Neural oscillatory changes within and across different frequency bands are thought to underlie motor dysfunction in Parkinson's disease (PD) and may serve as PD biomarkers. Here, we used oscillatory signals derived from chronically-implanted cortical and subcortical electrode arrays as features to train machine-learning algorithms to classify the clinical states in a nonhuman primate model. LFP data were collected over several months from a 12-channel subdural ECoG grid and a 6-channel custom array implanted in the subthalamic nucleus (STN). Relative to the naïve state, PD-state showed elevated M1 and STN power in the beta, high-gamma, and HFO bands, but decreased power in the delta band. Theta power decreased in STN but not M1. In the PD state there was elevated beta-HFO phase-amplitude coupling (PAC) in the STN. We applied support vector machines with Radial Basis Function (SVM-RBF) kernel, and k-nearest neighbors (KNN) classifiers trained by features related to power and PAC changes to discriminate between the naïve and PD states. Our results show that the most predictive feature of Parkinsonism in the STN was high-beta (~86% accuracy), and HFO in M1 (~98% accuracy). A feature fusion approach outperformed every individual feature in the STN (~96% accuracy). Overall, our data demonstrate the ability to use different frequency band powers in classifying clinical state, including a potential added benefit of feature fusion approaches, even during a relatively mild stage of the disease. This type of feature-tailored approach (using single or multiple features) may contribute to further optimizing patient-specific closed-loop or adaptive DBS approaches.

中文翻译：

---

神经振荡变化和机器学习揭示的轻度帕金森病的预测

不同频带内和不同频带之间的神经振荡变化被认为是帕金森病 (PD) 运动功能障碍的基础，并可作为 PD 生物标志物。在这里，我们使用源自长期植入的皮层和皮层下电极阵列的振荡信号作为特征来训练机器学习算法以对非人类灵长类动物模型中的临床状态进行分类。LFP 数据是在几个月内从 12 通道硬膜下 ECoG 网格和植入丘脑底核 (STN) 的 6 通道定制阵列中收集的。相对于初始状态，PD 状态在 beta、高伽马和 HFO 频段显示出 M1 和 STN 功率升高，但在 delta 频段中降低了功率。STN 中的 Theta 功率降低，但 M1 中没有。在 PD 状态下，STN 中的 β-HFO 相位幅度耦合 (PAC) 升高。我们应用了带有径向基函数 (SVM-RBF) 内核的支持向量机，以及通过与功率和 PAC 变化相关的特征训练的 k 最近邻 (KNN) 分类器来区分朴素和 PD 状态。我们的结果表明，STN 中帕金森病最具预测性的特征是高 β（准确率约 86%）和 M1 中的 HFO（准确率约 98%）。特征融合方法优于 STN 中的每个单独特征（约 96% 的准确率）。总体而言，我们的数据证明了使用不同频带功率对临床状态进行分类的能力，包括特征融合方法的潜在附加好处，即使在疾病相对较轻的阶段也是如此。这种类型的特征定制方法（使用单个或多个特征）可能有助于进一步优化特定于患者的闭环或自适应 DBS 方法。