CAREER: Peripheral nerve recording, analysis, and modulation for neural communication and control

电子药品是生物电子学和神经技术领域的一个新研究领域，可能使1000多万美国患者受益。它的目标是制造出能够监测和调节神经活动的植入物，以治疗胃肠道疾病、糖尿病、癫痫、哮喘、关节炎、慢性疼痛、高血压和其他心脏疾病。实现电子药物的两个重大工程挑战是：(1)感知和分析神经信号，(2)定义和整合神经反馈以改善刺激结果。本项目旨在开发一种新颖的集成硬件和软件平台来克服这两个挑战。因此，未来的电疗可以基于神经反馈和生理反应来实现和优化。该项目还包括一个综合的教育和外展部分，以促进跨学科研究培训，并增加代表性不足的学生参与STEM学科。该项目将建立一种新的低噪声记录能力，并具有刺激功能与神经接口。它还将生成有价值的神经数据集，这些数据集对于开发深度学习算法来分析神经信号和支持自适应神经调节至关重要。硬件方面的新技术贡献将包括一个具有多种降噪技术的新周围神经记录器，以实现神经记录，以及一个新的冗余交叉火力刺激器，以最大限度地减少同时记录和刺激的刺激噪声。在软件方面，本研究提出了一种基于深度神经网络的录音降噪、神经信号检测和信息解码流程。该项目还将进行新颖的体内实验，以验证所提出的技术平台，并模拟在治疗心力衰竭方面的实际应用，作为电子药物的概念验证演示。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Electroceuticals is a new research area in bioelectronics and neurotechnologies that can potentially benefit more than 10 million American patients. It aims to create implants that can monitor and modulate nerve activity to treat gastrointestinal diseases, diabetes, epilepsy, asthma, arthritis, chronic pain, and hypertension and other heart conditions. Two significant engineering challenges to implement electroceuticals are (1) to sense and analyze nerve neural signals, and (2) to define and incorporate neural feedback to improve stimulation outcomes. This project aims to develop a novel integrated hardware and software platform to overcome these two challenges. Thus a future electroceutical therapy can be implemented and optimized based on neural feedback and physiological responses. This project also includes an integrated educational and outreach component to both foster interdisciplinary research training and to increase participation of underrepresented students in STEM disciplines.This project will establish a new low-noise recording capability with a stimulation function to interface with nerves. It will also generate valuable nerve datasets that will be critical for the development of deep learning algorithms to analyze neural signals and support adaptive neuromodulation. The new technical contributions from the hardware aspects will include a new peripheral nerve recorder with multiple noise reduction techniques to enable nerve recording, and a new redundant crossfire stimulator to minimize stimulation noise artifacts for simultaneous recording and stimulation. From the software aspect, this research proposes a deep neural network based flow to de-noise the recordings, detect neural signals, and decode information. This project will also perform novel in-vivo experiments to validate the proposed technology platform and to simulate a real application in treating heart failure as a proof-of-concept demonstration of electroceuticals.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.