Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104, USA.
Department of Neurology, Thomas Jefferson University, Philadelphia, PA 19107, USA.
Sensors (Basel). 2024 Mar 16;24(6):1902. doi: 10.3390/s24061902.
In this study, we developed a machine learning model for automated seizure detection using system identification techniques on EEG recordings. System identification builds mathematical models from a time series signal and uses a small number of parameters to represent the entirety of time domain signal epochs. Such parameters were used as features for the classifiers in our study. We analyzed 69 seizure and 55 non-seizure recordings and an additional 10 continuous recordings from Thomas Jefferson University Hospital, alongside a larger dataset from the CHB-MIT database. By dividing EEGs into epochs (1 s, 2 s, 5 s, and 10 s) and employing fifth-order state-space dynamic systems for feature extraction, we tested various classifiers, with the decision tree and 1 s epochs achieving the highest performance: 96.0% accuracy, 92.7% sensitivity, and 97.6% specificity based on the Jefferson dataset. Moreover, as the epoch length increased, the accuracy dropped to 94.9%, with a decrease in sensitivity to 91.5% and specificity to 96.7%. Accuracy for the CHB-MIT dataset was 94.1%, with 87.6% sensitivity and 97.5% specificity. The subject-specific cases showed improved results, with an average of 98.3% accuracy, 97.4% sensitivity, and 98.4% specificity. The average false detection rate per hour was 0.5 ± 0.28 in the 10 continuous EEG recordings. This study suggests that using a system identification technique, specifically, state-space modeling, combined with machine learning classifiers, such as decision trees, is an effective and efficient approach to automated seizure detection.
在这项研究中，我们使用系统辨识技术在 EEG 记录上开发了一种用于自动癫痫发作检测的机器学习模型。系统辨识从时间序列信号构建数学模型，并使用少量参数来表示整个时域信号的时间段。这些参数被用作我们研究中分类器的特征。我们分析了托马斯杰斐逊大学医院的 69 个癫痫发作和 55 个非癫痫发作记录以及另外 10 个连续记录，以及来自 CHB-MIT 数据库的更大数据集。通过将 EEG 分为时段（1 秒、2 秒、5 秒和 10 秒）并使用五阶状态空间动态系统进行特征提取，我们测试了各种分类器，其中决策树和 1 秒时段实现了最高性能：基于杰斐逊数据集的准确率为 96.0%，灵敏度为 92.7%，特异性为 97.6%。此外，随着时段长度的增加，准确率下降到 94.9%，灵敏度下降到 91.5%，特异性下降到 96.7%。对于 CHB-MIT 数据集，准确率为 94.1%，灵敏度为 87.6%，特异性为 97.5%。特定于主题的案例显示出了改进的结果，平均准确率为 98.3%，灵敏度为 97.4%，特异性为 98.4%。在 10 个连续 EEG 记录中，平均每小时的误报率为 0.5 ± 0.28。本研究表明，使用系统辨识技术，特别是状态空间建模，并结合机器学习分类器，如决策树，是一种有效和高效的自动癫痫发作检测方法。
