3D Reaching Movements Prediction of Upper-limb Joints Based on Deep Neural Networks

BackgroundThe reaching test is widely adapted in motor function assessment of stroke rehabilitation. To evaluate the motor disorder quantitatively, it is important to measure the differences between reaching movements made by healthy people and patients. Thus a movement prediction model should be firstly established on healthy people as a customized benchmark. MethodsWe designed a simplified kinematic model for human upper limbs in which seven main joints of both the dominant and non-dominant side were extracted. With this model, the reaching movement data was collected from a healthy participant. A deep neural network (DNN) was trained with this dataset. Then, the DNN was utilized for predicting 3D movements of upper limb joints of a healthy participant. ResultsThe prediction trajectories of dominant side were high similar to the trajectories of real movements with the coupling distance around 60 mm, 50 mm, 30 mm, 30 mm, 20mm for hand, elbow, shoulder, 7th cervical vertebra and 8th thoracic vertebra. The result of non-dominant side were less accurate than dominant side but still was with relatively short coupling distance. ConclusionsThe DNN model could achieve the promising accuracy in 3D movements estimation of upper limb. With good capabilities of identifying specific reaching movements in dynamic processing, a customized benchmark established by data-driven methods could be utilized to inform the rehabilitation assessment and training in the future studies.