Department of Rehabilitation Medicine, the Second Affiliated Hospital, School of Medicine, South China University of Technology, Guangzhou, 510013 China.
Department of Rehabilitation Medicine, the Second Affiliated Hospital, School of Medicine, South China University of Technology, Guangzhou, 510013 China; Department of Rehabilitation Medicine, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, 519041 China.
Brain Res Bull. 2024 Mar;208:110902. doi: 10.1016/j.brainresbull.2024.110902. Epub 2024 Feb 16.
Continuous theta burst stimulation and intermittent theta burst stimulation are clinically popular models of repetitive transcranial magnetic stimulation. However, they are limited by high variability between individuals in cortical excitability changes following stimulation. Although electroencephalography oscillations have been reported to modulate the cortical response to transcranial magnetic stimulation, their association remains unclear. This study aims to explore whether machine learning models based on EEG oscillation features can predict the cortical response to transcranial magnetic stimulation.
Twenty-three young, healthy adults attended two randomly assigned sessions for continuous and intermittent theta burst stimulation. In each session, ten minutes of resting-state electroencephalography were recorded before delivering brain stimulation. Participants were classified as responders or non-responders based on changes in resting motor thresholds. Support vector machines and multi-layer perceptrons were used to establish predictive models of individual responses to transcranial magnetic stimulation.
Among the evaluated algorithms, support vector machines achieved the best performance in discriminating responders from non-responders for intermittent theta burst stimulation (accuracy: 91.30%) and continuous theta burst stimulation (accuracy: 95.66%). The global clustering coefficient and global characteristic path length in the beta band had the greatest impact on model output.
These findings suggest that EEG features can serve as markers of cortical response to transcranial magnetic stimulation. They offer insights into the association between neural oscillations and variability in individuals' responses to transcranial magnetic stimulation, aiding in the optimization of individualized protocols.
连续 theta 爆发刺激和间歇 theta 爆发刺激是重复经颅磁刺激的两种临床常用模式。然而，它们在刺激后皮质兴奋性变化方面个体间的可变性很大。尽管已经报道了脑电图振荡可以调节经颅磁刺激的皮质反应，但它们之间的关联尚不清楚。本研究旨在探讨基于脑电图振荡特征的机器学习模型是否可以预测经颅磁刺激的皮质反应。
23 名年轻健康的成年人参加了连续和间歇 theta 爆发刺激的两次随机分配的会议。在每次会议中，在给予脑刺激之前记录十分钟的静息状态脑电图。根据静息运动阈值的变化，将参与者分为反应者和无反应者。支持向量机和多层感知器被用于建立个体对经颅磁刺激反应的预测模型。
在所评估的算法中，支持向量机在区分间歇 theta 爆发刺激（准确性：91.30%）和连续 theta 爆发刺激（准确性：95.66%）的反应者和无反应者方面表现出最佳性能。β 波段的全局聚类系数和全局特征路径长度对模型输出的影响最大。
这些发现表明脑电图特征可以作为经颅磁刺激皮质反应的标志物。它们提供了关于神经振荡与个体对经颅磁刺激反应的可变性之间关联的见解，有助于优化个体化方案。
