Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning
Open Access
- 26 June 2023
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (13) , 15696-15702
Abstract
Mechanical ventilation is a key form of life support for patients with pulmonary impairment. Healthcare workers are required to continuously adjust ventilator settings for each patient, a challenging and time consuming task. Hence, it would be beneficial to develop an automated decision support tool to optimize ventilation treatment. We present DeepVent, a Conservative Q-Learning (CQL) based offline Deep Reinforcement Learning (DRL) agent that learns to predict the optimal ventilator parameters for a patient to promote 90 day survival. We design a clinically relevant intermediate reward that encourages continuous improvement of the patient vitals as well as addresses the challenge of sparse reward in RL. We find that DeepVent recommends ventilation parameters within safe ranges, as outlined in recent clinical trials. The CQL algorithm offers additional safety by mitigating the overestimation of the value estimates of out-of-distribution states/actions. We evaluate our agent using Fitted Q Evaluation (FQE) and demonstrate that it outperforms physicians from the MIMIC-III dataset.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Reinforcement Learning in Healthcare: A SurveyACM Computing Surveys, 2021
- Development and validation of a reinforcement learning algorithm to dynamically optimize mechanical ventilation in critical carenpj Digital Medicine, 2021
- A Deep Deterministic Policy Gradient Approach to Medication Dosing and Surveillance in the ICU2018
- Mechanical Ventilation: State of the ArtMayo Clinic Proceedings, 2017
- Comparative Effects of Volutrauma and Atelectrauma on Lung Inflammation in Experimental Acute Respiratory Distress SyndromeCritical Care Medicine, 2016
- MIMIC-III, a freely accessible critical care databaseScientific Data, 2016
- A decision support system to determine optimal ventilator settingsBMC Medical Informatics and Decision Making, 2014
- Ventilatory strategies and supportive care in acute respiratory distress syndromeInfluenza and Other Respiratory Viruses, 2013
- Initial ventilator settings for critically ill patientsCritical Care, 2013
- APACHE II-A Severity of Disease Classification SystemCritical Care Medicine, 1986