Automatic Detection and Reduction of Compensation in Stroke Patients During Robotic Rehabilitation

Rehabilitation robots offer promising clinical benefits, however, a critical concern is whether patients can perform exercises correctly without therapist guidance. Patients with stroke, in particular, often resort to compensatory movements without supervision, leading to less-than-optimal outcomes. To address this issue, our work aims to detect and minimize the use of compensation during robotic rehabilitation. Specifically, we developed an artificial neural network (ANN) that uses pressure distribution data to detect compensatory motions. Furthermore, a rehabilitation robot provided real-time force feedback to stroke patients to reduce trunk compensation when necessary. Our experiment involved 8 stroke patients and 12 healthy individuals who completed reaching tasks using an upper limb rehabilitation robot. Results demonstrated the effectiveness of our approach in both offline and online compensation detection. Moreover, we observed a significant reduction in trunk compensation among stroke patients. This study provides a promising solution for unsupervised robotic rehabilitation for stroke patients, paving the way for improved rehabilitation outcomes.