Agarwal R, Gotman J, Flanagan D, Rosenblatt B
Montreal Neurological Institute, McGill University, Quebec, Canada.
Electroencephalogr Clin Neurophysiol. 1998 Jul;107(1):44-58. doi: 10.1016/s0013-4694(98)00009-1.
To assist in the reviewing of prolonged EEGs, we have developed an automatic EEG analysis method that can be used to compress the prolonged EEG into two pages. The proposed approach of Automatic Analysis of Segmented-EEG (AAS-EEG) consists of 4 basic steps: (1) segmentation; (2) feature extraction; (3) classification; and (4) presentation. The idea is to break down the EEG into stationary segments and extract features that can be used to classify the segments into groups of like patterns. The final step involves the presentation of the processed data in a compressed form. This is done by providing the EEGer with a representative sample from each group of EEG patterns and a compressed time profile of the complete EEG. To verify the above approach, 41 6 h EEG records were assessed for normality via the AAS-EEG and conventional EEG approaches. The difference between the overall assessment via compressed and conventional EEG was within one abnormality level 100% of the time, and within one-half level for 73.6% of the records. We demonstrated the feasibility and reliability of automatically segmenting and clustering the EEG, thus allowing the reduction of a 6 h tracing to a few representative segments and their time sequence. This should facilitate review of long recordings during monitoring in the ICU.
为了辅助长时间脑电图（EEG）的审查，我们开发了一种自动脑电图分析方法，可用于将长时间的脑电图压缩为两页。所提出的分段脑电图自动分析（AAS-EEG）方法包括4个基本步骤：（1）分段；（2）特征提取；（3）分类；以及（4）呈现。其思路是将脑电图分解为平稳段，并提取可用于将这些段分类为相似模式组的特征。最后一步涉及以压缩形式呈现处理后的数据。这是通过为脑电图分析师提供来自每组脑电图模式的代表性样本以及完整脑电图的压缩时间概况来实现的。为了验证上述方法，通过AAS-EEG和传统脑电图方法对41份6小时的脑电图记录进行了正常性评估。通过压缩脑电图和传统脑电图进行的总体评估之间的差异在100%的时间内处于一个异常级别之内，并且在73.6%的记录中处于半个级别之内。我们证明了自动分割和聚类脑电图的可行性和可靠性，从而能够将6小时的追踪记录减少为几个代表性段及其时间序列。这应该有助于在重症监护病房（ICU）监测期间对长时间记录进行审查。
