Scholarlink

<p>Physical activity and mobility are critical for healthy aging and predict diverse health outcomes. While wrist-worn accelerometers are widely used to monitor physical activity, estimating gait metrics from wrist data remains challenging. We extend ElderNet, a self-supervised deep-learning model previously validated for walking-bout detection, to estimate gait metrics from wrist accelerometry. Validation involved 819 older adults (Rush-Memory-and-Aging-Project) and 85 individuals with gait impairments (Mobilise-D), from six medical centers. In Mobilise-D, ElderNet achieved an absolute error of 8.82 cm/s and an intra-class correlation of 0.87 for gait speed, outperforming state-of-the-art methods (<i>p</i> &lt; 0.001) and models using a lower-back sensor. ElderNet outperformed (percentage error; <i>p</i> &lt; 0.01) competing approaches in estimating cadence and stride length, and better (<i>p</i> &lt; 0.01) classified mobility disability (AUC = 0.80) than conventional gait or physical activity metrics. These results demonstrate the potential of ElderNet a scalable tool for gait assessment using wrist-worn devices in aging and clinical populations.</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

Continuous assessment of daily-living gait using self-supervised learning of wrist-worn accelerometer data

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月12日

查看全文
  • Yonatan E. Brand,
  • Aron S. Buchman,
  • Felix Kluge,
  • Luca Palmerini,
  • Clemens Becker,
  • Andrea Cereatti,
  • Walter Maetzler,
  • Beatrix Vereijken,
  • Alison J. Yarnall,
  • Lynn Rochester,
  • Silvia Del Din,
  • Arne Mueller,
  • Jeffrey M. Hausdorff,
  • Or Perlman

摘要

Physical activity and mobility are critical for healthy aging and predict diverse health outcomes. While wrist-worn accelerometers are widely used to monitor physical activity, estimating gait metrics from wrist data remains challenging. We extend ElderNet, a self-supervised deep-learning model previously validated for walking-bout detection, to estimate gait metrics from wrist accelerometry. Validation involved 819 older adults (Rush-Memory-and-Aging-Project) and 85 individuals with gait impairments (Mobilise-D), from six medical centers. In Mobilise-D, ElderNet achieved an absolute error of 8.82 cm/s and an intra-class correlation of 0.87 for gait speed, outperforming state-of-the-art methods (p < 0.001) and models using a lower-back sensor. ElderNet outperformed (percentage error; p < 0.01) competing approaches in estimating cadence and stride length, and better (p < 0.01) classified mobility disability (AUC = 0.80) than conventional gait or physical activity metrics. These results demonstrate the potential of ElderNet a scalable tool for gait assessment using wrist-worn devices in aging and clinical populations.