Adaptive Neural Rendering for Dynamic Advanced Life Support Team Training: A Continuous Volumetric Framework for Real-time Simulation Scenario Adaptation

Abstract Background: We introduce an adaptive neural rendering framework that advances dynamic Advanced Life Support (ALS) team training by overcoming limitations of static simulations through continuous volumetric implicit neural representations. Aims and Objectives: The system encodes anatomical structures and physiological dynamics as time-variant neural radiance fields, enabling smooth interpolation and deformation of clinical scenarios during resuscitation. Materials and Methods: A differentiable rendering pipeline synthesises photorealistic medical scenes modulated by latent vectors driven by real-time inputs from wearable sensors and team interventions, capturing disease progression and therapeutic effects. To optimise computational efficiency and maintain real-time performance, the framework employs foveated importance sampling aligned with gaze tracking, concentrating rendering resources on clinically relevant regions. Inverse rendering techniques extract key physiological parameters directly from volumetric neural fields, facilitating seamless integration with clinical assessment dashboards and automated debriefing systems. A distributed synchronisation mechanism ensures multiuser scenario coherence, while federated latent space averaging allows personalised adaptations without compromising global consistency. Interoperability is ensured via resolution-adaptive neural textures and projective augmented reality alignment, enabling integration with existing virtual reality (VR) platforms and traditional mannequin-based workflows. Results: Experimental validation demonstrates enhanced training efficacy through dynamic scenario difficulty modulation and realism adjustment driven by live performance metrics, offering a scalable and adaptive solution for next-generation ALS team education. Conclusion: The ANR framework offers a scalable, adaptive, and realistic approach for next-generation ALS education.