School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China.
Seizure. 2021 Oct;91:207-211. doi: 10.1016/j.seizure.2021.06.023. Epub 2021 Jun 29.
Seizure detection algorithms (SDAs) based on electroencephalography (EEG) have been described in previous studies, but the imbalanced data distribution of ictal and interictal states continue to pose a technical challenge. This study proposes a novel algorithm to address the imbalanced classification problem and improve seizure detection performance.
The proposed algorithm is designed based on hybrid sampling and a cost-sensitive (CS) classifier. Hybrid sampling resamples the imbalanced EEG data at data-level, and the CS classifier, which is used as an algorithm-level tool, reduces the overall misclassification cost of seizure detection. The synthetic minority oversampling technique and undersampling TomekLink technique are combined to reduce the imbalanced ratio between ictal and interictal states while retaining the generalization ability. Finally, CS support vector machine classifies the resampled EEG feature vectors, assigning different cost sensitive parameters to moderate the poor performance resulting from the imbalanced distribution problem.
The proposed algorithm improved the average sensitivity and AUC by 46.67% and 0.0482, respectively, compared with the original results without using the imbalanced EEG data processing (IEDP) technique. Experimental results showed that an average sensitivity and AUC of 86.34% and 0.9837, respectively, could be obtained across all cases. Finally, a performance evaluation showed that the proposed algorithm outperformed published methods in terms seizure detection.
A fusion algorithm combining data- and algorithm-level methods can achieve high sensitivity and AUC compared with existing IEDP methods. Thus, SDA performance can be improved, enabling their clinical use with EEG-based SMSs.
先前的研究已经描述了基于脑电图（EEG）的癫痫发作检测算法（SDAs），但发作和发作间期状态的不平衡数据分布仍然是一个技术挑战。本研究提出了一种新的算法来解决不平衡分类问题并提高癫痫发作检测性能。
所提出的算法是基于混合采样和代价敏感（CS）分类器设计的。混合采样在数据级对不平衡的 EEG 数据进行重采样，而作为算法级工具的 CS 分类器降低了癫痫发作检测的整体误分类成本。综合少数过采样技术和欠采样 Tomelink 技术结合使用，在保留泛化能力的同时降低发作和发作间期状态之间的不平衡比例。最后，CS 支持向量机对重采样的 EEG 特征向量进行分类，为平衡不平衡分布问题导致的性能不佳分配不同的代价敏感参数。
与不使用不平衡 EEG 数据处理（IEDP）技术的原始结果相比，所提出的算法分别将平均灵敏度和 AUC 提高了 46.67%和 0.0482。实验结果表明，所有病例的平均灵敏度和 AUC 分别可达 86.34%和 0.9837。最后，性能评估表明，所提出的算法在癫痫发作检测方面优于已发表的方法。
与现有的 IEDP 方法相比，结合数据级和算法级方法的融合算法可以实现更高的灵敏度和 AUC。因此，可以提高 SDA 的性能，使基于 EEG 的 SMS 能够在临床中使用。
