Article

Offline Reinforcement Learning for Out-of-Distribution ICU Sepsis Decision Support

2026-08-25

Abstract excerpt

Offline reinforcement learning (RL) provides a promising framework for learning and evaluating treatment policies from logged clinical data, particularly in sequential decision-making settings where prospective exploration would be unsafe. In ICU sepsis management, however, it remains unclear whether offline RL policies retain stable behavior under increasingly severe out-of-distribution (OOD) patient cohorts. In...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 5fe08e10-a933-5f77-8ab2-da887f8caaf1
DOI: 10.64898/2026.08.22.26361090

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Offline Reinforcement Learning for Out-of-Distribution ICU Sepsis Decision SupportDOI 10.64898/2026.08.22.26361090Read

Deep Reinforcement Learning for Personalized Clinical Decision SupportSemantic proximity Read

Learning to Treat Hypotensive Episodes in Sepsis Patients Using a Counterfactual Reasoning FrameworkSemantic proximity Read

Cyber-Physical Orchestration of Emergency Department Services Through a Bidirectional Digital Twin and a Deep Reinforcement Learning Agent: Architectural Design, In SilicoValidation, and Critical Analysis of Performance Under Demand StressSemantic proximity Read

A Simulation-Based Validation Framework for Uncertainty-Aware Clinical Triage: Conformal Prediction and Ensemble Learning Applied to a Synthetic ICU Benchmark CohortSemantic proximity Read

Fair Reinforcement Learning for Maternal Sepsis TreatmentSemantic proximity Read

abx_amr_simulator: A simulation environment for antibiotic prescribing policy optimization under antimicrobial resistanceSemantic proximity Read

Machine learning approaches to optimise the management of patients with sepsisSemantic proximity Read

Blood pressure response index trajectories identify distinct hemodynamic phenotypes and predict mortality in septic shock: a two-database retrospective cohort study.Semantic proximity Read

Algorithmic Fairness and Bias Mitigation for Clinical Machine Learning: A New Utility for Deep Reinforcement LearningSemantic proximity Read

Early Physiological Trajectory-Based Phenotyping in Surgical Intensive Care Unit Patients: A Gaussian Mixture Modeling Approach Integrating Temperature, Central Venous Pressure, Fluid Balance, and Glycemic DynamicsSemantic proximity Read

Low Responsiveness of Machine Learning Models to Critical or Deteriorating Health ConditionsSemantic proximity Read

Ventilator Treatment Policy Control based on BCQ off-line Deep Reinforcement LearningSemantic proximity Read