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

Niranjani Prasad, Li-Fang Cheng, Corey Chivers, Michael Draugelis, Barbara E Engelhardt
Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence, PMLR R15:41-50, 2017.

Abstract

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

Cite this Paper

BibTeX
@InProceedings{pmlr-vR15-prasad17a, title = {A Reinforcement Learning Approach to Weaning of Mechanical Ventilation in Intensive Care Units}, author = {Prasad, Niranjani and Cheng, Li-Fang and Chivers, Corey and Draugelis, Michael and Engelhardt, Barbara E}, booktitle = {Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence}, pages = {41--50}, year = {2017}, editor = {Elidan, Gal and Kersting, Kristian}, volume = {R15}, series = {Proceedings of Machine Learning Research}, month = {11--15 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r15/main/assets/prasad17a/prasad17a.pdf}, url = {https://proceedings.mlr.press/r15/prasad17a.html}, abstract = {The management of invasive mechanical ventilation, and the regulation of sedation and analgesia during ventilation, constitutes a major part of the care of patients admitted to intensive care units. Both prolonged dependence on mechanical ventilation and premature extubation are associated with increased risk of complications and higher hospital costs, but clinical opinion on the best protocol for weaning patients off of a ventilator varies. This work aims to develop a decision support tool that uses available patient information to predict time-to-extubation readiness and to recommend a personalized regime of sedation dosage and ventilator support. To this end, we use off-policy reinforcement learning algorithms to determine the best action at a given patient state from sub-optimal historical ICU data. We compare treatment policies from fitted Q-iteration with extremely randomized trees and with feedforward neural networks, and demonstrate that the policies learnt show promise in recommending weaning protocols with improved outcomes, in terms of minimizing rates of reintubation and regulating physiological stability.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T A Reinforcement Learning Approach to Weaning of Mechanical Ventilation in Intensive Care Units %A Niranjani Prasad %A Li-Fang Cheng %A Corey Chivers %A Michael Draugelis %A Barbara E Engelhardt %B Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2017 %E Gal Elidan %E Kristian Kersting %F pmlr-vR15-prasad17a %I PMLR %P 41--50 %U https://proceedings.mlr.press/r15/prasad17a.html %V R15 %X The management of invasive mechanical ventilation, and the regulation of sedation and analgesia during ventilation, constitutes a major part of the care of patients admitted to intensive care units. Both prolonged dependence on mechanical ventilation and premature extubation are associated with increased risk of complications and higher hospital costs, but clinical opinion on the best protocol for weaning patients off of a ventilator varies. This work aims to develop a decision support tool that uses available patient information to predict time-to-extubation readiness and to recommend a personalized regime of sedation dosage and ventilator support. To this end, we use off-policy reinforcement learning algorithms to determine the best action at a given patient state from sub-optimal historical ICU data. We compare treatment policies from fitted Q-iteration with extremely randomized trees and with feedforward neural networks, and demonstrate that the policies learnt show promise in recommending weaning protocols with improved outcomes, in terms of minimizing rates of reintubation and regulating physiological stability. %Z Reissued by PMLR on 04 October 2026.
APA
Prasad, N., Cheng, L., Chivers, C., Draugelis, M. & Engelhardt, B.E.. (2017). A Reinforcement Learning Approach to Weaning of Mechanical Ventilation in Intensive Care Units. Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R15:41-50 Available from https://proceedings.mlr.press/r15/prasad17a.html. Reissued by PMLR on 04 October 2026.

Related Material