Herbozo Contreras Luis Fernando, Truong Nhan Duy, Eshraghian Jason K, Xu Zhangyu, Huang Zhaojing, Bersani-Veroni Thomas Vincenzo, Aguilar Isabelle, Leung Wing Hang, Nikpour Armin, Kavehei Omid
School of Biomedical Engineering, The University of Sydney, Sydney, NSW 2006, Australia.
Sydney Nano Institute, The University of Sydney, Sydney, NSW 2006, Australia.
PNAS Nexus. 2024 Oct 30;3(11):pgae488. doi: 10.1093/pnasnexus/pgae488. eCollection 2024 Nov.
Neuromodulation techniques have emerged as promising approaches for treating a wide range of neurological disorders, precisely delivering electrical stimulation to modulate abnormal neuronal activity. While leveraging the unique capabilities of AI holds immense potential for responsive neurostimulation, it appears as an extremely challenging proposition where real-time (low-latency) processing, low-power consumption, and heat constraints are limiting factors. The use of sophisticated AI-driven models for personalized neurostimulation depends on the back-telemetry of data to external systems (e.g. cloud-based medical mesosystems and ecosystems). While this can be a solution, integrating continuous learning within implantable neuromodulation devices for several applications, such as seizure prediction in epilepsy, is an open question. We believe neuromorphic architectures hold an outstanding potential to open new avenues for sophisticated on-chip analysis of neural signals and AI-driven personalized treatments. With more than three orders of magnitude reduction in the total data required for data processing and feature extraction, the high power- and memory-efficiency of neuromorphic computing to hardware-firmware co-design can be considered as solution-in-the-making to resource-constraint implantable neuromodulation systems. This perspective introduces the concept of , a new breed of closed-loop responsive feedback system. It highlights its potential to revolutionize implantable brain-machine microsystems for patient-specific treatment.
神经调节技术已成为治疗多种神经系统疾病的有前景的方法，可精确地传递电刺激以调节异常的神经元活动。虽然利用人工智能的独特能力在响应性神经刺激方面具有巨大潜力，但在实时（低延迟）处理、低功耗和热限制等限制因素的情况下，这似乎是一个极具挑战性的提议。使用复杂的人工智能驱动模型进行个性化神经刺激依赖于将数据反向遥测到外部系统（例如基于云的医疗中间系统和生态系统）。虽然这可能是一种解决方案，但在植入式神经调节设备中集成持续学习以用于多种应用，如癫痫发作预测，仍是一个悬而未决的问题。我们认为，神经形态架构具有巨大潜力，可为神经信号的复杂片上分析和人工智能驱动的个性化治疗开辟新途径。由于数据处理和特征提取所需的总数据量减少了三个多数量级，神经形态计算在硬件 - 固件协同设计方面的高功率和内存效率可被视为资源受限的植入式神经调节系统的一种正在形成的解决方案。这一观点引入了一种新型闭环响应反馈系统的概念。它突出了其变革用于患者特异性治疗的植入式脑机微系统的潜力。
