Frontiers in Physiology (Feb 2024)

Adaptive auditory assistance for stride length cadence modification in older adults and people with Parkinson’s

  • Tina L. Y. Wu,
  • Anna Murphy,
  • Chao Chen,
  • Dana Kulić

DOI
https://doi.org/10.3389/fphys.2024.1284236
Journal volume & issue
Vol. 15

Abstract

Read online

Gait rehabilitation using auditory cues can help older adults and people with Parkinson’s improve walking performance. While auditory cues are convenient and can reliably modify gait cadence, it is not clear if auditory cues can reliably modify stride length (SL), another key gait performance metric. Existing algorithms also do not address habituation or fluctuation in motor capability, and have not been evaluated with target populations or under dual-task conditions. In this study, we develop an adaptive auditory cueing framework that aims to modulate SL and cadence. The framework monitors the gait parameters and learns a personalized cue-response model to relate the gait parameters to the input cues. The cue-response model is represented using a multi-output Gaussian Process (MOGP) and is used during optimization to select the cue to provide. The adaptive cueing approach is benchmarked against the fixed approach, where cues are provided at a fixed cadence. The two approaches are tested under single and dual-task conditions with 13 older adults (OA) and 8 people with Parkinson’s (PwP). The results show that more than half of the OA and PwP in the study can change both SL and cadence using auditory cues. The fixed approach is best at changing people’s gait without secondary task, however, the addition of the secondary task significantly degrades effectiveness at changing SL. The adaptive approach can maintain the same level of SL change regardless of the presence of the secondary task. A separate analysis is conducted to identify factors that influence the performance of the adaptive framework. Gait information from the previous time step, along with the previous input cue, can improve its prediction accuracy. More diversity in the initialization data can also improve the GP model. Finally, we did not find a strong correlation between stride length and cadence when the parameters are contingent upon input cues.

Keywords