Scholarlink

<p>A chronic and progressive neurological disorder, Parkinson’s disease (PD) has a significant influence on patients and their caregivers. Motor symptoms such as postural instability, tremors, and gait dysfunction lead to increased dependency, high caregiver vigilance, and chronic psychological distress in terms of stress, anxiety, and reduced quality of life. Caregivers of patients with PD experience chronic emotional and cognitive distress due to the uncertainty and unpredictability of motor symptoms in daily life, which are not effectively managed by traditional episodic clinical evaluations. To address this gap, we propose a multimodal gait analysis and feedback system that objectively evaluates motor dysfunction and provides remote supervision capabilities that may potentially support caregiver monitoring and reduce the need for constant physical vigilance. The system combines wearable sensors IMUs and flex sensors with a vision-based pose estimation algorithm to continuously monitor tremors and gait dysfunction in a home setting. When deviation exceeds clinically defined thresholds, real-time haptic, visual, and auditory feedback is provided, and wireless data synchronization enables remote monitoring by caregivers and clinicians. In a pilot trial conducted on six patients with PD (Hoehn and Yahr stages 2–3) and one healthy control, the gait classification system achieved a mean accuracy of 88.0% across PD participants and an average feedback response time of approximately 210&#xa0;ms. The alignment of sensor-derived outputs with standardised clinical scales (MDS-UPDRS Part III) supports the clinical interpretability of this system in a home monitoring context. This sensor-integrated monitoring platform is designed to reduce caregiver monitoring burden and may, in future studies with formal caregiver outcome measures, demonstrate benefit to caregiver mental health and quality of life.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Parkinson’s disease focused multimodal wearable vision based gait monitoring system with real time feedback to support mobility and caregiver well-being

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月9日

查看全文
  • Anusha M. U.,
  • Uma Rani K.,
  • Puneeth N.,
  • Kishor M.,
  • Nemichandra S.C.,
  • Deepak Dharrao,
  • Anupkumar M. Bongale

摘要

A chronic and progressive neurological disorder, Parkinson’s disease (PD) has a significant influence on patients and their caregivers. Motor symptoms such as postural instability, tremors, and gait dysfunction lead to increased dependency, high caregiver vigilance, and chronic psychological distress in terms of stress, anxiety, and reduced quality of life. Caregivers of patients with PD experience chronic emotional and cognitive distress due to the uncertainty and unpredictability of motor symptoms in daily life, which are not effectively managed by traditional episodic clinical evaluations. To address this gap, we propose a multimodal gait analysis and feedback system that objectively evaluates motor dysfunction and provides remote supervision capabilities that may potentially support caregiver monitoring and reduce the need for constant physical vigilance. The system combines wearable sensors IMUs and flex sensors with a vision-based pose estimation algorithm to continuously monitor tremors and gait dysfunction in a home setting. When deviation exceeds clinically defined thresholds, real-time haptic, visual, and auditory feedback is provided, and wireless data synchronization enables remote monitoring by caregivers and clinicians. In a pilot trial conducted on six patients with PD (Hoehn and Yahr stages 2–3) and one healthy control, the gait classification system achieved a mean accuracy of 88.0% across PD participants and an average feedback response time of approximately 210 ms. The alignment of sensor-derived outputs with standardised clinical scales (MDS-UPDRS Part III) supports the clinical interpretability of this system in a home monitoring context. This sensor-integrated monitoring platform is designed to reduce caregiver monitoring burden and may, in future studies with formal caregiver outcome measures, demonstrate benefit to caregiver mental health and quality of life.