English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The management of invasive mechanical ventilation, and the regulation ofsedation and analgesia during ventilation, constitutes a major part of the careof patients admitted to intensive care units. Both prolonged dependence onmechanical ventilation and premature extubation are associated with increasedrisk of complications and higher hospital costs, but clinical opinion on thebest protocol for weaning patients off of a ventilator varies. This work aimsto develop a decision support tool that uses available patient information topredict time-to-extubation readiness and to recommend a personalized regime ofsedation dosage and ventilator support. To this end, we use off-policyreinforcement learning algorithms to determine the best action at a givenpatient state from sub-optimal historical ICU data. We compare treatmentpolicies from fitted Q-iteration with extremely randomized trees and withfeedforward neural networks, and demonstrate that the policies learnt showpromise in recommending weaning protocols with improved outcomes, in terms ofminimizing rates of reintubation and regulating physiological stability.

A Reinforcement Learning Approach to Weaning of Mechanical Ventilation in Intensive Care Units