文献速递神经康复

机器学习改进卒中后上肢功能使用的加速度计测量:优于计数阈值法

Improving Accelerometry-Based Measurement of Functional Use of the Upper Extremity After Stroke: Machine Learning Versus Counts Threshold Method.
PubMed 文献 · Neurorehabil Neural Repair · 2020-11-05

该研究让健康对照和卒中患者在模拟社区环境中完成非结构化任务,同步记录腕部加速度计和视频,由人工标注视频作为功能/非功能活动的真实基准。结果显示计数比值与真实基准无显著相关且误差大(r=0.48,P=.16,平均误差52.7%),而最佳个体内机器学习算法在卒中患者患肢的准确率达92.6%,与真实基准相关r=0.99(P<.001,平均误差3.9%)。

要点

  • 计数比值法因患肢非功能运动多,与真实功能活动无显著相关且误差大。
  • 最佳个体内机器学习算法在卒中患者患肢准确率达92.6%,相关r=0.99。
  • 最佳跨个体模型准确率74.2%,相关r=0.81,平均误差5.2%。

核心结论

  • 在本样本中,计数比值不能准确反映功能活动,机器学习算法更准确。

研究设计与样本

  • 健康对照和卒中患者在模拟社区环境中完成非结构化任务,测试时长26±8分钟,同步记录加速度计和视频。
  • 人工标注视频每帧为功能或非功能活动作为真实基准,并开发多种机器学习算法区分加速度计数据中的功能与非功能活动。
  • 计算计数比值,即用阈值方案计算患肢活动时长并以较少受累肢体归一化。

主要发现

  • 计数比值与真实基准无显著相关(r=0.48,P=.16),平均误差52.7%,因患肢非功能运动水平高。
  • 计数不随功能运动增加而增加。
  • 最佳个体内机器学习算法在卒中患者患肢准确率92.6%,与真实基准相关r=0.99(P<.001),平均误差3.9%。
  • 最佳跨个体模型准确率74.2%,与真实基准相关r=0.81(P=.005),平均误差5.2%。

临床怎么用

  • 计数比值法不宜单独用于准确评估卒中后上肢功能使用。
  • 机器学习算法可提高加速度计检测功能活动的准确性,未来应开发临床工具。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: Wrist-worn accelerometry provides objective monitoring of upper-extremity functional use, such as reaching tasks, but also detects nonfunctional movements, leading to ambiguity in monitoring results. OBJECTIVE: Compare machine learning algorithms with standard methods (counts ratio) to improve accuracy in detecting functional activity. METHODS: Healthy controls and individuals with stroke performed unstructured tasks in a simulated community environment (Test duration = 26 ± 8 minutes) while accelerometry and video were synchronously recorded. Human annotators scored each frame of the video as being functional or nonfunctional activity, providing ground truth. Several machine learning algorithms were developed to separate functional from nonfunctional activity in the accelerometer data. We also calculated the counts ratio, which uses a thresholding scheme to calculate the duration of activity in the paretic limb normalized by the less-affected limb. RESULTS: The counts ratio was not significantly correlated with ground truth and had large errors (r = 0.48; P = .16; average error = 52.7%) because of high levels of nonfunctional movement in the paretic limb. Counts did not increase with increased functional movement. The best-performing intrasubject machine learning algorithm had an accuracy of 92.6% in the paretic limb of stroke patients, and the correlation with ground truth was r = 0.99 (P < .001; average error = 3.9%). The best intersubject model had an accuracy of 74.2% and a correlation of r =0.81 (P = .005; average error = 5.2%) with ground truth. CONCLUSIONS: In our sample, the counts ratio did not accurately reflect functional activity. Machine learning algorithms were more accurate, and future work should focus on the development of a clinical tool.

来源:Neurorehabil Neural Repair,查看原文。版权归原作者所有。

引用

  1. Lum PS, Shu L, Bochniewicz EM, et al. Improving Accelerometry-Based Measurement of Functional Use of the Upper Extremity After Stroke: Machine Learning Versus Counts Threshold Method. Neurorehabil Neural Repair. 2020. PMID: 33150830. doi:10.1177/1545968320962483

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。