摘要
射频热凝毁损术(RFTC)治疗难治性癫痫的疗效的个体差异较大。本课题旨在研究术前脑网络图论指标,建立预测RFTC预后的模型。基于45例难治性癫痫患者术前的立体脑电图数据,建立时变多变量自回归模型,通过计算频谱加权的时变部分指向性相干,构建时变效应连接网络,计算图论指标。根据RFTC后至少3个月的Engel分级,将患者分为RFTC有效组(EngelⅠ和Ⅱ级)与RFTC无效组(EngelⅢ级),进行组间图论指标的统计学分析,并基于图论指标,应用支持向量机(SVM)建模进行预后预测。结果表明,RFTC有效组的标准化的平均聚类系数(P=0.000)、小世界性(P=0.022)显著高于RFTC无效组,标准化的特征路径长度显著低于RFTC无效组(P=0.032)(RFTC有效组的标准化的平均聚类系数、小世界性和标准化的特征路径长度分别为0.9953±0.0002、0.8530±0.0062和1.1688±0.0085;RFTC无效组的标准化的平均聚类系数、小世界性和标准化的特征路径长度分别为0.9940±0.0002、0.8335±0.0056和1.1944±0.0080);应用以上3个指标,通过SVM进行RFTC疗效的预测,准确率达到81.97%。应用难治性癫痫患者术前的脑效应连接网络图论指标标准化的平均聚类系数、标准化的特征路径长度和小世界性建立的预后预测模型可以很好地预测RFTC疗效。
The outcome of radiofrequency thermocoagulation(RFTC)in different patients with refractory epilepsy is usually largely different.This study aimed to investigate graph theory indexes of brain networks and establish a RFTC prognosis prediction model.Based on the stereo-electroencephalography(SEEG)signals of 45 patients with refractory epilepsy before RFTC,a time-variant multi-variate autoregressive model was constructed.Spectrum-weighted time-variant partial directed coherence was computed to build an effective connectivity network of the brain and graph theory indexes of the effective connectivity network were analyzed.According to the Engel classification at least three months after RFTC,the patients were divided into RFTC responder group(Engel Ⅰ&Ⅱ)and RFTC non-responder group(Engel Ⅲ).The graph theory indexes were used for statistical analysis between the two groups and for establishing prognosis prediction by support vector machine(SVM).The normalized average clustering coefficient(P=0.000)and small-worldness(P=0.022)of the patients in RFTC responder group were significantly higher than those in RFTC non-responder group,and the normalized characteristic path length was significantly lower than those in the RFTC non-responder group(P=0.032)(The normalized average clustering coefficient,the small-worldness and the normalized characteristic path length of the patients in the RFTC responder group were 0.9953±0.0002,0.8530±0.0062 and 1.1688±0.0085,respectively.The normalized average clustering coefficient,small-worldness and normalized characteristic path length of the patients in RFTC non-responder group were 0.9940±0.0002,0.8335±0.0056 and 1.1944±0.0080),respectively.Based on the three indexes,the accuracy of the prognosis prediction reached 81.97% by SVM.The RFTC prognosis prediction model based on the graph theory indexes(normalized average clustering coefficient,normalized characteristic path length,and small-worldness)of the effective connectivity networks before RFTC could effectively predict the postoperative outcome.
作者
杨淑窈
谢宇海
宫语晨
刘强强
张溥明
Yang Shuyao;Xie Yuhai;Gong Yuchen;Liu Qiangqiang;Zhang Puming(School of Biomedical Engineering,Shanghai Jiao Tong University,Shanghai 200030,China;Clinical Neuroscience Center,Department of Functional Neurosurgery,Ruijin Hospital Luwan Branch,Shanghai Jiao Tong University School of Medicine,Shanghai 200025,China)
出处
《中国生物医学工程学报》
CAS
CSCD
北大核心
2023年第6期651-658,共8页
Chinese Journal of Biomedical Engineering
基金
国家自然科学基金(82071550)
上海交通大学医工交叉研究基金(YG2021QN30)。
关键词
癫痫
立体脑电图引导射频热凝毁损术
效应连接网络
图论
支持向量机
epilepsy
stereo-electroencephalography guided radiofrequency thermocoagulation
effective connectivity network
graph theory
support vector machine
作者简介
通信作者:张溥明,E-mail:pmzhang@sjtu.edu.cn。
