Leaver Amber M, Wade Benjamin, Vasavada Megha, Hellemann Gerhard, Joshi Shantanu H, Espinoza Randall, Narr Katherine L
Ahmanson-Lovelace Brain Mapping Center, Department of Neurology, University of California Los Angeles, Los Angeles, CA, United States.
Department of Psychiatry and Biobehavioral Sciences, University of California Los Angeles, Los Angeles, CA, United States.
Front Psychiatry. 2018 Mar 21;9:92. doi: 10.3389/fpsyt.2018.00092. eCollection 2018.
Electroconvulsive therapy (ECT) is arguably the most effective available treatment for severe depression. Recent studies have used MRI data to predict clinical outcome to ECT and other antidepressant therapies. One challenge facing such studies is selecting from among the many available metrics, which characterize complementary and sometimes non-overlapping aspects of brain function and connectomics. Here, we assessed the ability of aggregated, functional MRI metrics of basal brain activity and connectivity to predict antidepressant response to ECT using machine learning.
A radial support vector machine was trained using arterial spin labeling (ASL) and blood-oxygen-level-dependent (BOLD) functional magnetic resonance imaging (fMRI) metrics from n = 46 (26 female, mean age 42) depressed patients prior to ECT (majority right-unilateral stimulation). Image preprocessing was applied using standard procedures, and metrics included cerebral blood flow in ASL, and regional homogeneity, fractional amplitude of low-frequency modulations, and graph theory metrics (strength, local efficiency, and clustering) in BOLD data. A 5-repeated 5-fold cross-validation procedure with nested feature-selection validated model performance. Linear regressions were applied post hoc to aid interpretation of discriminative features.
The range of balanced accuracy in models performing statistically above chance was 58-68%. Here, prediction of non-responders was slightly higher than for responders (maximum performance 74 and 64%, respectively). Several features were consistently selected across cross-validation folds, mostly within frontal and temporal regions. Among these were connectivity strength among: a fronto-parietal network [including left dorsolateral prefrontal cortex (DLPFC)], motor and temporal networks (near ECT electrodes), and/or subgenual anterior cingulate cortex (sgACC).
Our data indicate that pattern classification of multimodal fMRI metrics can successfully predict ECT outcome, particularly for individuals who will not respond to treatment. Notably, connectivity with networks highly relevant to ECT and depression were consistently selected as important predictive features. These included the left DLPFC and the sgACC, which are both targets of other neurostimulation therapies for depression, as well as connectivity between motor and right temporal cortices near electrode sites. Future studies that probe additional functional and structural MRI metrics and other patient characteristics may further improve the predictive power of these and similar models.
电休克疗法（ECT）可以说是治疗重度抑郁症最有效的现有方法。最近的研究利用磁共振成像（MRI）数据来预测ECT及其他抗抑郁疗法的临床疗效。此类研究面临的一个挑战是从众多可用指标中进行选择，这些指标表征了脑功能和连接组学的互补且有时不重叠的方面。在此，我们使用机器学习评估了基础脑活动和连接性的聚合功能MRI指标预测ECT抗抑郁反应的能力。
使用来自n = 46名（26名女性，平均年龄42岁）ECT治疗前抑郁症患者（大多数为右侧单侧刺激）的动脉自旋标记（ASL）和血氧水平依赖（BOLD）功能磁共振成像（fMRI）指标训练径向支持向量机。使用标准程序进行图像预处理，指标包括ASL中的脑血流量，以及BOLD数据中的局部一致性、低频调制分数振幅和图论指标（强度、局部效率和聚类）。采用带有嵌套特征选择的5次重复5折交叉验证程序来验证模型性能。事后应用线性回归以辅助解释判别特征。
在统计学上表现高于随机水平的模型中，平衡准确率范围为58 - 68%。在此，对无反应者的预测略高于对有反应者（最高性能分别为74%和64%）。在交叉验证折叠中一致选择了几个特征，主要在额叶和颞叶区域内。其中包括以下区域之间的连接强度：额顶网络[包括左侧背外侧前额叶皮层（DLPFC）]、运动和颞叶网络（靠近ECT电极），和/或膝下前扣带回皮层（sgACC）。
我们的数据表明，多模态fMRI指标的模式分类可以成功预测ECT结果，特别是对于那些对治疗无反应的个体。值得注意的是，与ECT和抑郁症高度相关的网络的连接性一直被选为重要的预测特征。这些包括左侧DLPFC和sgACC，它们都是抑郁症其他神经刺激疗法的靶点，以及电极部位附近运动和右侧颞叶皮层之间的连接性。未来探究更多功能和结构MRI指标以及其他患者特征的研究可能会进一步提高这些及类似模型的预测能力。
