Bioelectronics Neurology and Engineering Laboratory, Department of Neurology, Mayo Clinic, Alfred 9-441C, 200 First Street SW, Rochester, MN 55905, United States of America.
School of Engineering, University of North Florida, Jacksonville, FL, United States of America.
J Neural Eng. 2021 Apr 8;18(5). doi: 10.1088/1741-2552/abef8a.
. The detection of seizures using wearable devices would improve epilepsy management, but reliable detection of seizures in an ambulatory environment remains challenging, and current studies lack concurrent validation of seizures using electroencephalography (EEG) data.. An adaptively trained long-short-term memory deep neural network was developed and trained using a modest number of seizure data sets from wrist-worn devices. Transfer learning was used to adapt a classifier that was initially trained on intracranial electroencephalography (iEEG) signals to facilitate classification of non-EEG physiological datasets comprising accelerometry, blood volume pulse, skin electrodermal activity, heart rate, and temperature signals. The algorithm's performance was assessed with and without pre-training on iEEG signals and transfer learning. To assess the performance of the seizure detection classifier using long-term ambulatory data, wearable devices were used for multiple months with an implanted neurostimulator capable of recording iEEG signals, which provided independent electrographic seizure detections that were reviewed by a board-certified epileptologist.. For 19 motor seizures from 10 in-hospital patients, the algorithm yielded a mean area under curve (AUC), a sensitivity, and an false alarm rate per day (FAR/day) of 0.98, 0.93, and 2.3, respectively. Additionally, for eight seizures with probable motor semiology from two ambulatory patients, the classifier achieved a mean AUC of 0.97 and an FAR of 2.45 events/day at a sensitivity of 0.9. For all seizure types in the ambulatory setting, the classifier had a mean AUC of 0.82 with a sensitivity of 0.47 and an FAR of 7.2 events/day.. The performance of the algorithm was evaluated using motor and non-motor seizures during in-hospital and ambulatory use. The classifier was able to detect multiple types of motor and non-motor seizures, but performed significantly better on motor seizures.
. 使用可穿戴设备检测癫痫发作可以改善癫痫管理，但在非卧床环境中可靠地检测癫痫发作仍然具有挑战性，并且目前的研究缺乏使用脑电图 (EEG) 数据对癫痫发作进行同步验证。. 开发了一种自适应训练的长短时记忆深度神经网络，并使用来自腕戴设备的少量癫痫数据集进行训练。迁移学习用于适应最初在颅内脑电图 (iEEG) 信号上训练的分类器，以促进对包含加速度计、血容量脉搏、皮肤电活动、心率和温度信号的非 EEG 生理数据集的分类。评估了在有无 iEEG 信号预训练和迁移学习的情况下算法的性能。为了使用长期的非卧床数据评估癫痫发作检测分类器的性能，使用可穿戴设备进行了多个月的监测，同时配备了能够记录 iEEG 信号的植入式神经刺激器，该刺激器提供了由 board-certified 癫痫专家审查的独立电描记癫痫发作检测。. 在 10 名住院患者的 19 例运动性癫痫发作中，该算法的平均曲线下面积 (AUC)、敏感性和每日误报率 (FAR/day) 分别为 0.98、0.93 和 2.3。此外，对于两名非卧床患者的 8 例具有可能运动半侧性的癫痫发作，分类器的 AUC 平均为 0.97，FAR 为 2.45 次/天，敏感性为 0.9。在非卧床环境中的所有癫痫发作类型中，分类器的 AUC 平均为 0.82，敏感性为 0.47，FAR 为 7.2 次/天。. 该算法的性能使用住院和非卧床期间的运动性和非运动性癫痫发作进行了评估。该分类器能够检测多种类型的运动性和非运动性癫痫发作，但对运动性癫痫发作的检测效果明显更好。
