TY - JOUR
T1 - Adaptive cueing strategy for gait modification
T2 - a case study using auditory cues
AU - Wu, Tina L.Y.
AU - Murphy, Anna
AU - Chen, Chao
AU - Kulić, Dana
N1 - Funding Information:
DK was supported by an Australian Research Council Future Fellowship (FT200100761).
Funding Information:
We acknowledge the support of the Natural Sciences and Engineering Research Council of Canada (NSERC), Monash Institute of Medical Engineering (MIME), the Commonwealth Scientific and Industrial Research Organization (CSIRO), and Monash Partners. We also acknowledge the help from Fight Parkinson's and the support from the members of the community.
Publisher Copyright:
Copyright © 2023 Wu, Murphy, Chen and Kulić.
PY - 2023/3/23
Y1 - 2023/3/23
N2 - People with Parkinson's (PwP) experience gait impairments that can be improved through cue training, where visual, auditory, or haptic cues are provided to guide the walker's cadence or step length. There are two types of cueing strategies: open and closed-loop. Closed-loop cueing may be more effective in addressing habituation and cue dependency, but has to date been rarely validated with PwP. In this study, we adapt a human-in-the-loop framework to conduct preliminary analysis with four PwP. The closed-loop framework learns an individualized model of the walker's responsiveness to cues and generates an optimized cue based on the model. In this feasibility study, we determine whether participants in early stages of Parkinson's can respond to the novel cueing framework, and compare the performance of the framework to two alternative cueing strategies (fixed/proportional approaches) in changing the participant's cadence to two target cadences (speed up/slow down). The preliminary results show that the selection of the target cadence has an impact on the participant's gait performance. With the appropriate target, the framework and the fixed approaches perform similarly in slowing the participants' cadence. However, the proposed framework demonstrates better efficiency, explainability, and robustness across participants. Participants also have the highest retention rate in the absence of cues with the proposed framework. Finally, there is no clear benefit of using the proportional approach.
AB - People with Parkinson's (PwP) experience gait impairments that can be improved through cue training, where visual, auditory, or haptic cues are provided to guide the walker's cadence or step length. There are two types of cueing strategies: open and closed-loop. Closed-loop cueing may be more effective in addressing habituation and cue dependency, but has to date been rarely validated with PwP. In this study, we adapt a human-in-the-loop framework to conduct preliminary analysis with four PwP. The closed-loop framework learns an individualized model of the walker's responsiveness to cues and generates an optimized cue based on the model. In this feasibility study, we determine whether participants in early stages of Parkinson's can respond to the novel cueing framework, and compare the performance of the framework to two alternative cueing strategies (fixed/proportional approaches) in changing the participant's cadence to two target cadences (speed up/slow down). The preliminary results show that the selection of the target cadence has an impact on the participant's gait performance. With the appropriate target, the framework and the fixed approaches perform similarly in slowing the participants' cadence. However, the proposed framework demonstrates better efficiency, explainability, and robustness across participants. Participants also have the highest retention rate in the absence of cues with the proposed framework. Finally, there is no clear benefit of using the proportional approach.
KW - continuum care
KW - human-in-the-loop
KW - Parkinson's disease
KW - rehabilitation robotics
KW - wearable robotics
UR - http://www.scopus.com/inward/record.url?scp=85153352790&partnerID=8YFLogxK
U2 - 10.3389/fnbot.2023.1127033
DO - 10.3389/fnbot.2023.1127033
M3 - Article
AN - SCOPUS:85153352790
SN - 1662-5218
VL - 17
JO - Frontiers in Neurorobotics
JF - Frontiers in Neurorobotics
M1 - 1127033
ER -