ERI: Epilepsy in Women: Monitoring and Management using Noninvasive Wearable Sensors

该奖项的全部或部分资金来自《2021年美国救援计划法案》(公法117-2)。世界上近1%的人口患有癫痫，其中一半是女性，她们的癫痫发作和抗癫痫药物会影响她们的月经周期、怀孕、更年期和骨骼健康。女性的荷尔蒙变化会影响癫痫发作的风险，并与可穿戴设备测量的生物信号的变化有关，如温度和心率变异性，并可能与癫痫发作模式有关。这一工程研究启动(ERI)奖的重点是通过创建预测算法来改善癫痫女性患者的生活质量，该算法可以根据预测的癫痫风险来帮助管理抗癫痫药物的剂量。拟议的研究将为不同的本科生和研究生群体提供培训机会，重点将是让女性学生参与研究。这项拟议的研究通过分析非侵入性可穿戴设备记录的生理信号，调查了与月经周期相关的荷尔蒙变化及其对女性癫痫风险的影响。使用侵入性脑电(EEG)设备的数据已经验证了提前几分钟到几个小时预测癫痫发作的能力；然而，使用非侵入性可穿戴设备来做到这一点仍然是一个挑战。如果在设计中考虑到与荷尔蒙变化相关的癫痫发作风险，以减少错误警报并提高敏感度，那么用于癫痫发作预测的机器学习算法的性能将显著提高。设计一种可靠的癫痫发作预测算法将允许患者使用较低的基线剂量的药物，并在癫痫发作风险较高的时候增加剂量。此外，调查影响癫痫发作风险的性别参数并将其应用于癫痫的管理将显著提高癫痫女性的生活质量。这一奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2). Almost 1% of the world's population lives with epilepsy and half of them are women, whose seizures and antiseizure medicines affect their menstrual cycle, pregnancy, menopause, and bone health. Hormonal changes in women can influence seizure risk and are associated with changes in biological signals measured by wearable devices, such as temperature and heart rate variability, and can be linked to seizure patterns. This Engineering Research Initiation (ERI) award focuses on improving the quality of life of women with epilepsy by creating forecasting algorithms that can help manage dosing of antiseizure medication based on predicted seizure risk. The proposed research will provide training opportunities for a diverse group of undergraduate and graduate students and the focus will be to engage female students in research. The proposed research investigates hormonal changes associated with the menstrual cycle and their effects on seizure risk in women by analyzing physiological signals recorded with non-invasive wearable devices. The ability to forecast seizures, minutes to hours in advance has already been verified using data from invasive EEG (Electroencephalography) devices; however, it is still a challenge to do this using noninvasive wearable devices. The performance of the machine learning algorithms for seizure forecasting could be significantly improved if the seizure risk associated with hormonal changes be considered in the design to mitigate false alarms and improve sensitivity. Designing a reliable seizure forecasting algorithm will allow patients to use lower baseline doses of medications, with escalated doses given during times of high seizure risk. Additionally, investigating the gender-specific parameters affecting seizure risk and implementing them in managing epilepsy will lead to significant improvements in quality of life for women with epilepsy.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.