Analysis of Detecting Compensation for Robotic Stroke Rehabilitation Therapy using Imbalanced Learning and Outlier Detection

You can see from the first sentence they are laboring under the wrong goal for stroke therapy. The only goal in stroke is 100% recovery for all, get out if you aren't shooting for that goal.  reduce impairments and improve the motor movements. 

THIS IS WHY WE NEED SURVIVORS IN CHARGE. Existing stroke leaders have been doing it all wrong for decades which is why we are so far away from solving stroke.

Analysis of Detecting Compensation for Robotic Stroke Rehabilitation Therapy using Imbalanced Learning and Outlier Detection

Publisher: IEEE

2

Author(s)

Sean Rich U. Uy ; Patricia Angela Abu

View All Authors

---

Abstract

Document Sections

• I.
  Introduction
• II.
  Related Works
• III.
  Dataset
• IV.
  Methodology
• V.
  Results and Analysis

Authors

Figures

References

Keywords

Abstract:

Stroke therapy is essential to reduce impairments and improve the motor movements of stroke survivors, however sessions can be expensive, time consuming, and geographically limited. Robotic stroke therapy seeks to remedy the limitations of traditional stroke therapy, but it is hampered by incorrect movements during the session. Incorrect usage of muscles, called as compensatory movements, can cause problems that can hamper the recovery of the patients.(You mean you don't know that you learn faster by doing incorrect movements and then correcting them? We know that learning from your mistakes is one of the best ways to learn,) Thus, there is a need to develop tools to automatically detect compensatory movements to assist patients doing autonomous therapy sessions. Previous studies on automatic detection using depth sensors did not yield satisfactory results. This study explores class imbalance as a possible reason for the low F1-score results on machine learning classifiers. Different methods to address class imbalance were employed to improve and to analyze the performance of the classifiers. The methods employed allowed the classifiers to sometimes detect compensatory movements however this degraded the performance of detecting the correct movements. Adjusting the decision thresholds of outlier detection algorithms shows this explicitly. Since addressing class imbalance only marginally improves the performance of the classifiers, other possible methods can be explored in conjunction with it. This study shows the possibility of detecting compensations in stroke patients.

Published in: 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

Date of Conference: 19-21 Feb. 2020

Date Added to IEEE Xplore: 16 April 2020

ISBN Information:

DOI: 10.1109/ICAIIC48513.2020.9064992

Publisher: IEEE

Conference Location: Fukuoka, Japan, Japan