Artificial Intelligence for Network Physiology

Network Physiology is an emerging interdisciplinary field dedicated to uncovering the complexity of physiological interactions across diverse organ systems in health and disease. Submissions to this Research Topic should be framed within the context of Network Physiology.

The human body is a supernetwork of networks, operating simultaneously at multiple spatial and temporal scales - from gene regulatory networks and metabolic pathways to neural and cardiovascular dynamics, all the way to behavioral and social interactions. The emerging discipline of Network Physiology provides a powerful framework for understanding these interdependent systems as they dynamically coordinate to maintain health and respond to disease. To move from mapping to modeling and intervention, we now face a pivotal question: How can we use principles of Artificial Intelligence systems for analysis and understanding the human body?

This Research Topic on "Artificial Intelligence in Network Physiology" aims to unify the latest methodological developments in AI with the multifaceted complexity of physiological networks. We seek contributions that combine advanced AI algorithms - including all possible Machine Learning Algorithms, Deep Neural Networks, Graph Neural Networks (GNNs), Transformer-based models, generative networks, and hybrid architectures - with applications to physiological, clinical, omic, and neuroimaging data. We particularly encourage work that integrates multiple modalities, such as transcriptomics, proteomics, EHRs, imaging, and wearable sensor data. The challenge is not merely to classify diseases or predict outcomes, but to understand and simulate the body's adaptive mechanisms, resilience, and breakdowns. We envision the organs as intelligent agents that processes information, learns from experiences, updates internal models, and generates coordinated responses across systems. This conceptualization opens new possibilities for diagnostics, personalized interventions, and adaptive digital twins in medicine.

We invite original research articles, technical reviews, and theoretical contributions on topics including but not limited to:
- Data analysis of different physiological data
- Modelling of complex physiological networks
- Multimodal physiological and omics data analysis using ML and AI
- Graph and hypergraph-based models and analysis of physiological networks
- AI methods for integration of EHR, imaging, and omic data
- Generative models (e.g., GANs) for simulating physiological or imaging data
- Applications of Large Language Models and GraphRAG for biomedical record mining
- AI-based discovery of network biomarkers and disease mechanisms - Explainable AI and interpretable neural networks in clinical contexts
- Neuromorphic architectures inspired by neuron-glia interactions
- Digital twins and predictive models of patient-specific physiology
- Dynamic models of resilience, adaptation, and systemic failure in the body
- Conceptual frameworks treating the human body or any it's organs as an AI system
- Graph neural networks 

This Research Topic offers a platform for researchers working at the intersection of clinical and physiological data science, network science, AI, systems biology, and clinical medicine. Our goal is to foster a multidisciplinary dialogue that accelerates both fundamental discoveries and translational applications in healthcare.