Abstract
Aiming at the problem that the Proportional-Integral-Derivative (PID) control strategy needs to readjust controller parameters for different Parkinson's disease (PD) states. This work proposes an improved control strategy that considers an artificial neural network control scheme. A backpropagation neural network (BPNN) controller is designed to solve the above problem and further to improve the performance of the closed-loop control strategy. The training data set of the BPNN controller is obtained by controlling eight different PD states (PD a - PD h ) by the PID controller and the BPNN controller is trained by the training data set to obtain a set of optimal weights. By modulating other different PD states (e.g. PD1 - PD3), the effectiveness of the PID-structure controller and BPNN controller are compared. We find that the BPNN controller can modulate different PD states without changing the controller parameters and reduce energy expenditure by 58.26%. This work is helpful for the design of more effective closed-loop deep brain stimulation (DBS) systems for clinical applications and provides a framework for the further development of closed-loop DBS.
Highlights
Parkinson’s disease (PD) is a neurodegenerative disease and its symptoms can be complicated to manage
In the closed-loop control system block diagram shown in Fig. 2, the controller is PID controller or backpropagation neural network (BPNN) controller, deep brain stimulation (DBS) is equivalent to an actuator, basal ganglia-thalamo-cortical network acts as the controlled object and yPY is the controlled variable. yPY is the average membrane potential signal of the PY neurons in the closed-loop DBS control system. yPY is the average membrane potential of the PY neurons in the normal state and used as the expected signal, u is the controller output signal, and z is the stimulus signal added to the controlled object after modulation by DBS, and e is the error between yPY and yPY
In order to remove the influence of the initial conditions on the simulation results, the simulation data of the first 1000ms was removed from the quantitative calculations, and all the results are averaged from 100 independent runs
Summary
Parkinson’s disease (PD) is a neurodegenerative disease and its symptoms can be complicated to manage. Closed-loop DBS can operate on-demand and adjust the stimulation parameters in real time according to changes of the patient’s physiological signals [14]–[16], which can effectively overcome the shortcomings of current open-loop DBS methods. The closed-loop DBS system is able to adjust the stimulation parameters in real time based on changes in the patients’ clinical states and to apply specific stimuli parameters according to the needs of different patients [17], [18]. Ye et al used artifcial neural networks to determine weights to scale the controller parameters Their results demonstrated that Zishenpingchan granules reduced the occurrence of motor complications, and were useful for mitigating dyskinesia and non-motor symptoms of PD [24].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
