An Adaptive Neuro-fuzzy Strategy in Closed-loop Control of Anesthesia

TL;DR

This paper introduces an adaptive neuro-fuzzy control system for anesthesia that dynamically adjusts drug infusion rates, effectively managing variability and disturbances to maintain desired anesthesia levels in real-time.

Contribution

It presents a novel neuro-fuzzy framework with reinforcement learning for improved closed-loop anesthesia control, addressing variability and uncertainties.

Findings

Controller effectively manages inter-patient variability.

It prevents overdose and underdose during anesthesia.

Achieves desired bispectral index within 2-4 minutes.

Abstract

This paper proposes an adaptive neuro-fuzzy framework to improve drug infusion rate in closed-loop control of anesthesia. The proposed controller provides a sub-optimal propofol administration rate as input to reach the desired bispectral index, which is the output of the system, in both induction and maintenance phases. In this controller, a critic agent assesses the plant output and produces a reinforcement signal to adapt the controller parameters and minimize the propofol administration rate. The controller is applied to a conventional pharmacokinetic-pharmacodynamics model of anesthesia to evaluate its applicability in closed loop-control of anesthesia. To simulate the designed controller, physiological parameters of 12 patients are used in the mathematical model. The simulation results show that the proposed controller can overcome current challenges in the closed-loop control of anesthesia like inter patient variability, model uncertainties and surgical disturbances without overdose or underdose in a time range of 2 to 4 minutes. Analytical comparison of results shows the strength of the controller in closed-loop control of anesthesia.