University of Tennessee Health Science Center, Department of Pediatrics and Department of Anatomy and Neurobiology, Le Bonheur Children's Hospital, Neuroscience Institute, Memphis, TN, USA.
University of Tennessee Health Science Center, Department of Pediatrics, Le Bonheur Children's Hospital, Neuroscience Institute, Memphis, TN, USA.
Clin Neurophysiol. 2018 Mar;129(3):560-571. doi: 10.1016/j.clinph.2017.12.031. Epub 2018 Jan 4.
To predict the postoperative language outcome using the support vector regression (SVR) and results of multimodal presurgical language mapping.
Eleven patients with epilepsy received presurgical language mapping using functional MRI (fMRI), magnetoencephalography (MEG), transcranial magnetic stimulation (TMS), and high-gamma electrocorticography (hgECoG), as well as pre- and postoperative neuropsychological evaluation of language. We constructed 15 (2-1) SVR models by considering the extent of resected language areas identified by all subsets of four modalities as input feature vector and the postoperative language outcome as output. We trained and cross-validated SVR models, and compared the cross-validation (CV) errors of all models for prediction of language outcome.
Seven patients had some level of postoperative language decline and two of them had significant postoperative decline in naming. Some parts of language areas identified by four modalities were resected in these patients. We found that an SVR model consisting of fMRI, MEG, and hgECoG provided minimum CV error, although an SVR model consisting of fMRI and MEG was the optimal model that facilitated the best trade-off between model complexity and prediction accuracy.
A multimodal SVR can be used to predict the language outcome.
The developed multimodal SVR models in this study can be utilized to calculate the language outcomes of different resection plans prior to surgery and select the optimal surgical plan.
利用支持向量回归（SVR）和多模态术前语言定位的结果预测术后语言结果。
11 例癫痫患者接受了功能磁共振成像（fMRI）、脑磁图（MEG）、经颅磁刺激（TMS）和高伽马皮层脑电图（hgECoG）的术前语言定位，以及术前和术后的语言神经心理学评估。我们通过考虑所有四个模态的子集识别的切除语言区的范围作为输入特征向量，并将术后语言结果作为输出，构建了 15 个（2-1）SVR 模型。我们对 SVR 模型进行了训练和交叉验证，并比较了所有模型对语言结果预测的交叉验证（CV）误差。
7 例患者术后有一定程度的语言下降，其中 2 例在命名方面有明显的术后下降。这些患者的部分语言区是由四种模态中的一部分识别出来的。我们发现，由 fMRI、MEG 和 hgECoG 组成的 SVR 模型提供了最小的 CV 误差，尽管由 fMRI 和 MEG 组成的 SVR 模型是最佳模型，它在模型复杂性和预测准确性之间实现了最佳折衷。
多模态 SVR 可用于预测语言结果。
本研究中开发的多模态 SVR 模型可用于计算不同切除方案的语言结果，并选择最佳的手术方案。
