重症监护病人脑电数据的自动聚类分析（英文）

Automatic clustering of EEG data from ICU patients

癫痫性发作、持续状态及痫样节律性活动是常见的病理性脑部放电状态,通常会在急性脑损伤患者的脑电图(EEG)中表现出来。完成此类病理性波形的有效标记,是进一步诊断与治疗相关疾病的重要前提。为辅助神经内科专家对不同病理波形进行快速标记,文中提出了一种全新的辅助检测标记系统。该系统分别采用特征提取、PCA降维和LE映射可视化等技术,实现EEG中同质模式簇的自动检测。所提方法对哈佛医学院/麻省总医院中10例ICU患者的长时程连续脑电图进行了系统分析。数值实验结果表明,海量脑电数据能够被有效地自动聚类为多种ICU典型标准波形,而且仅通过观测类中心及若干同类成员就能够达到有效标记的目标。同时,LE可视化结果也进一步证实了"发作间期-发作期"连续统假设是成立的。

Seizures,status epilepticus,and seizure-like rhythmic or periodic activity are common,pathological,and harmful states of brain electrical activity seen in the electroencephalogram(EEG)of patients during critical medical illnesses or acute brain injury.In this study,we aimed to develop a valid method to automatically discover a small number of homogeneous pattern clusters,to facilitate efficient interactive labelling by EEG experts.Long term continuous EEG of ten ICU patients at MGH were analysed,undergoing the pipeline of feature extraction,PCA-based dimensionality reduction,and embedding through LE map.This research suggests that large EEG datasets can be automatically clustered into a small number of patterns described by standard ICU EEG pattern labels.We demonstrated efficient cluster labelling by inspecting only the centroids of clusters.Furthermore,LE visualizations support the hypothesis of an interictal-ictal continuum.