Automatic Detection of Compensation during Robotic Stroke Rehabilitation Therapy

December 21, 2017

Ying Xuan ZhiMichelle LukasikMichael H. LiElham DolatabadiRosalie WangBabak Taati

Early Access Note:
Early Access articles are new content made available in advance of the final electronic or print versions and result from IEEE’s Preprint or Rapid Post processes. Preprint articles are peer-reviewed but not fully edited. Rapid Post articles are peer-reviewed and edited but not paginated. Both these types of Early Access articles are fully citable from the moment they appear in IEEE Xplore.


Automatic Detection of Compensation during Robotic Stroke Rehabilitation Therapy

Robotic stroke rehabilitation therapy can greatly increase the efficiency of therapy delivery. However, when left unsupervised, users often compensate for limitations in affected muscles and joints by recruiting unaffected muscles and joints, leading to undesirable rehabilitation outcomes. This study aims to develop a computer vision system that augments robotic stroke rehabilitation therapy by automatically detecting such compensatory motions. Nine stroke survivors and ten healthy adults participated in this study. All participants completed scripted motions using a table-top rehabilitation robot. The healthy participants also simulated three types of compensatory motions. The 3-D trajectories of upper body joint positions tracked over time were used for multiclass classification of postures. A Support Vector Machine (SVM) classifier detected lean-forward compensation from healthy participants with excellent accuracy (AUC=0.98, F1=0.82), followed by trunk-rotation compensation (AUC=0.77, F1=0.57). Shoulder-elevation compensation was not well detected (AUC=0.66, F1=0.07). A Recurrent Neural Network classifier (RNN), which encodes the temporal dependency of video frames, obtained similar results. In contrast, F1- scores in stroke survivors were low for all three compensations while using RNN: lean-forward compensation (AUC =0.77, F1=0.17), trunk-rotation compensation (AUC =0.81, F1=0.27), shoulder-elevation compensation (AUC =0.27, F1=0.07). The result was similar while using SVM. To improve detection accuracy for stroke survivors, future work should focus on predefining the range of motion, direct camera placement, delivering exercise intensity tantamount to that of real stroke therapies, adjusting seat height, and recording full therapy sessions.



New Here? Sign Up

Looking for increased exposure in the field of biomedical engineering? EMBS offers journals, conferences and a community for biomedical engineers. Membership includes PULSE Magazine.