[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82052-en":3,"doc-seo-82052-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82052,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",7,"Healthcare","EHR-MPC Inference Time Control for Sepsis Treatment with Generative Patient Digital Twins","Sepsis remains a major cause of mortality, while optimal treatment policies are still debated. Existing reinforcement learning methods often learn fixed strategies, restricting adaptation to shifting clinical objectives during inference. EHR-MPC separates patient-dynamics learning from treatment optimization by training a generative EHR digital twin and using inference-time model predictive control (MPC) to plan over simulated trajectories. Across 8-hospital ICU data, EHR-MPC matches off-policy baselines and improves simulation performance versus RL approaches.","arXiv :2607 .08793v1 [ stat .ML] 7 Jul 2026  \nEHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins  \nJoshua Pickard [jpickard@broadinstitute.org](jpickard@broadinstitute.org)  \nBroad Institute of MIT and Harvard  \nWei Qi  \nBroad Institute of MIT and Harvard  \nNa Li  \nHarvard University  \nAnn Woolley  \nBrigham and Women’s Hospital  \nLisa Cosimi  \nBrigham and Women’s Hospital  \nRoy Kishony  \nTechnion–Israel Institute of Technology  \nDeborah Hung  \nBroad Institute of Harvard and MIT  \nAbstract  \nSepsis 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.  \n1. Introduction  \nTreatment of sepsis patients is a major healthcare challenge affecting more than 48 million people and resulting in 11 million deaths per year globally (World Health Organization, 2024) . Extensive work has explored optimal sepsis treatment policies in both clinical trials (Venkatesh et al. , 2018; Annane et al. , 2018) and reinforcement learning (Raghu et al. , 2017a,b, 2018; Komorowski et al. , 2018; Huang et al. , 2022) . In particular, corticosteroid administration remains a longstanding clinical question, with more than 60 randomized controlled trials conducted (Schumer, 1976; Annane et al. , 2025) . Still, evidence guiding which patients should receive corticosteroids, as well as the appropriate timing and dosage, remains contested (Marik, 2018) .  \n© 2026 J. Pickard, W. Qi, N. Li, A. Woolley, L. Cosimi, R. Kishony & D. Hung.  \nInference-Time Control for Sepsis Treatment with Generative Patient Digital Twins  \nWhile both clinical trials and reinforcement learning (RL) aim to identify optimal policies for sepsis management, their recommendations remain largely disconnected. For instance, one RL study suggests that “optimal treatment [with corticosteroids] may be more restrictive than routine clinical practice” (Bologheanu et al. , 2023), in contrast to randomized clinical trial evidence indicating that corticosteroids “probably reduce 28-day and hospital mortality among patients with sepsis” (Annane et al. , 2025) . This discrepancy highlights a limitation of RL approaches, as despite strong retrospective performance under off-policy evaluation, learned policies are often difficult to interpret, adapt, or validate in clinical practice (Zhang et al. , 2022; Frommeyer et al. , 2025) . Optimizing a fixed reward function without explicitly modeling patient dynamics limits the ability of RL-based treatment strategies to accommodate individualized clinical goals or to adapt to competing objectives (Jayaraman et al. , 2024) . In practice, sepsis management requires balancing trade-offs such as short-term hemodynamic stabilization versus long-term organ-system preservation, informed by clinician judgment, evolving standards of care, and patient-specific context (Prescott et al. , 2026) . Because RL typically entangles patient dynamics and reward specificat","cbCaihWzywNdr2ck","https://ap.wps.com/l/cbCaihWzywNdr2ck","pdf",2110007,1,27,"English","en",105,"# Introduction\n## Motivation and limitations of prior RL approaches\n## EHR-MPC framework and inference-time MPC\n## Generalizable machine learning insights in healthcare","[{\"question\":\"Why do current reinforcement learning approaches struggle in sepsis treatment deployment?\",\"answer\":\"They typically learn fixed policies that entangle patient dynamics and a fixed reward objective, making policies difficult to interpret, adapt, or validate when clinical goals or settings change.\"},{\"question\":\"How does EHR-MPC decouple dynamics learning from treatment optimization?\",\"answer\":\"It trains a generative patient digital twin from EHR data to model patient trajectories, then uses inference-time model predictive control (MPC) to optimize treatments by simulating counterfactual outcomes under candidate interventions.\"},{\"question\":\"What evaluation setup is used to assess EHR-MPC for sepsis?\",\"answer\":\"The method is evaluated on a multicenter ICU sepsis cohort across 8 hospitals, using off-policy importance sampling and on-policy simulation-based evaluation, and compared with RL baselines.\"}]",1784177831,68,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"ehr-mpc-inference-time-control-for-sepsis-treatment-with-generative-patient-digital-twins","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/healthcare/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/ehr-mpc-inference-time-control-for-sepsis-treatment-with-generative-patient-digital-twins/82052/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why do current reinforcement learning approaches struggle in sepsis treatment deployment?","Question",{"text":74,"@type":75},"They typically learn fixed policies that entangle patient dynamics and a fixed reward objective, making policies difficult to interpret, adapt, or validate when clinical goals or settings change.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does EHR-MPC decouple dynamics learning from treatment optimization?",{"text":79,"@type":75},"It trains a generative patient digital twin from EHR data to model patient trajectories, then uses inference-time model predictive control (MPC) to optimize treatments by simulating counterfactual outcomes under candidate interventions.",{"name":81,"@type":72,"acceptedAnswer":82},"What evaluation setup is used to assess EHR-MPC for sepsis?",{"text":83,"@type":75},"The method is evaluated on a multicenter ICU sepsis cohort across 8 hospitals, using off-policy importance sampling and on-policy simulation-based evaluation, and compared with RL baselines.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,117,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":115,"slug":116},40,"healthcare",{"id":118,"doc_module":4,"doc_module_name":45,"category_name":119,"show_sort_weight":120,"slug":121},8,"Research & Report",30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]