Laser-light cueing shoes with integrated foot pressure and inertial sensing for investigating the impact of visual cueing on gait characteristics in Parkinson's disease individuals.

Gait disorders are a fundamental challenge in Parkinson's disease (PD). The use of laser-light visual cues emitted from shoes has demonstrated effective in improving freezing of gait within less restrictive environments. However, the effectiveness of shoes-based laser-light cueing may vary among individuals with PD who have different types of impairments. We introduced an innovative laser-light visual shoes system capable of producing alternating visual cues for the left and right feet through one-side cueing at a time, while simultaneously recording foot inertial data and foot pressures. The effects of this visual cueing system on gait patterns were assessed in individuals with PD, both those with well-gait and those with worse-gait. Our device successfully quantified gait characteristics, including the asymmetry in the center of pressure trajectory, in individuals with PD. Furthermore, visual cueing prolonged stride times and increased the percentage of stance phase, while concurrently reducing stride length in PD individuals with well-gait. Conversely, in PD individuals with worse-gait, visual cueing resulted in a decreased freeze index and a reduction in the proportion of intervals prone to freezing episodes. The effects of visual cueing varied between PD individuals with well-gait and those with worse-gait. Visual cueing slowed down gait in the well-gait group while it appeared to mitigate freezing episodes in worse-gait group. Future researches, including enhancements to extend the projection distance of visual cues and clinical assessments conducted in real-world settings, will help establish the clinical utility of our proposed visual cueing system.

Laser-light Visual Cueing Shoes with Foot Pressures and Inertial Sensing for Individuals with Parkinson's Disease.

Gait disorder is a core problem in individuals with Parkinson's disease (PD), including bradykinesia, shuffling steps, festinating gait, and freeze of gait (FOG). Laser-light visual cueing has been demonstrated to be efficient in the mediation of gaits and the reduction in number of FOG episodes. However, previous approaches commonly adopted independent controls of visual cueing on left and right sides which was prone to produce two cues while individual was not in normal walking. In this study, we developed laser-light visual shoes which produced interlaced visual cues for left and right feet in a manner of one-side cueing at a time, solving the aforementioned problem. With parallel measurement of foot inertial data and foot pressures in each shoe, our results showed that the proposed visual cueing made PD individuals in the on-medication condition walk with a longer stance and swing times, that is, they walked more carefully and stable. The proposed approach can also be used to study kinematic and kinetic characteristics of gaits in the off-medication condition to clarify the mediation of visual cueing on motor control of PD individuals.Clinical Relevance- This demonstrates the effect of laser-light visual cueing on gaits in individuals with Parkinson's disease.

Deep Neural Network for the Detections of Fall and Physical Activities Using Foot Pressures and Inertial Sensing.

Fall detection and physical activity (PA) classification are important health maintenance issues for the elderly and people with mobility dysfunctions. The literature review showed that most studies concerning fall detection and PA classification addressed these issues individually, and many were based on inertial sensing from the trunk and upper extremities. While shoes are common footwear in daily off-bed activities, most of the aforementioned studies did not focus much on shoe-based measurements. In this paper, we propose a novel footwear approach to detect falls and classify various types of PAs based on a convolutional neural network and recurrent neural network hybrid. The footwear-based detections using deep-learning technology were demonstrated to be efficient based on the data collected from 32 participants, each performing simulated falls and various types of PAs: fall detection with inertial measures had a higher F1-score than detection using foot pressures; the detections of dynamic PAs (jump, jog, walks) had higher F1-scores while using inertial measures, whereas the detections of static PAs (sit, stand) had higher F1-scores while using foot pressures; the combination of foot pressures and inertial measures was most efficient in detecting fall, static, and dynamic PAs.