Scholarlink

<p>VisionMD-Gait enables clinical-grade gait assessment using a single frontal-view smartphone video. This open-source platform integrates state-of-the-art monocular video analysis and 3D pose estimation to compute objective gait parameters without specialized hardware, technical expertise, or sharing data with cloud-based services. We validated VisionMD-Gait against a research-grade wearable system in 24 healthy adults and 10 individuals with vestibular dizziness. Video-derived measures showed strong agreement with wearable sensors across gait speed, cadence, step duration and other clinically relevant gait measurements, with mean absolute errors under 10%. Clinical comparisons revealed significant gait alterations in patients with dizziness, despite no clinically overt gait impairments. VisionMD-Gait’s ability to process data locally, preserving patient privacy, and function in standard clinical spaces underscores its scalability and transformative potential for gait screening, fall risk assessment, and monitoring. VisionMD-Gait represents a step towards the democratization of quantitative gait analysis for clinicians and researchers seeking accessible, cost-effective, mobile health solutions.</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

VisionMD-Gait: scalable clinical gait assessment from smartphone videos

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月7日

查看全文
  • Shuyu Liu,
  • Alvin Wong,
  • Si Chen,
  • Patrick J. Antonelli,
  • Diego L. Guarín

摘要

VisionMD-Gait enables clinical-grade gait assessment using a single frontal-view smartphone video. This open-source platform integrates state-of-the-art monocular video analysis and 3D pose estimation to compute objective gait parameters without specialized hardware, technical expertise, or sharing data with cloud-based services. We validated VisionMD-Gait against a research-grade wearable system in 24 healthy adults and 10 individuals with vestibular dizziness. Video-derived measures showed strong agreement with wearable sensors across gait speed, cadence, step duration and other clinically relevant gait measurements, with mean absolute errors under 10%. Clinical comparisons revealed significant gait alterations in patients with dizziness, despite no clinically overt gait impairments. VisionMD-Gait’s ability to process data locally, preserving patient privacy, and function in standard clinical spaces underscores its scalability and transformative potential for gait screening, fall risk assessment, and monitoring. VisionMD-Gait represents a step towards the democratization of quantitative gait analysis for clinicians and researchers seeking accessible, cost-effective, mobile health solutions.