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 pape...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2018-01-01
|
Series: | IEEE Journal of Translational Engineering in Health and Medicine |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8214256/ |
_version_ | 1818411484575694848 |
---|---|
author | Ying Xuan Zhi Michelle Lukasik Michael H. Li Elham Dolatabadi Rosalie H. Wang Babak Taati |
author_facet | Ying Xuan Zhi Michelle Lukasik Michael H. Li Elham Dolatabadi Rosalie H. Wang Babak Taati |
author_sort | Ying Xuan Zhi |
collection | DOAJ |
description | 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 paper 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 (RNN) classifier, 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), and 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. |
first_indexed | 2024-12-14T10:32:09Z |
format | Article |
id | doaj.art-967765e775694d30aad23bbc1f225e44 |
institution | Directory Open Access Journal |
issn | 2168-2372 |
language | English |
last_indexed | 2024-12-14T10:32:09Z |
publishDate | 2018-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Journal of Translational Engineering in Health and Medicine |
spelling | doaj.art-967765e775694d30aad23bbc1f225e442022-12-21T23:06:05ZengIEEEIEEE Journal of Translational Engineering in Health and Medicine2168-23722018-01-0161710.1109/JTEHM.2017.27808368214256Automatic Detection of Compensation During Robotic Stroke Rehabilitation TherapyYing Xuan Zhi0https://orcid.org/0000-0002-3153-0210Michelle Lukasik1Michael H. Li2https://orcid.org/0000-0002-6244-8500Elham Dolatabadi3https://orcid.org/0000-0003-2236-2611Rosalie H. Wang4Babak Taati5https://orcid.org/0000-0001-9763-4293Toronto Rehabilitation Institute—University Health Network, Toronto, ON, CanadaToronto Rehabilitation Institute—University Health Network, Toronto, ON, CanadaToronto Rehabilitation Institute—University Health Network, Toronto, ON, CanadaToronto Rehabilitation Institute—University Health Network, Toronto, ON, CanadaToronto Rehabilitation Institute—University Health Network, Toronto, ON, CanadaToronto Rehabilitation Institute—University Health Network, Toronto, ON, CanadaRobotic 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 paper 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 (RNN) classifier, 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), and 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.https://ieeexplore.ieee.org/document/8214256/Motion compensationposture classificationrehabilitation roboticsstroke rehabilitation |
spellingShingle | Ying Xuan Zhi Michelle Lukasik Michael H. Li Elham Dolatabadi Rosalie H. Wang Babak Taati Automatic Detection of Compensation During Robotic Stroke Rehabilitation Therapy IEEE Journal of Translational Engineering in Health and Medicine Motion compensation posture classification rehabilitation robotics stroke rehabilitation |
title | Automatic Detection of Compensation During Robotic Stroke Rehabilitation Therapy |
title_full | Automatic Detection of Compensation During Robotic Stroke Rehabilitation Therapy |
title_fullStr | Automatic Detection of Compensation During Robotic Stroke Rehabilitation Therapy |
title_full_unstemmed | Automatic Detection of Compensation During Robotic Stroke Rehabilitation Therapy |
title_short | Automatic Detection of Compensation During Robotic Stroke Rehabilitation Therapy |
title_sort | automatic detection of compensation during robotic stroke rehabilitation therapy |
topic | Motion compensation posture classification rehabilitation robotics stroke rehabilitation |
url | https://ieeexplore.ieee.org/document/8214256/ |
work_keys_str_mv | AT yingxuanzhi automaticdetectionofcompensationduringroboticstrokerehabilitationtherapy AT michellelukasik automaticdetectionofcompensationduringroboticstrokerehabilitationtherapy AT michaelhli automaticdetectionofcompensationduringroboticstrokerehabilitationtherapy AT elhamdolatabadi automaticdetectionofcompensationduringroboticstrokerehabilitationtherapy AT rosaliehwang automaticdetectionofcompensationduringroboticstrokerehabilitationtherapy AT babaktaati automaticdetectionofcompensationduringroboticstrokerehabilitationtherapy |