目的:使用来自受影响UE的残余自愿性EMG信号,在意向驱动的机器人手训练后,得出并验证上肢(UE)运动功能的最小临床重要差异(MCID)的预测模型。
方法:前瞻性纵向多中心队列研究。我们收集了干预前的候选预测因子:人口统计学,临床特征,UE的Fugl-Meyer评估(FMAUE),行动研究手臂测试成绩,在最大自愿收缩(MVC)期间通过EMG测量的趾屈肌和趾伸肌(ED)的运动意图。对于EMG措施,认识到中风幸存者移动瘫痪手的挑战,在MVC-EMG(0.1s-5s)期间,从八个时间窗口中提取峰值信号,以识别受试者的运动意图。采用分类和回归树算法预测具有FMAUEMCID的幸存者。进一步研究了预测因子与运动改善之间的关系。
方法:9个康复中心。
方法:慢性卒中幸存者(N=131),包括87个派生样本,44为验证样本。
方法:所有参与者都接受了20次机器人手训练(40分钟/次,3-5次/周)。
方法:通过受试者工作特征曲线下面积(AUC)评估模型的预测效果。最佳有效模型是最终模型,并使用AUC和总体准确性进行验证。
结果:最佳模型包括FMAUE(截止分数:46)和一秒MVC-EMG的ED峰值活动(MVC-EMG比静息EMG高4.604倍),与其他时间窗口或仅使用临床评分(AUC:0.595)相比,其预测准确性(AUC:0.807)显着提高。在外部验证中,该模型显示出稳健的预测(AUC:0.916)。在ED-EMG和FMAUE增加之间观察到显着的二次关系。
结论:本研究为慢性卒中幸存者的意向驱动机器人手训练提供了一个预测模型。它强调了通过1秒EMG窗口捕获运动意图的重要性,作为20次机器人训练后UE运动功能MCID改善的预测指标。两种情况下的幸存者表现出很高的临床运动改善百分比:中度至高度运动意图和低度至中度功能;以及高意图和高功能。
OBJECTIVE: To derive and validate a prediction model for minimal clinically important differences (MCID) in upper extremity (UE) motor function after intention-driven robotic-hand training using residual voluntary EMG signals from affected UE.
METHODS: A prospective longitudinal multicenter cohort study. We collected pre-intervention candidate predictors: demographics, clinical characteristics, Fugl-Meyer assessment of UE (FMAUE), Action Research Arm Test scores, and motor-intention of flexor digitorum and extensor digitorum (ED) measured by EMG during maximal voluntary contraction (MVC). For EMG measures, recognizing challenges for stroke survivors to move paralyzed hand, peak signals were extracted from eight time-windows during MVC-EMG (0.1s-5s) to identify subjects\' motor-intention. Classification And Regression Tree algorithm was employed to predict survivors with MCID of FMAUE. Relationship between predictors and motor-improvements was further investigated.
METHODS: Nine rehabilitation centers.
METHODS: Chronic stroke survivors (N=131), including 87 for Derivation-sample, and 44 for Validation-sample.
METHODS: All participants underwent 20-session robotic-hand training (40min/session, 3-5sessions/week).
METHODS: Prediction efficacies of models were assessed by area under the receiver operating characteristic curve (AUC). The best effective model was final model and validated using AUC and overall accuracy.
RESULTS: The best model comprised FMAUE (cut-off score: 46) and peak activity of ED from one-second MVC-EMG (MVC-EMG 4.604 times higher than resting-EMG), which demonstrated significantly higher prediction accuracy (AUC: 0.807) than other time-windows or solely using clinical-scores (AUC: 0.595). In external validation, this model displayed robust prediction (AUC: 0.916). Significant quadratic relationship was observed between ED-EMG and FMAUE increases.
CONCLUSIONS: This study presents a prediction model for intention-driven robotic-hand training in chronic stroke survivors. It highlights significance of capturing motor-intention through 1-second EMG-window as a predictor for MCID improvement in UE motor-function after 20-session robotic-training. Survivors in two conditions showed high percentage of clinical motor-improvement: moderate-to-high motor-intention and low-to-moderate function; as well as high-intention and high-function.