Human Digital Twins in Rehabilitation: A Case Study on Exoskeleton and Serious-Game-Based Stroke Rehabilitation Using the ETHICA Methodology

Abstract

Human Digital Twins (HDTs) hold significant potential to transform physical rehabilitation by monitoring patient conditions and personalizing therapeutic interventions. However, practical applications of HDTs in stroke rehabilitation remain limited. This paper presents the design and implementation of an HDT system for upper-limb stroke rehabilitation using exoskeletons and serious games, following the ETHICA methodology. Our system demonstrates how HDTs can enable real-time adjustments to therapy difficulty and exoskeleton assistance based on patient conditions, enhance collaboration between medical and non-medical stakeholders through data visualizations and decision-support mechanisms, and boost patient engagement through personalized feedback. Further, we developed a motion-based muscle fatigue estimation algorithm, predicting muscle fatigue on a continuous scale from 0 to 100% based on movement speed variations, and a compensatory movement detection model, trained with 1590 data samples, which detects unnatural supportive movements with 96% accuracy. Finally, we highlight key implications for the field, including 1) the need for interdisciplinary collaboration to address human factors and sensor technology limitations; 2) the importance of aligning HDT components to avoid incompatibilities; 3) the value of user-centered design for increasing HDT usability and acceptance, and 4) the potential of HDT embodiments for enhancing user engagement and rehabilitation outcomes. Together, these insights provide a roadmap for advancing HDT research and its application in physical rehabilitation.

Keywords

• Avatars
• decision support systems
• digital human modeling
• digital twins
• ETHICA
• exoskeletons