Scholarlink

<p>Purpose: Visually Guided Reaching (VGR) on the Kinarm robot yields sensitive kinematic biomarkers but requires 40–64 reaches, imposing time and fatigue burdens. We evaluate whether time series foundation models can replace unrecorded trials from an early subset of reaches while preserving agreement with full-session estimates of standard Kinarm parameters. Methods: We analyzed VGR speed signals from 461 stroke and 599 control participants across 4- and 8-target reaching protocols. We withheld all but the first 8 or 16 reaching trials and used ARIMA, MOMENT, and Chronos models, fine-tuned on 70% of participants, to forecast synthetic trials. We recomputed four kinematic features of reaching (reaction time, movement time, posture speed, max speed) on combined recorded plus forecasted trials and compared to full-length references using ICC(2,1). Results: Chronos forecasts increased ICC values for all parameters (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\ge 0.90\)</EquationSource> </InlineEquation>) when combining only 8 recorded trials with forecasted trials, achieving agreement comparable to that obtained using 24–28 recorded reaches (<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\Delta ICC \le 0.07\)</EquationSource> </InlineEquation>). MOMENT yielded intermediate gains, while ARIMA improvements were minimal. Across cohorts and protocols, synthetic trials replaced reaches without significantly compromising feature reliability. Conclusion: Foundation-model forecasting can greatly shorten Kinarm VGR assessment time. For the most impaired stroke survivors, sessions drop from 4–5&#xa0;min to about 1&#xa0;min while maintaining agreement with full-session Kinarm parameter estimates. This forecast-augmented paradigm promises efficient robotic evaluations for assessing motor impairments following stroke.</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

Reducing robotic upper-limb assessment time while maintaining precision: a time series foundation model approach

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月6日

查看全文
  • Faranak Akbarifar,
  • Nooshin Maghsoodi,
  • Sean P. Dukelow,
  • Stephen H. Scott,
  • Parvin Mousavi

摘要

Purpose: Visually Guided Reaching (VGR) on the Kinarm robot yields sensitive kinematic biomarkers but requires 40–64 reaches, imposing time and fatigue burdens. We evaluate whether time series foundation models can replace unrecorded trials from an early subset of reaches while preserving agreement with full-session estimates of standard Kinarm parameters. Methods: We analyzed VGR speed signals from 461 stroke and 599 control participants across 4- and 8-target reaching protocols. We withheld all but the first 8 or 16 reaching trials and used ARIMA, MOMENT, and Chronos models, fine-tuned on 70% of participants, to forecast synthetic trials. We recomputed four kinematic features of reaching (reaction time, movement time, posture speed, max speed) on combined recorded plus forecasted trials and compared to full-length references using ICC(2,1). Results: Chronos forecasts increased ICC values for all parameters ( \(\ge 0.90\) ) when combining only 8 recorded trials with forecasted trials, achieving agreement comparable to that obtained using 24–28 recorded reaches ( \(\Delta ICC \le 0.07\) ). MOMENT yielded intermediate gains, while ARIMA improvements were minimal. Across cohorts and protocols, synthetic trials replaced reaches without significantly compromising feature reliability. Conclusion: Foundation-model forecasting can greatly shorten Kinarm VGR assessment time. For the most impaired stroke survivors, sessions drop from 4–5 min to about 1 min while maintaining agreement with full-session Kinarm parameter estimates. This forecast-augmented paradigm promises efficient robotic evaluations for assessing motor impairments following stroke.