Department of Neurology, Charité-Universitätsmedizin Berlin, Berlin, Germany.
Berlin Institute of Health, Berlin, Germany.
Epilepsia. 2020 Dec;61(12):2653-2666. doi: 10.1111/epi.16719. Epub 2020 Oct 11.
Seizure forecasting may provide patients with timely warnings to adapt their daily activities and help clinicians deliver more objective, personalized treatments. Although recent work has convincingly demonstrated that seizure risk assessment is in principle possible, these early approaches relied largely on complex, often invasive setups including intracranial electrocorticography, implanted devices, and multichannel electroencephalography, and required patient-specific adaptation or learning to perform optimally, all of which limit translation to broad clinical application. To facilitate broader adaptation of seizure forecasting in clinical practice, noninvasive, easily applicable techniques that reliably assess seizure risk without much prior tuning are crucial. Wristbands that continuously record physiological parameters, including electrodermal activity, body temperature, blood volume pulse, and actigraphy, may afford monitoring of autonomous nervous system function and movement relevant for such a task, hence minimizing potential complications associated with invasive monitoring and avoiding stigma associated with bulky external monitoring devices on the head.
Here, we applied deep learning on multimodal wristband sensor data from 69 patients with epilepsy (total duration > 2311 hours, 452 seizures) to assess its capability to forecast seizures in a statistically significant way.
Using a leave-one-subject-out cross-validation approach, we identified better-than-chance predictability in 43% of the patients. Time-matched seizure surrogate data analyses indicated forecasting not to be driven simply by time of day or vigilance state. Prediction performance peaked when all sensor modalities were used, and did not differ between generalized and focal seizure types, but generally increased with the size of the training dataset, indicating potential further improvement with larger datasets in the future.
Collectively, these results show that statistically significant seizure risk assessments are feasible from easy-to-use, noninvasive wearable devices without the need of patient-specific training or parameter optimization.
癫痫发作预测可为患者提供及时预警，以调整日常活动，并帮助临床医生提供更客观、个性化的治疗。尽管最近的研究已经令人信服地证明了癫痫风险评估在理论上是可行的，但这些早期方法主要依赖于复杂的、通常是侵入性的设置，包括颅内脑电图、植入设备和多通道脑电图，并且需要针对患者进行特定的调整或学习才能达到最佳效果，所有这些都限制了其在广泛临床应用中的转化。为了促进癫痫发作预测在临床实践中的广泛应用，需要非侵入性、易于应用的技术，这些技术可以在无需大量预先调整的情况下可靠地评估癫痫发作风险。连续记录生理参数（包括皮肤电活动、体温、血流脉搏和动作）的腕带可以监测自主神经系统功能和与该任务相关的运动，从而最大限度地减少与侵入性监测相关的潜在并发症，并避免与头部笨重的外部监测设备相关的耻辱感。
在这里，我们应用深度学习方法对 69 名癫痫患者的多模态腕带传感器数据（总时长>2311 小时，452 次发作）进行分析，以评估其以统计学显著方式预测癫痫发作的能力。
使用单病例交叉验证方法，我们在 43%的患者中发现了优于随机的预测能力。与发作时间相匹配的替代数据分析表明，预测并不仅仅受时间或警觉状态的驱动。当使用所有传感器模式时，预测性能达到峰值，并且与全面性和局灶性发作类型无关，但通常随着训练数据集的增大而增加，这表明随着未来更大数据集的使用，预测性能可能会进一步提高。
总的来说，这些结果表明，从易于使用的非侵入性可穿戴设备中进行统计学上显著的癫痫风险评估是可行的，而无需患者特定的训练或参数优化。
