Medical Physics & Biomedical Engineering Department, School of Medicine, Tehran University of Medical Sciences., Tehran, Iran.
Comput Methods Programs Biomed. 2017 Jul;145:11-22. doi: 10.1016/j.cmpb.2017.04.001. Epub 2017 Apr 6.
Epilepsy is a neurological disorder that causes recurrent and abrupt seizures which makes the patients insecure. Predicting seizures can reduce the burdens of this disorder.
A new approach in seizure prediction is presented that includes a novel technique in feature extraction from EEG. The algorithm firsts creates an embedding space from EEG time series. Then it takes samples with most of the information using an optimized and data specific Poincare plane. In order to quantify small dynamics on the Poincare plane, based on the order of locations of Poincaré samples in the sequence, 64 fuzzy rules in each channel are defined. Features are extracted based on the frequency distribution of these fuzzy rules in each minute. Then features with higher variance are selected as ictal features and again reduced using PCA. Finally, in order to evaluate how these innovative features can increase the performance of the seizure prediction algorithm, the transition from interictal to preictal state is scored utilizing SVM.
The algorithm is tested on 460 h of EEG from 19 patients of Freiburg dataset who had at least 3 seizures. Considering maximum Seizure Prediction Horizon of 42 minutes, average sensitivity was 91.8 - 96.6% and average false prediction rate was 0.05 - 0.08/h.
The presented algorithm shows a better performance and more robustness compare to most of existing methods, and shows power in extracting optimal features from EEG.
癫痫是一种导致反复、突然发作的神经系统疾病，使患者感到不安。预测癫痫发作可以减轻这种疾病的负担。
提出了一种新的癫痫预测方法，包括从 EEG 中提取特征的新方法。该算法首先从 EEG 时间序列创建一个嵌入空间。然后，它使用优化和特定于数据的 Poincaré 平面来获取具有大部分信息的样本。为了量化 Poincaré 平面上的小动态，根据 Poincaré 样本在序列中的位置顺序，在每个通道中定义 64 条模糊规则。基于每个分钟内这些模糊规则的频率分布提取特征。然后选择具有更高方差的特征作为发作特征，并再次使用 PCA 进行降维。最后，为了评估这些创新特征如何提高癫痫预测算法的性能，利用 SVM 对从发作间期到发作前期的转变进行评分。
该算法在来自弗莱堡数据集的 19 名至少有 3 次发作的患者的 460 小时 EEG 上进行了测试。考虑到最大癫痫预测时间为 42 分钟，平均灵敏度为 91.8%至 96.6%，平均假阳性率为 0.05%至 0.08/h。
与大多数现有方法相比，提出的算法具有更好的性能和更强的稳健性，并展示了从 EEG 中提取最佳特征的能力。
