Deep reinforcement learning-based propofol infusion control for anesthesia: A feasibility study with a 3000-subject dataset

In this work, we present a deep reinforcement learning-based approach as a baseline system for autonomous propofol infusion control. Specifically, design an environment for simulating the possible conditions of a target patient based on input demographic data and design our reinforcement learning mo...

Full description

Saved in:
Bibliographic Details
Published in:Computers in biology and medicine 2023-04, Vol.156, p.106739-106739, Article 106739
Main Authors: Yun, Won Joon, Shin, MyungJae, Jung, Soyi, Ko, JeongGil, Lee, Hyung-Chul, Kim, Joongheon
Format: Article
Language:English
Subjects:
Analgesics
Anesthesia
Anesthesia, Intravenous - methods
Anesthetics, Intravenous
Automated drug control computing
Automation
Biology
Computer engineering
Computers
Control algorithms
Decision making
Deep learning
Deep reinforcement learning
Design
Drug dosages
Electroencephalography
Feasibility Studies
General anesthesia
Healthcare IT
Humans
Hypnosis
Learning
Manual control
Medical personnel
Medicine
Model-based systems
Neural networks
Patients
Pharmacodynamics
Pharmacokinetics
Piperidines
Propofol
Reinforcement
Remifentanil
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this work, we present a deep reinforcement learning-based approach as a baseline system for autonomous propofol infusion control. Specifically, design an environment for simulating the possible conditions of a target patient based on input demographic data and design our reinforcement learning model-based system so that it effectively makes predictions on the proper level of propofol infusion to maintain stable anesthesia even under dynamic conditions that can affect the decision-making process, such as the manual control of remifentanil by anesthesiologists and the varying patient conditions under anesthesia. Through an extensive set of evaluations using patient data from 3000 subjects, we show that the proposed method results in stabilization in the anesthesia state, by managing the bispectral index (BIS) and effect-site concentration for a patient showing varying conditions.
ISSN:0010-4825
1879-0534
DOI:10.1016/j.compbiomed.2023.106739