A Rehabilitation Exercise Assessment System for Knee Osteoarthritis

• Main Authors: Po-Chao Chen, 陳柏超
• Other Authors: Chia-Tai Chan
• Format: Others
• Language: en_US
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/15887940352310620483

碩士 === 國立陽明大學 === 醫學工程研究所 === 101 === Since the knee joint bears the heaviest weight of the human body, it is the body part most susceptible to OsteoArthritis (OA). The early rehabilitation stages last for approximately six weeks, during which the patient works with the physical therapist several times each week. The patient is afterwards given instructions for continuing rehabilitation exercise at home. In order to enable the knee OA patients to manage their own rehabilitation progress, this study develops a rehabilitation exercise assessment system for knee OA using three wearable sensors mounted on the chest, thigh and shank of working leg. The system generates 51 features include the calculated angles, spectrum, and means of the acceleration signal to identify the exercise type and determine whether their postures are proper or not. After ten subjects performed three kinds of rehabilitation activities, we get 99.29% accuracy for exercise type classification, and 90.14% accuracy for wrong exercise recognition. Three types of rehabilitation exercise commonly prescribed to knee OA patients are: Short-Arc Exercise (SAE), Straight Leg Raise (SLR), and Quadriceps Strengthening Mini-squats (QSM). The experimental results demonstrate that the proposed system can help the physician to monitor the rehabilitation progress efficiently. Moreover, the system can help patients perform standard rehabilitation movement, making the progress effectively.