Data_Sheet_1_Combined brain network topological metrics with machine learning algorithms to identify essential tremor.docx

Background and objectiveEssential tremor (ET) is a common movement syndrome, and the pathogenesis mechanisms, especially the brain network topological changes in ET are still unclear. The combination of graph theory (GT) analysis with machine learning (ML) algorithms provides a promising way to identify ET from healthy controls (HCs) at the individual level, and further help to reveal the topological pathogenesis in ET.
MethodsResting-state functional magnetic resonance imaging (fMRI) data were obtained from 101 ET and 105 HCs. The topological properties were analyzed by using GT analysis, and the topological metrics under every single threshold and the area under the curve (AUC) of all thresholds were used as features. Then a Mann-Whitney U-test and least absolute shrinkage and selection operator (LASSO) were conducted to feature dimensionality reduction. Four ML algorithms were adopted to identify ET from HCs. The mean accuracy, mean balanced accuracy, mean sensitivity, mean specificity, and mean AUC were used to evaluate the classification performance. In addition, correlation analysis was carried out between selected topological features and clinical tremor characteristics.
ResultsAll classifiers achieved good classification performance. The mean accuracy of Support vector machine (SVM), logistic regression (LR), random forest (RF), and naïve bayes (NB) was 84.65, 85.03, 84.85, and 76.31%, respectively. LR classifier achieved the best classification performance with 85.03% mean accuracy, 83.97% sensitivity, and an AUC of 0.924. Correlation analysis results showed that 2 topological features negatively and 1 positively correlated with tremor severity.
ConclusionThese results demonstrated that combining topological metrics with ML algorithms could not only achieve high classification accuracy for discrimination ET from HCs but also help us to reveal the potential topological pathogenesis of ET.

背景与目的：原发性震颤（Essential Tremor, ET）是一种常见的运动综合征，其发病机制，尤其是脑网络拓扑结构改变，目前仍未明确。将图论（Graph Theory, GT）分析与机器学习（Machine Learning, ML）算法相结合，为在个体层面区分原发性震颤患者与健康对照（Healthy Controls, HCs）提供了颇具前景的研究路径，同时也有助于进一步揭示原发性震颤的拓扑发病机制。

方法：本研究从101例原发性震颤患者及105例健康对照者中采集了静息态功能磁共振成像（Resting-state functional magnetic resonance imaging, fMRI）数据。采用图论分析方法对脑网络拓扑属性进行解析，以单个阈值下的拓扑指标及所有阈值对应的曲线下面积（Area Under the Curve, AUC）作为特征集。随后通过曼-惠特尼U检验（Mann-Whitney U-test）与最小绝对收缩和选择算子（Least Absolute Shrinkage and Selection Operator, LASSO）完成特征降维。采用四种机器学习算法实现原发性震颤患者与健康对照者的分类识别，并以平均准确率、平均平衡准确率、平均灵敏度、平均特异度及平均曲线下面积作为分类性能的评估指标。此外，本研究还对筛选得到的拓扑特征与临床震颤特征开展了相关性分析。

结果：所有分类器均取得了良好的分类性能。支持向量机（Support Vector Machine, SVM）、逻辑回归（Logistic Regression, LR）、随机森林（Random Forest, RF）及朴素贝叶斯（Naïve Bayes, NB）的平均准确率分别为84.65%、85.03%、84.85%及76.31%。其中逻辑回归分类器表现最优，其平均准确率达85.03%，灵敏度为83.97%，曲线下面积为0.924。相关性分析结果显示，共有2项拓扑特征与震颤严重程度呈负相关，1项拓扑特征与震颤严重程度呈正相关。

结论：本研究结果表明，将拓扑指标与机器学习算法相结合，不仅可实现原发性震颤患者与健康对照者的高精度分类识别，还有助于揭示原发性震颤潜在的拓扑发病机制。