Suresh Rishishankar E, Zobaer M S, Triano Matthew J, Saway Brian F, Rowland Nathan C
Medical University of South Carolina.
Res Sq. 2024 Sep 2:rs.3.rs-4809587. doi: 10.21203/rs.3.rs-4809587/v1.
In individuals with chronic stroke and hemiparesis, noninvasive brain stimulation (NIBS) may be used as an adjunct to therapy for improving motor recovery. Specific states of movement during motor recovery are more responsive to brain stimulation than others, thus a system that could auto-detect movement state would be useful in correctly identifying the most effective stimulation periods. The aim of this study was to compare the performance of different machine learning models in classifying movement periods during EEG recordings of hemiparetic individuals receiving noninvasive brain stimulation. We hypothesized that transcranial direct current stimulation, a form of NIBS, would modulate brain recordings correlating with movement state and improve classification accuracies above those receiving sham stimulation.
Electroencephalogram data were obtained from 10 participants with chronic stroke and 11 healthy individuals performing a motor task while undergoing transcranial direct current stimulation. Eight traditional machine learning algorithms and five ensemble methods were used to classify two movement states (a hold posture and an arm reaching movement) before, during and after stimulation. To minimize compute times, preprocessing and feature extraction were limited to z-score normalization and power binning into five frequency bands (delta through gamma).
Classification of disease state produced significantly higher accuracies in the stimulation (versus sham) group at 78.9% (versus 55.6%, p < 0.000002). We observed significantly higher accuracies when classifying stimulation state in the chronic stroke group (77.6%) relative to healthy controls (64.1%, p < 0.0095). In the chronic stroke cohort, classification of hold versus reach was highest during the stimulation period (75.2%) as opposed to the pre- and post-stimulation periods. Linear discriminant analysis, logistic regression, and decision tree algorithms classified movement state most accurately in participants with chronic stroke during the stimulation period (76.1%). For the ensemble methods, the highest classification accuracy for hold versus reach was achieved using low gamma frequency (30-50 Hz) as a feature (74.5%), although this result did not achieve statistical significance.
Machine learning algorithms demonstrated sufficiently high movement state classification accuracy in participants with chronic stroke performing functional tasks during noninvasive brain stimulation. tDCS improved disease state and movement state classification in participants with chronic stroke.
在患有慢性中风和偏瘫的个体中，非侵入性脑刺激（NIBS）可作为治疗辅助手段以改善运动恢复。运动恢复过程中的特定运动状态对脑刺激的反应比其他状态更敏感，因此，一个能够自动检测运动状态的系统将有助于正确识别最有效的刺激时段。本研究的目的是比较不同机器学习模型在对接受非侵入性脑刺激的偏瘫个体进行脑电图记录时的运动时段分类性能。我们假设经颅直流电刺激（一种NIBS形式）会调节与运动状态相关的脑记录，并提高分类准确率，高于接受假刺激的个体。
从10名患有慢性中风的参与者和11名健康个体在接受经颅直流电刺激时执行运动任务过程中获取脑电图数据。使用8种传统机器学习算法和5种集成方法对刺激前、刺激期间和刺激后的两种运动状态（保持姿势和手臂伸展运动）进行分类。为了最小化计算时间，预处理和特征提取限于z分数归一化以及将功率划分为五个频段（从δ到γ）。
疾病状态分类在刺激组（相对于假刺激组）的准确率显著更高，为78.9%（相对于55.6%，p<0.000002）。我们观察到，相对于健康对照组（64.1%，p<0.0095），慢性中风组在对刺激状态进行分类时准确率显著更高（77.6%）。在慢性中风队列中，保持与伸展的分类在刺激期间最高（75.2%），而不是在刺激前和刺激后阶段。线性判别分析、逻辑回归和决策树算法在刺激期间对慢性中风参与者的运动状态分类最准确（76.1%）。对于集成方法，使用低γ频率（30 - 50Hz）作为特征时，保持与伸展的分类准确率最高（74.5%），尽管该结果未达到统计学显著性。
机器学习算法在患有慢性中风的参与者进行非侵入性脑刺激时执行功能任务过程中显示出足够高的运动状态分类准确率。经颅直流电刺激改善了慢性中风参与者的疾病状态和运动状态分类。
