Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning

by   Flemming Kondrup, et al.
McGill University

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.


page 1

page 2

page 3

page 4


Challenges for Reinforcement Learning in Healthcare

Many healthcare decisions involve navigating through a multitude of trea...

Towards Safe Propofol Dosing during General Anesthesia Using Deep Offline Reinforcement Learning

Automated anesthesia promises to enable more precise and personalized an...

An Empirical Study of Representation Learning for Reinforcement Learning in Healthcare

Reinforcement Learning (RL) has recently been applied to sequential esti...

A Conservative Q-Learning approach for handling distribution shift in sepsis treatment strategies

Sepsis is a leading cause of mortality and its treatment is very expensi...

Pruning the Way to Reliable Policies: A Multi-Objective Deep Q-Learning Approach to Critical Care

Most medical treatment decisions are sequential in nature. Hence, there ...

Safely Bridging Offline and Online Reinforcement Learning

A key challenge to deploying reinforcement learning in practice is explo...

Reinforcement Learning For Survival, A Clinically Motivated Method For Critically Ill Patients

There has been considerable interest in leveraging RL and stochastic con...

Please sign up or login with your details

Forgot password? Click here to reset