Physio Galenus: a modular decision support platform for AI-supported physical rehabilitation

This paper presents Physio Galenus, a system that supports therapists in delivering adaptive physical rehabilitation, particularly for neurological conditions such as stroke. The system integrates a web-based therapist application with a backend server that manages patient execution data and interfaces with heterogeneous patient-facing rehabilitation applications. A core component of the platform is a decision support system (DSS) based on fuzzy logic, enabling automatic adjustment of rehabilitation routines. The DSS incorporates an Explainable Artificial Intelligence (XAI) module that provides human-interpretable justifications for each recommendation. The architecture is decoupled from patient applications and supports integration with immersive technologies such as augmented and virtual reality systems, as well as other sensor data. Physio Galenus has served as the foundation for multiple research lines in AI applied to rehabilitation and is released as open-source software to facilitate reproducibility, extension, and adoption in both academic and clinical contexts.