Learning to assess the quality of stroke rehabilitation exercises

If we had protocols instead of guidelines then patients would be motivated to continue their exercises because they know a certain result will occur. 

Learning to assess the quality of stroke rehabilitation exercises

Published in:

· Proceeding

IUI '19 Proceedings of the 24th International Conference on Intelligent User Interfaces

Pages 218-228 Marina del Ray, California — March 17 - 20, 2019 ACM New York, NY, USA ©2019 table of contents ISBN: 978-1-4503-6272-6 doi>10.1145/3301275.3302273

Authors: Min Hun Lee Carnegie Mellon University Daniel P. Siewiorek Carnegie Mellon University Asim Smailagic Carnegie Mellon University Alexandre Bernadino Instituto Superior Técnico Sergi Bermúdez i Badia Madeira Interactive Technology Institute

2019 Article   Bibliometrics · Citation Count: 0 · Downloads (cumulative): n/a · Downloads (12 Months): n/a · Downloads (6 Weeks): n/a

 Due to the limited number of therapists, task-oriented exercises are often prescribed for post-stroke survivors as in-home rehabilitation. During in-home rehabilitation, a patient may become unmotivated or confused to comply prescriptions without the feedback of a therapist. To address this challenge, this paper proposes an automated method that can achieve not only qualitative, but also quantitative assessment of stroke rehabilitation exercises. Specifically, we explored a threshold model that utilizes the outputs of binary classifiers to quantify the correctness of a movements into a performance score. We collected movements of 11 healthy subjects and 15 post-stroke survivors using a Kinect sensor and ground truth scores from primary and secondary therapists. The proposed method achieves the following agreement with the primary therapist: 0.8436, 0.8264, and 0.7976 F1-scores on three task-oriented exercises. Experimental results show that our approach performs equally well or better than multi-class classification, regression, or the evaluation of the secondary therapist. Furthermore, we found a strong correlation (R² = 0.95) between the sum of computed exercise scores and the Fugl-Meyer Assessment scores, clinically validated motor impairment index of post-stroke survivors. Our results demonstrate a feasibility of automatically assessing stroke rehabilitation exercises with the decent agreement levels and clinical relevance.