AUTHOR=Siddique Md Abu Bakr , Zhang Yan , An Hongyu 

TITLE=Monitoring time domain characteristics of Parkinson’s disease using 3D memristive neuromorphic system

JOURNAL=Frontiers in Computational Neuroscience

VOLUME=Volume 17 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2023.1274575

DOI=10.3389/fncom.2023.1274575

ISSN=1662-5188

ABSTRACT=Parkinson's disease (PD) is a neurodegenerative disorder affecting millions of patients. Closed-Loop Deep Brain Stimulation (CL-DBS) is a therapy that can alleviate the symptoms of PD. The CL-DBS system consists of an electrode sending electrical stimulation signals to a specific region of the brain and a battery-powered stimulator implanted in the chest. The electrical stimuli need to be adjusted in real-time in accordance with the state of PD symptoms. Thus, fast and accurate monitoring of PD symptoms is critical functionality for CL-DBS systems. However, the current CL-DBS techniques suffer from high computational demands that are not feasible for implanted and wearable medical devices. In this paper, we develop a neuromorphic PD symptom detector using memristive threedimensional (3D) circuits. The beta oscillation at the subthalamic nucleus (STN) is used as a biomarker of PD symptoms. In addition, the effect of deep brain stimulation (DBS) signals on this asymmetry is studied. Simulation results show that our neuromorphic PD detector implemented of 8-layer spiking LSTM (S-LSTM) is proficient at recognizing PD symptoms, with a training accuracy of 99.74% and a validation accuracy of 99.52% for 75%-25% data splits. The improvement of our neuromorphic CL-DBS detector is evaluated with NeuroSIM. The chip area, latency, energy, and power usage of our CL-DBS detector are reduced by 47.4%, 66.63%, 65.6%, and 67.5% for monolithic 3D-designed chips and by 44.8%, 64.75%, 65.28%, and 67.7% for heterogeneous 3Ddesigned chips using memristive synapses to replace the traditional Static Random Access Memory (SRAM).