文献速递神经康复儿童康复

多模态参与度估计在儿童机器人辅助步态训练中的应用:整合生理传感与生物力学交互

Multimodal engagement estimation in paediatric robot-assisted gait training: integrating physiological sensing and biomechanical interaction.
PubMed 文献 · J Neuroeng Rehabil · 2026-06-18

本研究针对20名接受Hocoma Lokomat®机器人辅助步态训练的脑性瘫痪儿童,采集心率变异性、面部红外热成像和外骨骼生物力学特征,由临床专家以三分类量表标注参与度,并开发监督多分类机器学习框架进行自动估计。Extra Trees分类器结合多模态特征取得最佳性能,宏平均F1为0.658 ± 0.027。研究证明在复杂临床人群中整合生理与机器人交互数据进行客观参与度建模具有可行性。

要点

  • Extra Trees结合多模态特征估计参与度,宏平均F1为0.658 ± 0.027。
  • 极端参与水平识别较好,误分类多发生在相邻类别尤其中性状态。
  • 外骨骼力矩特征最具影响力,热成像与心率变异性提供互补信息。

核心结论

  • 整合生理传感与机器人交互数据可在脑性瘫痪儿童机器人辅助步态训练中实现客观参与度估计。
  • 多模态机器学习方法在复杂临床人群中具有可行性,有望支持自适应康复系统与个性化人机交互。

研究设计与样本

  • 研究纳入20名接受Hocoma Lokomat®机器人辅助步态训练的脑性瘫痪儿童,跨越多次治疗会话进行监测。
  • 采集心率变异性、面部红外热成像和外骨骼生物力学特征,分割时间窗提取统计、频谱和复杂度特征。
  • 参与度由专家临床医生以三分类量表(未参与、中性、参与)标注,采用监督多分类机器学习框架。
  • 评估多种集成分类器,采用重复分层划分严格分离训练与测试,并使用类别加权学习处理类别不平衡。

主要发现

  • 多模态特征结合Extra Trees分类器表现最佳,宏平均F1为0.658 ± 0.027。
  • 类别分析显示极端参与水平(未参与和参与)性能较高,多数误分类发生在相邻类别之间,尤其涉及中性状态。
  • 特征选择与可解释性分析识别外骨骼力矩特征为最有影响力的预测因子,热成像和心率变异性特征提供互补的自主神经与情绪信息。

临床怎么用

  • 可利用多模态传感在机器人辅助步态训练中连续监测脑性瘫痪儿童参与度,辅助治疗师客观评估。
  • 外骨骼力矩特征可作为参与度估计的核心预测指标,热成像和心率变异性提供补充信息。
  • 研究框架有望支持自适应康复系统,根据参与度实时调整训练参数以实现个性化人机交互。

局限性

  • 研究样本为20名脑性瘫痪儿童,队列规模受后勤、伦理和技术挑战限制。
  • 参与度标注基于单一专家临床医生的三分类主观量表。
  • 中性状态与其他类别的误分类较多,分类性能仍有提升空间。

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: Patients' engagement plays a crucial role in the effectiveness of robot-assisted gait training (RAGT), particularly in paediatric neurorehabilitation, where motivation and active participation strongly influence functional outcomes. Despite its clinical relevance, engagement assessment is still largely based on subjective observation, limiting objectivity and scalability. Objective modelling of engagement in children with cerebral palsy remains underexplored, especially when relying on physiological signals acquired during therapy, due to logistical, ethical, and technological challenges that constrain multimodal data collection and cohort sizes. This study proposes a novel multimodal framework to automatically estimate engagement in a paediatric cerebral palsy population undergoing RAGT, capturing clinically relevant variability across patients. METHODS: A cohort of 20 paediatric patients with cerebral palsy undergoing RAGT with the Hocoma Lokomat® system was monitored across multiple therapy sessions. Heart rate variability (HRV), facial infrared thermography (IRT), and exoskeleton-derived biomechanical features were acquired to capture complementary physiological and behavioural responses related to engagement. Signals were segmented into time windows and processed to extract statistical, spectral, and complexity features. Engagement was annotated by an expert clinician using a three-class scale (not engaged, neutral, engaged). A supervised multiclass machine-learning framework was then developed to estimate engagement from multimodal data, evaluating several ensemble-based classifiers under strict training-testing separation with repeated stratified splits and class-weighted learning to tackle class imbalance. RESULTS: The combination of multimodal features with the Extra Trees classifier achieved the best performance, with a macro-F1 score of 0.658 ± 0.027. Class-wise analysis showed higher performance for extreme engagement levels (not engaged and engaged), with most misclassifications occurring between adjacent classes, particularly involving the neutral state. Feature selection and explainability analyses identified exoskeleton-derived torque features as the most influential predictors, with thermal and HRV features providing complementary autonomic and emotional information. CONCLUSIONS: This study presents a novel multimodal machine learning approach for automatic engagement estimation during RAGT in children with cerebral palsy. Beyond classification performance, it demonstrates the feasibility of objective engagement modelling in a complex clinical population by integrating physiological and robotic interaction data. The results highlight the potential of multimodal sensing to support adaptive rehabilitation systems for continuous monitoring and personalized human-robot interaction.

来源:J Neuroeng Rehabil,查看原文。版权归原作者所有。

引用

  1. Campilii E, Romano F, Perpetuini D, et al. Multimodal engagement estimation in paediatric robot-assisted gait training: integrating physiological sensing and biomechanical interaction. J Neuroeng Rehabil. 2026. PMID: 42316377. doi:10.1186/s12984-026-02050-2

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。