Optimal adaptive control of drug dosing using integral reinforcement learning.
Anesthesia administration
Drug dosing
Optimal adaptive control
Reinforcement learning
Journal
Mathematical biosciences
ISSN: 1879-3134
Titre abrégé: Math Biosci
Pays: United States
ID NLM: 0103146
Informations de publication
Date de publication:
03 2019
03 2019
Historique:
received:
20
10
2018
revised:
24
01
2019
accepted:
31
01
2019
pubmed:
9
2
2019
medline:
18
12
2019
entrez:
9
2
2019
Statut:
ppublish
Résumé
In this paper, a reinforcement learning (RL)-based optimal adaptive control approach is proposed for the continuous infusion of a sedative drug to maintain a required level of sedation. To illustrate the proposed method, we use the common anesthetic drug propofol used in intensive care units (ICUs). The proposed online integral reinforcement learning (IRL) algorithm is designed to provide optimal drug dosing for a given performance measure that iteratively updates the control solution with respect to the pharmacology of the patient while guaranteeing convergence to the optimal solution. Numerical results are presented using 10 simulated patients that demonstrate the efficacy of the proposed IRL-based controller.
Identifiants
pubmed: 30735696
pii: S0025-5564(18)30358-4
doi: 10.1016/j.mbs.2019.01.012
pii:
doi:
Substances chimiques
Anesthetics, Intravenous
0
Propofol
YI7VU623SF
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
131-142Informations de copyright
Copyright © 2019 Elsevier Inc. All rights reserved.