Reliable Seizure Prediction Using Physiological Signals and Machine Learning

使用生理信号和机器学习进行可靠的癫痫发作预测

基本信息

批准号：
10629373
负责人：
Gregory A Worrell
金额：
$ 58.68万
依托单位：
MAYO CLINIC ROCHESTER
依托单位国家：
美国
项目类别：
财政年份：
2022
资助国家：
美国
起止时间：
2022-06-01 至 2027-05-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10629373
关键词：
Anticonvulsants Automobile Driving Bilateral Biological Markers Body Temperature Brain Canis familiaris Chronic Classification Clinical Data Analytics Development Device Designs Devices Dose Drug Side Effects Effectiveness Electric Stimulation Electrical Stimulation of the Brain Electrocardiogram Electroencephalography Electrophysiology (science)Epilepsy Event Evoked Potentials Focal Seizure Goals Grant Hippocampus Human Immune Sera Immunologic Factors Immunologic Markers Immunologics Implant Implantable Injection/Infusion Ports Incidence Individual Injury Intelligence Investigation Life Machine Learning Modeling Morbidity - disease rate Neural Network Simulation Partial Epilepsies Patients Pattern Performance Persons Physiological Probability Psychological Impact Research Risk Sampling Seizures Series Signal Transduction Stream Temperature Temperature Sense Therapy trial Time Work circadian convolutional neural network deep learning electric impedance epileptiform implantable device improved learning strategy machine learning method machine learning model multimodal data multimodality pharmacologic prevent prospective psychologic response side effect support vector machine targeted treatment

项目摘要

For most individuals living with epilepsy, seizures are relatively infrequent events occupying a small fraction of their life. Despite spending as little as 0.01% of their lives having seizures (typically only minutes per month), people with epilepsy take anti-seizure drugs (ASD) daily, suffer ASD related side effects, and spend their lives dreading when the next seizure will strike. The apparent randomness of seizures is associated with significant psychological consequences. In addition, despite daily ASD, approximately 1/3 of patients continue to have seizures. We hypothesize that epilepsy can be more effectively treated, both the seizures and their psychological impact, by providing patients with real-time seizure forecasting. There is strong evidence that focal epilepsy is associated with a variable seizure risk that may enable adaptive therapy targeting periods of high seizure probability. Periods of low seizure probability could require lower ASD doses, reducing exposure and side effects. We propose that high seizure probability states will respond to adaptive electrical brain stimulation (aEBS). In addition, patients could alter their activities during periods of high seizure probability to reduce injury and manage their ASD and activities. The hypotheses driving this proposal are that 1.) seizures can be prevented (reduced incidence) by targeted EBS therapy during the pre-ictal state 2.) seizures are not random events, and that brain states associated with low and high seizure probability can be reliably classified using machine learning methods applied to physiologic signals and used to adaptively change EBS parameters. 3.) Furthermore, we propose forecasting can be improved using multi-modal features beyond passive iEEG recordings, including active brain probing with electrical stimulation (impedance & evoked potentials), core temperature, ECG and serum immunological markers. Goal: Develop reliable seizure forecasting (>90% sensitivity) with few false positives (<1% time in warning) and demonstrate modulation of seizure risk and reduction of focal seizures using aEBS.

对于大多数癫痫患者来说，癫痫发作是相对罕见的事件，只占一小部分。他们的生活。尽管他们一生中癫痫发作的时间只有 0.01%（通常每月只有几分钟），癫痫患者每天服用抗癫痫药物 (ASD)，遭受 ASD 相关副作用，并度过一生担心下一次癫痫发作的时间。癫痫发作的明显随机性与显着相关心理后果。此外，尽管每天都有自闭症谱系障碍，但大约 1/3 的患者仍然患有自闭症谱系障碍 (ASD) 癫痫发作。我们假设癫痫可以得到更有效的治疗，包括癫痫发作及其发作通过为患者提供实时癫痫发作预测来减轻心理影响。有强有力的证据表明局灶性癫痫与可变的癫痫发作风险相关，这可能使适应性针对癫痫发作高概率期的治疗。癫痫发作概率低的时期可能需要较低的 ASD 剂量，减少暴露和副作用。我们建议高癫痫发作概率国家将做出反应适应性脑电刺激（aEBS）。此外，患者可以在治疗期间改变他们的活动。高癫痫发作概率，可减少伤害并管理他们的 ASD 和活动。推动该提议的假设是 1.) 可以通过有针对性的预防（减少发病率）癫痫发作发作前状态期间的 EBS 治疗 2.) 癫痫发作不是随机事件，并且与以下因素相关的大脑状态可以使用机器学习方法对低和高癫痫发作概率进行可靠分类生理信号并用于自适应地改变 EBS 参数。 3.) 此外，我们建议预测可以使用被动 iEEG 记录之外的多模式功能进行改进，包括主动脑探测具有电刺激（阻抗和诱发电位）、核心温度、心电图和血清免疫学标记。目标：开发可靠的癫痫发作预测（>90% 灵敏度），几乎没有误报（<1% 时间）警告）并展示使用 aEBS 调节癫痫风险和减少局灶性癫痫发作。

项目成果

期刊论文数量（19）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

SVM-Based System for Prediction of Epileptic Seizures From iEEG Signal.

DOI：
10.1109/tbme.2016.2586475
发表时间：
2017-05
期刊：
IEEE transactions on bio-medical engineering
影响因子：
0
作者：
Shiao HT;Cherkassky V;Lee J;Veber B;Patterson EE;Brinkmann BH;Worrell GA
通讯作者：
Worrell GA

Intracranial electrophysiological recordings from the human brain during memory tasks with pupillometry.

DOI：
10.1038/s41597-021-01099-z
发表时间：
2022-01-13
期刊：
Scientific data
影响因子：
9.8
作者：
Cimbalnik J;Dolezal J;Topçu Ç;Lech M;Marks VS;Joseph B;Dobias M;Van Gompel J;Worrell G;Kucewicz M
通讯作者：
Kucewicz M

Identifying seizure risk factors: A comparison of sleep, weather, and temporal features using a Bayesian forecast.

DOI：
10.1111/epi.16785
发表时间：
2021-03
期刊：
Epilepsia
影响因子：
5.6
作者：
Payne DE;Dell KL;Karoly PJ;Kremen V;Gerla V;Kuhlmann L;Worrell GA;Cook MJ;Grayden DB;Freestone DR
通讯作者：
Freestone DR

Seizure Forecasting and the Preictal State in Canine Epilepsy.