration of compartmental epidemiological models with deep neural architectures, the role of real-time mobility data, and the importance of interpretability and ethical considerations. Results from published applications across influenza, COVID-19, dengue, and emerging zoonotic diseases demonstrate that AI models consistently outperform classical statistical models under conditions of high-dimensional and non-linear data. However, limitations persist regarding data quality, bias propagation, model transparency, and generalizability across geographical contexts. This review concludes by outlining future research directions, including multimodal data fusion, human-AI collaborative decision systems, and privacy-preserving federated modeling frameworks.

• pdf

This work is licensed under a Creative Commons Attribution 4.0 International License.