当前位置: X-MOL 学术Clin. EEG Neurosci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Detection of an Autism EEG Signature From Only Two EEG Channels Through Features Extraction and Advanced Machine Learning Analysis
Clinical EEG and Neuroscience ( IF 2 ) Pub Date : 2020-12-21 , DOI: 10.1177/1550059420982424
Enzo Grossi 1 , Giovanni Valbusa 2 , Massimo Buscema 3, 4
Affiliation  

BACKGROUND AND OBJECTIVE In 2 previous studies, we have shown the ability of special machine learning systems applied to standard EEG data in distinguishing children with autism spectrum disorder (ASD) from non-ASD children with an overall accuracy rate of 100% and 98.4%, respectively. Since the equipment routinely available in neonatology units employ few derivations, we were curious to check if just 2 derivations were enough to allow good performance in the same cases of the above-mentioned studies. METHODS A continuous segment of artifact-free EEG data lasting 1 minute in ASCCI format from C3 and C4 EEG channels present in 2 previous studies, was used for features extraction and subsequent analyses with advanced machine learning systems. A features extraction software package (Python tsfresh) applied to time-series raw data derived 1588 quantitative features. A special hybrid system called TWIST (Training with Input Selection and Testing), coupling an evolutionary algorithm named Gen-D and a backpropagation neural network, was used to subdivide the data set into training and testing sets as well as to select features yielding the maximum amount of information after a first variable selection performed with linear correlation index threshold. RESULTS After this intelligent preprocessing, 12 features were extracted from C3-C4 time-series of study 1 and 36 C3-C4 time-series of study 2 representing the EEG signature. Acting on these features the overall accuracy predictive capability of the best artificial neural network acting as a classifier in deciphering autistic cases from typicals (study 1) and other neuropsychiatric disorders (study 2) resulted in 100 % for study 1 and 94.95 % for study 2. CONCLUSIONS The results of this study suggest that also a minor part of EEG contains precious information useful to detect autism if treated with advanced computational algorithms. This could allow in the future to use standard EEG from newborns to check if the ASD signature is already present at birth.

中文翻译:

通过特征提取和高级机器学习分析仅从两个 EEG 通道检测自闭症 EEG 特征

背景和目的 在之前的 2 项研究中,我们展示了特殊机器学习系统应用于标准 EEG 数据在区分自闭症谱系障碍 (ASD) 儿童和非 ASD 儿童方面的能力,总体准确率分别为 100% 和 98.4%,分别。由于新生儿科常规使用的设备很少使用衍生物,因此我们很好奇是否仅使用 2 个衍生物就足以在上述研究的相同情况下获得良好的性能。方法 来自先前 2 项研究中存在的 C3 和 C4 EEG 通道的持续 1 分钟的无伪影 EEG 数据的连续片段,以 ASCCI 格式,用于特征提取和随后的高级机器学习系统分析。一个特征提取软件包(Python tsfresh)应用于时间序列原始数据,导出1588个定量特征。一种称为 TWIST(输入选择和测试训练)的特殊混合系统,将名为 Gen-D 的进化算法和反向传播神经网络耦合在一起,用于将数据集细分为训练集和测试集,并选择产生最大的特征使用线性相关指数阈值执行第一次变量选择后的信息量。结果 在这种智能预处理之后,从研究 1 的 C3-C4 时间序列和研究 2 的 36 个 C3-C4 时间序列中提取了 12 个特征,代表 EEG 特征。根据这些特征,作为分类器的最佳人工神经网络在从典型(研究 1)和其他神经精神障碍(研究 2)中解密自闭症病例的整体准确度预测能力导致研究 1 为 100 %,研究 2 为 94.95 % . 结论 这项研究的结果表明,如果使用先进的计算算法进行治疗,EEG 的一小部分也包含可用于检测自闭症的宝贵信息。这可以在未来使用新生儿的标准脑电图来检查 ASD 签名是否在出生时就已经存在。结论 这项研究的结果表明,如果使用先进的计算算法进行治疗,EEG 的一小部分也包含可用于检测自闭症的宝贵信息。这可以在未来使用新生儿的标准脑电图来检查 ASD 签名是否在出生时就已经存在。结论 这项研究的结果表明,如果使用先进的计算算法进行治疗,EEG 的一小部分也包含可用于检测自闭症的宝贵信息。这可以在未来使用新生儿的标准脑电图来检查 ASD 签名是否在出生时就已经存在。
更新日期:2020-12-21
down
wechat
bug