Unveiling systemic complexity: The role of artificial intelligence in integrative athlete monitoring

Dear Editor-in-ChiefWe are pleased to submit our manuscript, "Unveiling Systemic Complexity: The Role of Artificial Intelligence in Integrative Athlete Monitoring," for peer review and potential publication as a Letter in Exercise & Organ Crosstalk. The current paradigm in athlete monitoring, while rich in data from wearables and physiological assays, often struggles with a fundamental challenge: synthesizing disparate data streams into a coherent, holistic model of the athlete's state. While systematic reviews highlight the potential of AI for multivariate injury risk assessment (Claudino et al., 2019), and recent studies demonstrate success in forecasting complex, temporal phenomena like sleep and performance (Mateus et al., 2024), a generalized AI framework for modeling the underlying cross-talk between physiological systems is still lacking. Traditional statistical methods, and even many current AI applications, remain inadequate for fully capturing the non-linear, dynamic, and highly individualized nature of inter-organ communication and systemic response to exercise stress.Our manuscript directly addresses this challenge by proposing a novel framework that leverages the power of artificial intelligence (AI) and machine learning (ML). We argue that techniques such as recurrent neural networks (RNNs) and graph neural networks (GNNs) are uniquely suited to model the very "cross-talk" that is the focus of your journal. These models can integrate data from the cardiovascular, musculoskeletal, endocrine, and nervous systems to identify complex, latent patterns that predict performance outcomes, fatigue, and injury risk far more accurately than univariate or linear multivariate models.This work aligns perfectly with the scope of Exercise & Organ Cross Talk, as it moves beyond viewing physiological systems in isolation.We provide a perspective on how AI can act as the essential computational tool to finally quantify and model the deep, systemic interactions that define an athlete's adaptation to training. We believe this perspective will be of significant interest to your readership, stimulating new research at the intersection of computational biology, exercise physiology, and sports medicine.