Multi-shell connectome DWI-based graph theory measures for the prediction of temporal lobe epilepsy and cognition.
Multi-shell connectome DWI-based graph theory measures for the prediction of temporal lobe epilepsy and cognition.
复制标题
基于多壳连接体 DWI 的图论测量用于预测颞叶癫痫和认知。
DOI：
10.1093/cercor/bhad098
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Struck,Aaron
中科院分区：
文献类型：
--
作者：
Garcia-Ramos,Camille;Adluru,Nagesh;Chu,DanielY;Nair,Veena;Adluru,Anusha;Nencka,Andrew;Maganti,Rama;Mathis,Jedidiah;Conant,LisaL;Alexander,AndrewL;Prabhakaran,Vivek;Binder,JeffreyR;Meyerand,MaryE;Hermann,Bruce;Struck,Aaron
颞叶癫痫（Temporal lobe epilepsy，TLE）是最常见的癫痫综合征，它在经验上代表了一种网络障碍，这使得图论（graph theory，GT）成为理解TLE的一种实用方法。从协调DWI矩阵中提取的GT测量值用作支持向量机（SVM）分析中的因素，以区分各组，并在k均值算法中找到TLE内的内在结构表型。使用10倍交叉验证，SVM能够预测组成员资格（平均准确度= 0.70，曲线下面积（AUC）= 0.747，Brier评分（BS）= 0.264）。此外，k均值聚类确定了2个TLE簇：1个与对照相似，1个不相似。各组间认知表型分布差异有统计学意义（χ2= 6.641，P = 0.036），其中差异型组包含了大多数伴认知功能障碍的TLE患者。此外，集群成员之间的GT措施和临床变量显着相关性。考虑到SVM分类似乎是由相异聚类驱动的，重复SVM分析以分类相异与相似+对照，平均准确度为0.91（AUC = 0.957，BS = 0.189）。总之，结果的模式表明，GT措施的基础上，连接组DWI可能是显着的因素，在寻找TLE的临床和神经行为的生物标志物。
Temporal lobe epilepsy (TLE) is the most common epilepsy syndrome that empirically represents a network disorder, which makes graph theory (GT) a practical approach to understand it. Multi-shell diffusion-weighted imaging (DWI) was obtained from 89 TLE and 50 controls. GT measures extracted from harmonized DWI matrices were used as factors in a support vector machine (SVM) analysis to discriminate between groups, and in a k-means algorithm to find intrinsic structural phenotypes within TLE. SVM was able to predict group membership (mean accuracy = 0.70, area under the curve (AUC) = 0.747, Brier score (BS) = 0.264) using 10-fold cross-validation. In addition, k-means clustering identified 2 TLE clusters: 1 similar to controls, and 1 dissimilar. Clusters were significantly different in their distribution of cognitive phenotypes, with theDissimilarcluster containing the majority of TLE with cognitive impairment (χ2= 6.641,P= 0.036). In addition, cluster membership showed significant correlations between GT measures and clinical variables. Given that SVM classification seemed driven by theDissimilarcluster, SVM analysis was repeated to classifyDissimilarversusSimilar + Controlswith a mean accuracy of 0.91 (AUC = 0.957, BS = 0.189). Altogether, the pattern of results shows that GT measures based on connectome DWI could be significant factors in the search for clinical and neurobehavioral biomarkers in TLE.