Institute of Neurology and Neuropsychology, Tbilisi, Georgia.
Epihunter, Hasselt, Belgium.
Epilepsia. 2023 Dec;64 Suppl 4:S40-S46. doi: 10.1111/epi.17200. Epub 2022 Mar 13.
Our primary goal was to measure the accuracy of fully automated absence seizure detection, using a wearable electroencephalographic (EEG) device. As a secondary goal, we also tested the feasibility of automated behavioral testing triggered by the automated detection.
We conducted a phase 3 clinical trial (NCT04615442), with a prospective, multicenter, blinded study design. The input was the one-channel EEG recorded with dry electrodes embedded into a wearable headband device connected to a smartphone. The seizure detection algorithm was developed using artificial intelligence (convolutional neural networks). During the study, the predefined algorithm, with predefined cutoff value, analyzed the EEG in real time. The gold standard was derived from expert evaluation of simultaneously recorded full-array video-EEGs. In addition, we evaluated the patients' responsiveness to the automated alarms on the smartphone, and we compared it with the behavioral changes observed in the clinical video-EEGs.
We recorded 102 consecutive patients (57 female, median age = 10 years) on suspicion of absence seizures. We recorded 364 absence seizures in 39 patients. Device deficiency was 4.67%, with a total recording time of 309 h. Average sensitivity per patient was 78.83% (95% confidence interval [CI] = 69.56%-88.11%), and median sensitivity was 92.90% (interquartile range [IQR] = 66.7%-100%). The average false detection rate was .53/h (95% CI = .32-.74). Most patients (n = 66, 64.71%) did not have any false alarms. The median F1 score per patient was .823 (IQR = .57-1). For the total recording duration, F1 score was .74. We assessed the feasibility of automated behavioral testing in 36 seizures; it correctly documented nonresponsiveness in 30 absence seizures, and responsiveness in six electrographic seizures.
Automated detection of absence seizures with a wearable device will improve seizure quantification and will promote assessment of patients in their home environment. Linking automated seizure detection to automated behavioral testing will provide valuable information from wearable devices.
我们的主要目标是使用可穿戴脑电图（EEG）设备来测量全自动失神发作检测的准确性。作为次要目标，我们还测试了由自动检测触发的自动行为测试的可行性。
我们进行了一项 3 期临床试验（NCT04615442），采用前瞻性、多中心、盲法研究设计。输入是使用嵌入到与智能手机连接的可穿戴头带设备中的干电极记录的单通道 EEG。使用人工智能（卷积神经网络）开发了癫痫发作检测算法。在研究过程中，使用预定义的算法和预定义的截止值实时分析 EEG。金标准来自同时记录的全阵列视频-EEG 的专家评估。此外，我们评估了患者对智能手机上自动警报的反应能力，并将其与临床视频-EEG 中观察到的行为变化进行了比较。
我们怀疑有失神发作的 102 例连续患者（57 例女性，中位年龄= 10 岁）接受了记录。在 39 名患者中记录了 364 次失神发作。设备缺陷率为 4.67%，总记录时间为 309 小时。每位患者的平均灵敏度为 78.83%（95%置信区间[CI] = 69.56%-88.11%），中位灵敏度为 92.90%（四分位距[IQR] = 66.7%-100%）。平均假阳性率为.53/h（95%CI =.32-.74）。大多数患者（n=66，64.71%）没有任何假警报。每位患者的中位数 F1 评分为.823（IQR =.57-1）。对于总记录时长，F1 评分为.74。我们评估了 36 次癫痫发作中自动行为测试的可行性；它正确记录了 30 次失神发作中的无反应性和 6 次电描记发作中的反应性。
使用可穿戴设备进行失神发作的自动检测将改善癫痫发作的定量，并促进患者在其家庭环境中的评估。将自动癫痫发作检测与自动行为测试相关联将从可穿戴设备提供有价值的信息。
