Nasseri Mona, Kremen Vaclav, Nejedly Petr, Kim Inyong, Chang Su-Youne, Joon Jo Hang, Guragain Hari, Nelson Nathaniel, Patterson Edward, Sturges Beverly K, Crowe Chelsea M, Denison Tim, Brinkmann Benjamin H, Worrell Gregory A
Mayo Systems Electrophysiology Laboratory, Department of Neurology, Mayo Clinic, Rochester, MN, USA.
Czech Institute of Informatics, Robotics, and Cybernetics, Czech Technical University in Prague, Prague, Czech Republic.
Biomed Signal Process Control. 2020 Mar;57. doi: 10.1016/j.bspc.2019.101743. Epub 2019 Nov 14.
Conventional selection of pre-ictal EEG epochs for seizure prediction algorithm training data typically assumes a continuous pre-ictal brain state preceding a seizure. This is carried out by defining a fixed duration, pre-ictal time period before seizures from which pre-ictal training data epochs are uniformly sampled. However, stochastic physiological and pathological fluctuations in EEG data characteristics and underlying brain states suggest that pre-ictal state dynamics may be more complex, and selection of pre-ictal training data segments to reflect this could improve algorithm performance.
We propose a semi-supervised technique to select pre-ictal training data most distinguishable from interictal EEG according to pre-specified data characteristics. The proposed method uses hierarchical clustering to identify optimal pre-ictal data epochs.
In this paper we compare the performance of a seizure forecasting algorithm with and without hierarchical clustering of pre-ictal periods in chronic iEEG recordings from six canines with naturally occurring epilepsy. Hierarchical clustering of training data improved results for Time In Warning (TIW) (0.18 vs. 0.23) and False Positive Rate (FPR) (0.5 vs. 0.59) when evaluated across all subjects (p<0.001, n=6). Results were mixed when evaluating TIW, FPR, and Sensitivity for individual dogs.
Hierarchical clustering is a helpful method for training data selection overall, but should be evaluated on a subject-wise basis.
The clustering method can be used to optimize results of forecasting towards sensitivity or TIW or FPR, and therefore can be useful for epilepsy management.
用于癫痫发作预测算法训练数据的发作前脑电图（EEG）时段的传统选择通常假定在癫痫发作之前存在连续的发作前脑状态。这是通过定义一个固定时长的发作前时间段来实现的，在癫痫发作前从此时间段中均匀采样发作前训练数据时段。然而，EEG数据特征和潜在脑状态中的随机生理和病理波动表明，发作前状态动态可能更为复杂，选择能够反映这一点的发作前训练数据片段可能会提高算法性能。
我们提出一种半监督技术，根据预先指定的数据特征选择与发作间期EEG最具区分性的发作前训练数据。所提出的方法使用层次聚类来识别最佳发作前数据时段。
在本文中，我们比较了在来自六只患有自然发生癫痫的犬的慢性颅内EEG记录中，对发作前时段进行层次聚类和不进行层次聚类时癫痫预测算法的性能。在对所有受试者进行评估时，训练数据的层次聚类改善了预警时间（TIW）（0.18对0.23）和误报率（FPR）（0.5对0.59）的结果（p<0.001，n = 6）。在评估个体犬的TIW、FPR和敏感性时，结果好坏参半。
总体而言，层次聚类是一种有助于训练数据选择的方法，但应在个体受试者基础上进行评估。
聚类方法可用于优化针对敏感性或TIW或FPR的预测结果，因此可用于癫痫管理。
