机器学习和电场特征的个体差异可预测 tDCS 治疗反应。
Machine learning and individual variability in electric field characteristics predict tDCS treatment response.
机构信息
Center for Cognitive Aging and Memory, McKnight Brain Institute, University of Florida, Gainesville, USA; Department of Neuroscience, College of Medicine, University of Florida, Gainesville, USA.
Center for Cognitive Aging and Memory, McKnight Brain Institute, University of Florida, Gainesville, USA; J. Crayton Pruitt Family Department of Biomedical Engineering, Herbert Wertheim College of Engineering, University of Florida, Gainesville, USA.
出版信息
Brain Stimul. 2020 Nov-Dec;13(6):1753-1764. doi: 10.1016/j.brs.2020.10.001. Epub 2020 Oct 10.
BACKGROUND
Transcranial direct current stimulation (tDCS) is widely investigated as a therapeutic tool to enhance cognitive function in older adults with and without neurodegenerative disease. Prior research demonstrates that electric current delivery to the brain can vary significantly across individuals. Quantification of this variability could enable person-specific optimization of tDCS outcomes. This pilot study used machine learning and MRI-derived electric field models to predict working memory improvements as a proof of concept for precision cognitive intervention.
METHODS
Fourteen healthy older adults received 20 minutes of 2 mA tDCS stimulation (F3/F4) during a two-week cognitive training intervention. Participants performed an N-back working memory task pre-/post-intervention. MRI-derived current models were passed through a linear Support Vector Machine (SVM) learning algorithm to characterize crucial tDCS current components (intensity and direction) that induced working memory improvements in tDCS responders versus non-responders.
MAIN RESULTS
SVM models of tDCS current components had 86% overall accuracy in classifying treatment responders vs. non-responders, with current intensity producing the best overall model differentiating changes in working memory performance. Median current intensity and direction in brain regions near the electrodes were positively related to intervention responses (r=0.811,p<0.001 and r=0.774,p=0.001).
CONCLUSIONS
This study provides the first evidence that pattern recognition analyses of MRI-derived tDCS current models can provide individual prognostic classification of tDCS treatment response with 86% accuracy. Individual differences in current intensity and direction play important roles in determining treatment response to tDCS. These findings provide important insights into mechanisms of tDCS response as well as proof of concept for future precision dosing models of tDCS intervention.
背景
经颅直流电刺激（tDCS）作为一种增强患有和不患有神经退行性疾病的老年人认知功能的治疗工具，已得到广泛研究。先前的研究表明，电流输送到大脑在个体之间可能会有很大的差异。对这种变异性进行量化可以实现 tDCS 结果的个性化优化。这项初步研究使用机器学习和 MRI 衍生的电场模型来预测工作记忆改善，作为精准认知干预的概念验证。
方法
14 名健康的老年人在两周的认知训练干预期间接受了 20 分钟 2 mA 的 tDCS 刺激（F3/F4）。参与者在干预前后进行了 N 回工作记忆任务。将 MRI 衍生的电流模型通过线性支持向量机（SVM）学习算法进行传递，以描述在 tDCS 应答者与非应答者中诱导工作记忆改善的关键 tDCS 电流成分（强度和方向）。
主要结果
tDCS 电流成分的 SVM 模型对治疗应答者与非应答者的总体分类准确率为 86%，其中电流强度产生了最佳的整体模型，可区分工作记忆表现的变化。电极附近脑区的电流强度和方向中位数与干预反应呈正相关（r=0.811，p<0.001 和 r=0.774，p=0.001）。
结论
这项研究首次提供了证据，表明 MRI 衍生的 tDCS 电流模型的模式识别分析可以提供 86%准确率的 tDCS 治疗反应的个体预后分类。电流强度和方向的个体差异在确定 tDCS 治疗反应中起着重要作用。这些发现为 tDCS 反应的机制提供了重要的见解，并为未来的 tDCS 干预精准剂量模型提供了概念验证。
Zotero 插件