analiza aiqbench
This research introduces EHR-MPC, a framework that uses generative patient digital twins to optimize sepsis treatment through inference-time control rather than fixed reinforcement learning policies. By decoupling the modeling of clinical dynamics from optimization strategies, the approach allows for adaptable decision-making in complex ICU environments using real-world multicenter data. The study demonstrates how advanced machine learning techniques can be applied directly to high-stakes medical scenarios by simulating patient trajectories before intervention.
EHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins
arXiv:2607.08793v3 Announce Type: replace-cross 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.
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.
Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Systems and Control (eess.SY); Optimization and Control (math.OC)
arXiv:2607.08793 [stat.ML]
(or arXiv:2607.08793v3 [stat.ML] for this version)
Text integral sub licența deschisă a publicației · 176 cuvinte
Subiecte conexe
Forbes Asia 100 To Watch 2026
forbes.com · 24 aug. 2026
Deconfusing Corrigibility
AI Alignment Forum · 17 oct. 2026
AI in healthcare: applications and best practices
Databricks · 24 iul. 2026
Reducing medical claims review time with AI on AWS: The EXL Medical IDP solution
AWS · 21 sept. 2026