Organizer: Dr. Hanadi H. Alzubadi, Associate Professor of Applied Mathematics, Department of Mathematics, Umm Al-Qura University, Saudi Arabia
[hhzubadi@uqu.edu.sa and ORCID https://orcid.org/0000-0002-0803-4868 ]
This Mini symposium brings together researchers working at the interface of applied mathematics, artificial intelligence, and biomedical and health sciences, with a particular focus on fractional-order and memory- dependent mathematical models. Classical integer-order models often fail to capture the non-Markovian, history-dependent dynamics observed in many biological and physiological processes; fractional-order formulations, combined with modern AI techniques such as physics-informed neural networks (PINNs) and reinforcement learning, offer a more faithful and predictive framework for these systems.
The symposium will centre on three connected themes: (1) fractional differential equations and dynamical systems for modelling disease progression and physiological processes; (2) AI-enhanced and hybrid computational methods, including PINNs, machine learning, and reinforcement learning, for parameter estimation, prediction, and decision support; and (3) applications to chronic and complex diseases, including liver disease and cancer, as well as large-scale human-mobility problems.
This relates directly to ICNAAM’s core themes of numerical analysis and applied mathematics, extending them into computational medicine and health sciences.
Format and Session Structure
The symposium is proposed as one to two sessions of approximately 90 minutes each, comprising 4 to 6 talks of 20-25 minutes (including questions), with a short discussion period at the end of the final session to identify collaboration opportunities.
Topics
- Fractional differential equations and dynamical systems in mathematical biology
- Physics-informed neural networks (PINNs) for biomedical and physiological modeling
- Reinforcement learning and AI-driven decision support in health sciences
- Microbiome-immune interaction modeling
- Computational and digital health, multi-omics integration
- Disease prediction and modeling of chronic diseases, including liver disease and cancer
- Data-driven modeling of large-scale human dynamics (e.g., pilgrim crowd movement)