Personalized Contingent Neurostimulation for Epilepsy by Machine Learning in Organic Brain Interfaces

通过有机脑接口中的机器学习对癫痫进行个性化偶然神经刺激

• 批准号: 549625-2020
• 负责人: Genov, RomanR
• 金额: $ 8.92万
• 依托单位: University of Toronto
• 依托单位国家: 加拿大
• 项目类别: Collaborative Health Research Projects
• 财政年份: 2022
• 资助国家: 加拿大
• 起止时间: 2022-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=751693
• 关键词: Personalized; Contingent; Neurostimulation; Epilepsy; Machine

Epilepsy is a chronic, neurological condition characterized by unpredictable, disablingseizures. This devastating disorder increases mortality by 4 times and depression by 2 timespopulation rates. Unfortunately, epilepsy is extremely common, affecting 1 in 100 people, andin 33% of cases, medications do not prevent seizures. An emerging technology to aid suchpatients with drug-resistant epilepsy is contingent neurostimulation devices. These devicesare implanted in a patient so that they can detect epileptiform activity and electrically stimulatethe nervous system to prevent/abort seizures. Recently, two commercial contingentneurostimulators have been approved for treating epilepsy. These devices have provensuccessful at reducing seizure activity, however their efficacy is low. In particular, they arevery unlikely to produce seizure freedom, which is necessary to restore patient independenceand quality of life.The primary reasons why existing neurostimulation devices have had such limited successare that: (a) they use rudimentary (sparse and large) electrodes that poorly interface with thebrain and (b) they are extremely simplistic in their seizure detection and abortion capabilitiesdue to the use of basic electronics as constrained by energy limitations of an implant. Wepropose to combine (a) the far superior brain-interfacing electrode technology from ourpartner Panaxium and (b) our energy-efficient state-of-the-art implantable electronic circuitsthat employ artificial intelligence for optimal seizure prediction and prevention - to greatlyimprove the seizure-freedom efficacy of the neuromodulation therapy for intractable epilepsy.Our team is uniquely well qualified for this project. It is led by an expert in low-powerbiomedical and computational electronics (Genov), an epilepsy neurosurgeon and an expertin brain neurophysiology (Valiante), and Panaxiums Technology Commercialization Leaderand a 20-year industry veteran (Weinroth).

癫痫是一种慢性神经系统疾病，其特征是不可预测的致残性癫痫发作。这种毁灭性的疾病使死亡率增加了4倍，使抑郁症增加了2倍。不幸的是，癫痫非常常见，每100人中就有1人受到影响，在33%的病例中，药物不能预防癫痫发作。一种新兴的技术，以帮助这样的病人与耐药性癫痫是偶然的神经刺激装置。这些装置被植入病人体内，这样它们就可以检测癫痫样活动，并电刺激神经系统以防止/中止癫痫发作。最近，两种商业应急神经刺激器已被批准用于治疗癫痫。这些装置已经证明在减少癫痫发作活动方面是成功的，但是它们的功效很低。特别是，它们不太可能产生癫痫发作自由，而癫痫发作自由是恢复患者独立性和生活质量所必需的。现有神经刺激设备成功有限的主要原因是：（一）使用基本（稀疏和大）电极与大脑的接口很差，以及（B）它们在癫痫发作检测和流产能力方面是极其简单的，这是由于使用基本的电子器件，这受到植入物的能量限制的限制。我们建议将联合收割机（a）我们的合作伙伴Panaxium的上级脑接口电极技术和（B）我们的节能最先进的植入式电子电路结合起来，这些电路采用人工智能进行最佳的癫痫预测和预防-以极大地提高神经调节疗法治疗顽固性癫痫的无并发症疗效。我们的团队是唯一能够胜任此项目的团队。它由低功耗生物医学和计算电子学专家（Genov）、癫痫神经外科医生和脑神经生理学专家（Valiante）以及Panaxiums技术商业化负责人和20年行业资深人士（Weinroth）领导。