Offline Reinforcement Learning for Hemodynamic Management of Sepsis in the ICU: a MIMIC-IV Study with Dual Off-Policy Evaluation

• URL: http://arxiv.org/abs/2608.16482v2
• Date: Wed, 26 Aug 2026 09:12:54 GMT
• Title: Offline Reinforcement Learning for Hemodynamic Management of Sepsis in the ICU: a MIMIC-IV Study with Dual Off-Policy Evaluation
• Abstract summary: This work advances the reliable evaluation of sepsis treatment policies by combining off-policy estimation, reliability diagnostics, and clinician-agreement analyses.<n>We modeled fluid and vasopressor dosing on a cohort of 36,872 septic ICU stays from the MIMIC-IV critical-care database.<n>The learned policy was evaluated with two estimators, weighted importance sampling (WIS) and fitted Q evaluation (FQE), with the ESS and clinician agreement as reliability checks.
• Score: 0.3545294650344768
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The dosing of intravenous fluids and vasopressors in sepsis is a sequential decision made under uncertainty and guided largely by clinical judgment, which makes it a natural target for reinforcement learning from historical care. Because a learned policy cannot be trialed on patients, its value must be estimated off-policy, and such estimates can be fragile and optimistic. This work advances the reliable evaluation of sepsis treatment policies by combining off-policy estimation, reliability diagnostics, and clinician-agreement analyses in a transparent validation framework. We modeled fluid and vasopressor dosing on a cohort of 36,872 septic ICU stays drawn from the MIMIC-IV critical-care database, as a discretized Markov decision process with 1,000 states and 25 actions, defined by a five-by-five grid of fluid and vasopressor levels and solved by policy iteration. The clinicians' behavior policy was estimated with a random forest, which mitigated the collapse of the Effective Sample Size (ESS 50.1 against 4.0 with smoothed counts) that otherwise destabilizes the importance-sampling estimate. The learned policy was evaluated with two estimators, weighted importance sampling (WIS) and fitted Q evaluation (FQE), with the ESS and clinician agreement as reliability checks. An empirical variable selection found that the composition of the state matters more than its size. Both estimators place the learned policy above the clinicians' return (WIS 50.8 and FQE 46.8 against 38.2, ESS 50.1), yet it departs only modestly from observed practice (total variation 0.18), favoring less intravenous fluid. These retrospective single-center off-policy results support the learned policy as a clinically plausible refinement of observed practice and motivate its further evaluation as a discordance-based clinical decision-support approach.

Related papers

• Evaluating Large Language Models in Dynamic Clinical Decision-Making with Standardized Patient Cases [71.12461204050985]
  MedSP1000 is an SP-derived interactive benchmark for clinical-agent evaluation.<n>It converts peer-reviewed SP teaching cases into executable scenarios with defined SP case scripts, clinical environment contexts, and human-validated structured rubrics.<n>Applying MedSP1000 to a range of general-purpose and medically specialized LLMs, we find that performance on static benchmarks does not reliably translate to such educational scenarios.
  arXiv  Detail & Related papers  (2026-06-03T17:17:16Z)
• From Static Risk to Dynamic Trajectories: Toward World-Model-Inspired Clinical Prediction [61.12883122613684]
  This Review focuses on intervention-aware disease trajectory modeling in clinical AI--methods estimating patient-specific longitudinal disease evolution and assessing trajectory changes under alternative treatments.<n>We organize the field around six linked components: three decision tasks (factual forecasting, counterfactual estimation, policy evaluation) and three data-generating mechanisms (disease evolution, treatment assignment, observation process) that determine identifiability.<n>We present the first unified framework bridging forecasting, counterfactual trajectories, and policy evaluation across discrete/continuous time, explicitly addressing treatment assignment, time-varying confounding, and observation bias.
  arXiv  Detail & Related papers  (2026-05-16T10:45:26Z)
• Reliability Auditing for Downstream LLM tasks in Psychiatry: LLM-Generated Hospitalization Risk Scores [5.004814662623874]
  Large language models (LLMs) are increasingly utilized in clinical reasoning and risk assessment.<n>However, their interpretive reliability in critical and indeterminate domains such as psychiatry remains unclear.<n>We propose an approach for reliability auditing downstream LLM tasks by structuring evaluation around the impact of prompt design.
  arXiv  Detail & Related papers  (2026-04-23T20:42:22Z)
• Evaluating Patient Safety Risks in Generative AI: Development and Validation of a FMECA Framework for Generated Clinical Content [0.5049603364708264]
  Failure Mode, Effects, and Criticality Analysis (FMECA) provides a proactive framework for systematic risk identification.<n>This study aimed to develop and validate a novel FMECA framework for the prospective assessment of patient safety risks in LLM-generated clinical summaries.
  arXiv  Detail & Related papers  (2026-04-23T14:44:15Z)
• AgentsEval: Clinically Faithful Evaluation of Medical Imaging Reports via Multi-Agent Reasoning [73.50200033931148]
  We introduce AgentsEval, a multi-agent stream reasoning framework that emulates the collaborative diagnostic workflow of radiologists.<n>By dividing the evaluation process into interpretable steps including criteria definition, evidence extraction, alignment, and consistency scoring, AgentsEval provides explicit reasoning traces and structured clinical feedback.<n> Experimental results demonstrate that AgentsEval delivers clinically aligned, semantically faithful, and interpretable evaluations that remain robust under paraphrastic, semantic, and stylistic perturbations.
  arXiv  Detail & Related papers  (2026-01-23T11:59:13Z)
• Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models [51.91760712805404]
  We introduce VivaBench, a benchmark for evaluating sequential clinical reasoning in large language models (LLMs)<n>Our dataset consists of 1762 physician-curated clinical vignettes structured as interactive scenarios that simulate a (oral) examination in medical training.<n>Our analysis identified several failure modes that mirror common cognitive errors in clinical practice.
  arXiv  Detail & Related papers  (2025-10-11T16:24:35Z)
• From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations [45.414878840652115]
  Large language models (LLMs) have demonstrated promising performance on medical benchmarks.<n>However, their ability to perform medical calculations remains underexplored and poorly evaluated.<n>In this work, we revisit medical calculation evaluation with a stronger focus on clinical trustworthiness.
  arXiv  Detail & Related papers  (2025-09-20T09:10:26Z)
• Pruning the Way to Reliable Policies: A Multi-Objective Deep Q-Learning Approach to Critical Care [46.2482873419289]
  We introduce a deep Q-learning approach to obtain more reliable critical care policies. We evaluate our method in off-policy and offline settings using simulated environments and real health records from intensive care units.
  arXiv  Detail & Related papers  (2023-06-13T18:02:57Z)
• COVID-Net Clinical ICU: Enhanced Prediction of ICU Admission for COVID-19 Patients via Explainability and Trust Quantification [71.80459780697956]
  We introduce COVID-Net Clinical ICU, a neural network for ICU admission prediction based on patient clinical data. The proposed COVID-Net Clinical ICU was built using a clinical dataset from Hospital Sirio-Libanes comprising of 1,925 COVID-19 patients. We conducted system-level insight discovery using a quantitative explainability strategy to study the decision-making impact of different clinical features.
  arXiv  Detail & Related papers  (2021-09-14T14:16:32Z)
• Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration [55.88616573143478]
  Outcome prediction from clinical text can prevent doctors from overlooking possible risks. Diagnoses at discharge, procedures performed, in-hospital mortality and length-of-stay prediction are four common outcome prediction targets. We propose clinical outcome pre-training to integrate knowledge about patient outcomes from multiple public sources.
  arXiv  Detail & Related papers  (2021-02-08T10:26:44Z)
• Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding [33.58862183373374]
  We assess robustness of OPE methods under unobserved confounding. We show that even small amounts of per-decision confounding can heavily bias OPE methods. We propose an efficient loss-minimization-based procedure for computing worst-case bounds.
  arXiv  Detail & Related papers  (2020-03-12T05:20:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.