Application of Machine Learning to Electroencephalography for the Diagnosis of Primary Progressive Aphasia: A Pilot Study.
Application of Machine Learning to Electroencephalography for the Diagnosis of Primary Progressive Aphasia: A Pilot Study.
复制标题
机器学习在诊断原发性进行性失语症的脑电图中的应用：一项初步研究。
DOI：
10.3390/brainsci11101262
复制
发表时间：
2021-09-24
期刊：
影响因子：
3.3
通讯作者：
Ayala JL
中科院分区：
文献类型：
--
作者：
Moral-Rubio C;Balugo P;Fraile-Pereda A;Pytel V;Fernández-Romero L;Delgado-Alonso C;Delgado-Álvarez A;Matias-Guiu J;Matias-Guiu JA;Ayala JL
背景原发性进行性失语症（PPA）是一种神经退行性综合征，诊断通常具有挑战性。诊断和监测需要生物标志物。在这项研究中，我们的目的是评估脑电图（EEG）作为诊断PPA的生物标志物。方法.我们进行了一项横断面研究，40例PPA患者分为非流利，语义，和logopenic变量，和20名对照。静息状态下的32个通道的EEG采集和预处理使用几个程序（定量EEG，小波变换，自动编码器，图论分析）。评估了七种机器学习算法（决策树、弹性网络、支持向量机、随机森林、K最近邻、高斯朴素贝叶斯和多项式朴素贝叶斯）。结果区分PPA和对照组的诊断能力很高（kNN算法的准确率为75%，F1评分为83%）。分类中最重要的特征来自基于图论的网络分析。相反，PPA变体之间的区分度较低（kNN的准确度为58%，F1评分为60%）。结论. ML在静息态EEG中的应用可能对PPA的诊断，特别是与对照组的鉴别诊断有一定的作用。未来的高密度EEG研究应探索区分PPA变体的能力。
Background. Primary progressive aphasia (PPA) is a neurodegenerative syndrome in which diagnosis is usually challenging. Biomarkers are needed for diagnosis and monitoring. In this study, we aimed to evaluate Electroencephalography (EEG) as a biomarker for the diagnosis of PPA. Methods. We conducted a cross-sectional study with 40 PPA patients categorized as non-fluent, semantic, and logopenic variants, and 20 controls. Resting-state EEG with 32 channels was acquired and preprocessed using several procedures (quantitative EEG, wavelet transformation, autoencoders, and graph theory analysis). Seven machine learning algorithms were evaluated (Decision Tree, Elastic Net, Support Vector Machines, Random Forest, K-Nearest Neighbors, Gaussian Naive Bayes, and Multinomial Naive Bayes). Results. Diagnostic capacity to distinguish between PPA and controls was high (accuracy 75%, F1-score 83% for kNN algorithm). The most important features in the classification were derived from network analysis based on graph theory. Conversely, discrimination between PPA variants was lower (Accuracy 58% and F1-score 60% for kNN). Conclusions. The application of ML to resting-state EEG may have a role in the diagnosis of PPA, especially in the differentiation from controls. Future studies with high-density EEG should explore the capacity to distinguish between PPA variants.
登录
查看更多内容
影响因子：
3.6
作者：
Matias-Guiu, Jordi A.;Diaz-Alvarez, Josefa;Ayala, Jose L.
通讯作者：
Ayala, Jose L.
影响因子：
1.8
作者：
Jalili, Mahdi;Knyazeva, Maria G.
通讯作者：
Knyazeva, Maria G.
影响因子：
11.2
作者：
Josephs KA;Martin PR;Botha H;Schwarz CG;Duffy JR;Clark HM;Machulda MM;Graff-Radford J;Weigand SD;Senjem ML;Utianski RL;Drubach DA;Boeve BF;Jones DT;Knopman DS;Petersen RC;Jack CR Jr;Lowe VJ;Whitwell JL
通讯作者：
Whitwell JL
影响因子：
3.4
作者：
Epelbaum S;Saade YM;Flamand Roze C;Roze E;Ferrieux S;Arbizu C;Nogues M;Azuar C;Dubois B;Tezenas du Montcel S;Teichmann M
通讯作者：
Teichmann M
影响因子：
4.2
作者：
Gaubert, Sinead;Houot, Marion;Epelbaum, Stephane
通讯作者：
Epelbaum, Stephane