Human and automated detection of high-frequency oscillations in clinical intracranial EEG recordings
Human and automated detection of high-frequency oscillations in clinical intracranial EEG recordings
复制标题
DOI：
10.1016/j.clinph.2006.12.019
复制
发表时间：
2007-05-01
影响因子：
4.7
通讯作者：
Litt, Brian
中科院分区：
文献类型：
--
作者：
Gardner, Andrew B.;Worrell, Greg A.;Litt, Brian
目的：近期研究表明，病理性高频振荡（HFOs）是致痫性大脑的特征。需要自动化工具来描述这些事件。我们提出一种新算法，用于检测30至85赫兹的HFOs，并通过人类脑电图专家进行验证。
方法：我们从两名患者中随机选取28个3分钟的单通道颅内脑电图（IEEG）时段。三名人类评审员和三个自动探测器对所有记录进行标记，以识别候选的HFOs。随后，人类评审员对所有标记进行验证。
结果：总共共同识别出1330个事件。此处提出的新方法相对于人类专家一致标记集达到了89.7%的准确率。单因素方差分析确定人类评审员和自动算法的平均F值之间没有差异。人类kappa统计量（平均kappa = 0.38）显示出边缘的识别一致性，主要是由于假阴性错误。
结论：我们提出一种HFO探测器，它对现有算法进行了改进，并且在我们的测试数据集上表现与人类专家一样好。由于评分者间的变异性，探测器性能的验证必须与不止一名专家进行比较。
意义：该算法将有助于分析大型脑电图数据库，以确定HFO事件在人类癫痫网络中的病理生理意义。（c）2007国际临床神经生理学联合会。由爱思唯尔爱尔兰有限公司出版。保留所有权利。
Objective: Recent studies indicate that pathologic high-frequency oscillations (HFOs) are signatures of epileptogenic brain. Automated tools are required to characterize these events. We present a new algorithm tuned to detect HFOs from 30 to 85 Hz, and validate it against human expert electroencephalographers.Methods: We randomly selected 28 3-min-single-channel epochs of intracranial EEG (IEEG) from two patients. Three human reviewers and three automated detectors marked all records to identify candidate HFOs. Subsequently, human reviewers verified all markings.Results: A total of 1330 events were collectively identified. The new method presented here achieved 89.7% accuracy against a consensus set of human expert markings. A one-way ANOVA determined no difference between the mean F-measures of the human reviewers and automated algorithm. Human kappa statistics (mean kappa = 0.38) demonstrated marginal identification consistency, primarily due to false negative errors.Conclusions: We present an HFO detector that improves upon existing algorithms, and performs as well as human experts on our test data set. Validation of detector performance must be compared to more than one expert because of interrater variability.Significance: This algorithm will be useful for analyzing large EEG databases to determine the pathophysiological significance of HFO events in human epileptic networks. (c) 2007 International Federation of Clinical Neurophysiology. Published by Elsevier Ireland Ltd. All rights reserved.