Representation and Reinforcement Learning for Personalized Glycemic Control in Septic Patients

By Wei-Hung Weng, Mingwu Gao, Ze He, Susu Yan, Peter Szolovits. 2017

60 citations recorded by the source corpus.

Glycemic control is essential for critical care. However, it is a challenging task because there has been no study on personalized optimal strategies for glycemic control. This work aims to learn personalized optimal glycemic trajectories for severely ill septic patients by learning data-driven policies to identify optimal targeted blood glucose levels as a reference for clinicians. We encoded patient states using a sparse autoencoder and adopted a reinforcement learning paradigm using policy iteration to learn the optimal policy from data. We also estimated the expected return following the policy learned from the recorded glycemic trajectories, which yielded a function indicating the relationship between real blood glucose values and 90-day mortality rates. This suggests that the learned optimal policy could reduce the patients' estimated 90-day mortality rate by 6.3%, from 31% to 24.7%. The result demonstrates that reinforcement learning with appropriate patient state encoding can potentially provide optimal glycemic trajectories and allow clinicians to design a personalized strategy for glycemic control in septic patients.

Subfields: Endocrinology, Diabetes and Metabolism, Epidemiology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Endocrinology, Diabetes and Metabolism

In Epidemiology

Citations in the corpus

Reinforcement Learning in Healthcare: A Survey (2019, neutral): “[204] PI N/A N/A MIMIC-III Learning the optimal targeted blood glucose levels for sepsis patients Cytokine mediation Petersen et al.”
Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation (2018, methodology): “Recently, some studies employ deep RL to solve the DTR problem based on large scale EHRs [26, 27, 38].”
Incorporating causal factors into reinforcement learning for dynamic treatment regimes in HIV (2019, background): “Reinforcement learning (RL) [1] has achieved tremendous achievements in solving complex sequential decision making problems in various health care domains, such as treatment in HIV [2], cancer [3], diabetics [4], schizophrenia [5], and sepsis [6].”
Dynamic Measurement Scheduling for Adverse Event Forecasting using Deep RL (2018, methodology): “Similarly, Kotecha et al. (2017) shows that the cost of ordering lab tests can be signiﬁcantly reduced without increasing in mortality or re-admission rates in cardiac and surgical ICU.”
Inverse reinforcement learning for intelligent mechanical ventilation and sedative dosing in intensive care units (2019, methodology): “Background Emerging in recent years as a powerful trend and paradigm in machine learning, reinforcement learning (RL) [1] has achieved tremendous achievements in solving complex sequential decision making problems in various health care domains, including treatment in HIV [2], cancer [3], diabetics ”
Deep Reinforcement Learning for Closed-Loop Blood Glucose Control (2020, background): “Examples include matching patients to treatment in the management of sepsis (Weng et al., 2017; Komorowski et al., 2018) and mechanical ventilation (Prasad et al., 2017).”