Automated Evaluation of Upper-Limb Motor Function Impairment Using Fugl-Meyer Assessment

The Fugl-Meyer assessment (FMA) is the most popular instrument for evaluating upper extremity motor function in stroke patients. However, it is a labor-intensive and time-consuming method. This paper proposes a novel automated FMA system to overcome these limitations of the FMA. For automation, we used Kinect v2 and force sensing resistor sensors owing to their convenient installation as compared with body-worn sensors. Based on the linguistic guideline of the FMA, a rule-based binary logic classification algorithm was developed to assign FMA scores using the extracted features obtained from the sensors. The algorithm is appropriate for clinical use, because it is not based on machine learning, which requires additional learning processes with a large amount of clinical data. The proposed system was able to automate 79% of the FMA tests because of optimized sensor selection and the classification algorithm. In clinical trials conducted with nine stroke patients, the proposed system exhibited high scoring accuracy (92%) and time efficiency (85% reduction in clinicians' required time).