EHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins

• URL: http://arxiv.org/abs/2607.08793v2
• Date: Mon, 13 Jul 2026 15:31:17 GMT
• Title: EHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins
• Abstract summary: Existing reinforcement learning approaches learn fixed strategies for sepsis treatment.<n>We propose EHRMPC, a framework that decouples learning patient dynamics from optimizing treatment.
• Score: 3.229417465367373
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sepsis is a leading cause of mortality, yet optimal treatment policies remain contested. Existing reinforcement learning (RL) approaches learn fixed strategies for sepsis treatment, limiting adaptability to changing clinical objectives during inference. We propose EHRMPC, a framework that decouples learning patient dynamics from optimizing treatment by training a patient digital twin in the form of a generative electronic health record (EHR) model. The digital twin predicts clinical trajectories under interventions and enables model predictive control (MPC) to optimize treatments via inference-time planning over simulations. We evaluate EHR-MPC on a multicenter ICU sepsis cohort spanning 8 hospitals in the Mass General Brigham health system using both off-policy importance sampling and on-policy simulation-based evaluation. Relative to RL baselines, EHR-MPC achieves comparable off-policy performance and improved simulation performance. Unlike RL, this work frames sepsis treatment optimization as inference-time control over learned patient dynamics, establishing a general framework for decision making with generative clinical models.

Related papers

• Enhancing Personalized Bladder Cancer Treatment Through Reinforcement Learning: A Recurrent Patient State Transition Decision Support Framework [0.0]
  Bladder cancer treatment requires personalized and adaptive decision-making.<n>This paper presents a recurrent patient state-transition simulation framework for bladder cancer treatment planning.<n>It integrates predictive state-transition modeling with a Markov Decision Process (MDP) and a Deep Q-Network (DQN) reinforcement learning environment.
  arXiv  Detail & Related papers  (2026-07-18T18:16:44Z)
• CT-CLIP Representations for Multimodal Lung Cancer Survival Prediction [6.141870006905838]
  This study evaluates whether representations from a domain-specific foundation model can be used for multimodal survival prediction in data-constrained clinical settings.<n>We assess the foundation model CT-CLIP as a feature extractor for pretreatment computed tomography images and clinical variables from 242 diagnosed lung cancer patients.
  arXiv  Detail & Related papers  (2026-07-09T14:00:14Z)
• Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model [57.78184285979881]
  We introduce SepsisAgent, a world model-augmented LLM agent for sepsis treatment recommendation.<n>SepsisAgent uses a learned Clinical World Model to simulate patient responses under candidate fluid--vasopressor interventions.
  arXiv  Detail & Related papers  (2026-05-14T11:50:00Z)
• ReMedi: Reasoner for Medical Clinical Prediction [70.84466325266068]
  We present ReMedi, a framework for improving clinical outcome prediction from EHR.<n>ReMedi generates rationale-answer pairs using a challenging sample regeneration mechanism for complex clinical questions.<n> Experiments on multiple EHR prediction tasks demonstrate substantial gains of up to 19.9 percent over state-of-the-art baselines in terms of F1 score.
  arXiv  Detail & Related papers  (2026-05-02T14:44:49Z)
• Optimizing Hospital Capacity During Pandemics: A Dual-Component Framework for Strategic Patient Relocation [0.0]
  This research proposes a two-part framework to optimize hospital capacity through patient relocation strategies.<n>The first component involves developing a time series prediction model to forecast patient arrival rates.<n>The second is a simulation model that evaluates the impact of different patient relocation strategies.
  arXiv  Detail & Related papers  (2026-03-16T22:22:10Z)
• PREBA: Surgical Duration Prediction via PCA-Weighted Retrieval-Augmented LLMs and Bayesian Averaging Aggregation [51.96735866702332]
  PREBA is a retrieval-augmented framework that integrates PCA-weighted retrieval and Bayesian averaging aggregation.<n> PREBA significantly improves performance-for instance, reducing MAE by up to 40% and raising R2 from -0.13 to 0.62 over zero-shot inference.
  arXiv  Detail & Related papers  (2026-02-27T07:19:23Z)
• TECM*: A Data-Driven Assessment to Reinforcement Learning Methods and Application to Heparin Treatment Strategy for Surgical Sepsis [20.372045640927993]
  This study proposes a data-driven metric and a continuous reward function to optimize heparin therapy in surgical sepsis patients.<n>The training cohort consisted of abdominal surgery patients receiving unfractionated heparin (UFH) after postoperative sepsis onset.
  arXiv  Detail & Related papers  (2025-12-02T08:38:07Z)
• Realistic CDSS Drug Dosing with End-to-end Recurrent Q-learning for Dual Vasopressor Control [37.613456891934085]
  We develop an end-to-end approach for learning optimal drug dosing and control policies for dual vasopressor administration in intensive care unit (ICU) patients with septic shock.<n>For realistic drug dosing, we apply action space design that accommodates discrete, continuous, and directional dosing strategies.<n>The proposed methods achieve improved patient outcomes of over 15% in survival improvement probability, while aligning with established clinical protocols.
  arXiv  Detail & Related papers  (2025-10-01T23:02:00Z)
• SoC-DT: Standard-of-Care Aligned Digital Twins for Patient-Specific Tumor Dynamics [13.83306392535935]
  Accurate prediction of tumor trajectories under standard-of-care (SoC) therapies remains a major unmet need in oncology.<n>We introduce Standard-of-Care Digital Twin (SoC-DT), a differentiable framework that unifies reaction-diffusion tumor growth models.<n>An implicit-explicit exponential time-differencing solver, IMEX-SoC, is also proposed, which ensures stability, positivity, and scalability in SoC treatment situations.
  arXiv  Detail & Related papers  (2025-09-29T04:14:11Z)
• Medical World Model: Generative Simulation of Tumor Evolution for Treatment Planning [50.16114813279694]
  We introduce the Medical World Model (MeWM), the first world model in medicine that visually predicts future disease states based on clinical decisions.<n>MeWM comprises (i) vision-language models to serve as policy models, and (ii) tumor generative models as dynamics models.<n>We propose the inverse dynamics model that applies survival analysis to the simulated post-treatment tumor, enabling the evaluation of treatment efficacy and the selection of the optimal clinical action plan.
  arXiv  Detail & Related papers  (2025-06-02T23:50:40Z)
• Optimal discharge of patients from intensive care via a data-driven policy learning framework [58.720142291102135]
  It is important that the patient discharge task addresses the nuanced trade-off between decreasing a patient's length of stay and the risk of readmission or even death following the discharge decision. This work introduces an end-to-end general framework for capturing this trade-off to recommend optimal discharge timing decisions. A data-driven approach is used to derive a parsimonious, discrete state space representation that captures a patient's physiological condition.
  arXiv  Detail & Related papers  (2021-12-17T04:39:33Z)
• Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations [114.16762407465427]
  We introduce the Counterfactual Recurrent Network (CRN) to estimate treatment effects over time. CRN uses domain adversarial training to build balancing representations of the patient history. We show how our model achieves lower error in estimating counterfactuals and in choosing the correct treatment and timing of treatment.
  arXiv  Detail & Related papers  (2020-02-10T20:47:36Z)

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.