[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125779-en":3,"doc-seo-125779-105":30,"detail-sidebar-cat-0-en-105":91},{"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":27,"seo_description":14,"update_tm":28,"read_time":29},125779,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Integrating decision modeling and machine learning to inform treatment stratification","Growing interest exists in moving beyond “one size fits all (OSFA)” approaches toward stratifying treatment choices by patient characteristics. The paper addresses how expected effectiveness and cost-effectiveness vary with covariates and how modern machine learning can learn outcome heterogeneity without pre-specifying subgroups. A key gap is that ML estimates are not yet integrated into decision modeling for long-term, policy-relevant outcomes. The study proposes a method combining ML and decision modeling using individual patient data to estimate treatment-specific survival time and build policy-relevant decision rules.","Received: 6 March 2023  \nRevised: 18 March 2024  \nAccepted: 29 March 2024  \nDOI: 10. 1002/hec.4834  \nRESEARCH ARTICLE  \nIntegrating decision modeling and machine learning to inform treatment stratification  \nDavid Glynn1  | John Giardina2  | Julia Hatamyar1  | Ankur Pandya2  | Marta Soares1  | Noemi Kreif1   \n1Centre for Health Economics, University of York, York, UK  \n2Department of Health Policy and Management, Harvard T.H. Chan School of Public Health, Boston, Massachusetts, USA  \nCorrespondence  \nDavid Glynn, Centre for Health  \nEconomics, University of York, York, UK.  \nEmail: [david.glynn@york.ac.uk](david.glynn@york.ac.uk)  \nFunding information  \nMedical Research Council, Grant/Award Number: MR/T04487X/1  \nAbstract  \nThere is increasing interest in moving away from “one size fits all (OSFA)”approaches toward stratifying treatment decisions. Understanding how expected effectiveness and cost‐effectiveness varies with patient covariates is a key aspect of stratified decision making. Recently proposed machine learning (ML) methods can learn heterogeneity in outcomes without pre‐specifying subgroups or functional forms, enabling the construction of decision rules (‘policies’) that map individual covariates into a treatment decision. However, these methods do not yet integrate ML estimates into a decision modeling framework in order to reflect long‐term policy‐relevant outcomes and synthesize information from multiple sources. In this paper, we propose a method to integrate ML and decision modeling, when individual patient data is available to estimate treatment‐specific survival time. We also propose a novel implementation of policy tree algorithms to define subgroups using decision model output. We demonstrate these methods using the SPRINT (Systolic Blood Pressure Intervention Trial), comparing outcomes for “standard” and“intensive” blood pressure targets. We find that including ML into a decision model can impact the estimate of incremental net health benefit (INHB) for OSFA policies. We also find evidence that stratifying treatment using subgroups defined by a tree‐based algorithm can increase the estimates of the INHB.  \nKEYWORDS  \ncausal inference, decision modeling, heterogeneity, machine learning, microsimulation, optimal policy, precision medicine  \nThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.  \n© 2024 The Authors. Health Economics published by John Wiley & Sons Ltd.  \n2  \n-  \nGLYNN  \nET AL.  \n1 | INTRODUCTION  \nAn overarching goal throughout health care decision making is to give the right treatment to the right individual at the right time. Health decision makers, however, often rely on evidence about whether a policy improves health outcomeson average for a given population, leading to “one size fits all” treatment decisions that can mask important heterogeneity in the effectiveness and cost‐effectiveness of treatments.  \nHealth decision analysis, including cost‐effectiveness analysis, aims to quantitatively compare different treatment options to identify the optimal choice. Subgroup analysis techniques have been used to characterize heterogeneity indecision analytic models so that recommendations can be targeted toward specific groups of patients and more individuals receive their particular optimal treatment or intervention. The approach to subgroup analyses can range from a simple analysis in which a population is split into two groups, to complex methods that aim to stratify decision making by multiple groups based on patient characteristics (Basu & Meltzer, 2007; Coyle et al., 2003; Espinoza et al., 2014) .  \nThe key issue when conducting these subgroup analyses is to find ways to use the available data to appropriately parameterize the decision analytic model for each subgroup. There is an increasing focus on parameterizing decision models directly with","cbCaiv283lidPzkv","https://ap.wps.com/l/cbCaiv283lidPzkv","pdf",2762172,1,21,"English","en",105,"# Introduction\n## Subgroup analysis and heterogeneity in decision models\n## Parameterizing decision models with individual patient data\n# Background\n## Value of heterogeneity and expected value of individualized care","[{\"question\":\"Why move away from one size fits all (OSFA) treatment policies?\",\"answer\":\"OSFA decisions often rely on average population effects, which can hide meaningful differences in both effectiveness and cost-effectiveness across patient groups.\"},{\"question\":\"What gap does the paper target regarding machine learning and decision modeling?\",\"answer\":\"Machine learning can estimate heterogeneity, but methods have not yet integrated those ML estimates into a decision modeling framework to reflect long-term, policy-relevant outcomes.\"},{\"question\":\"How does the proposed approach use individual patient data in practice?\",\"answer\":\"When individual patient data are available, the method integrates ML and decision modeling to estimate treatment-specific survival time and construct policy tree-based subgroups to define treatment decisions.\"}]","Integrating decision modeling and machine learning to inform treatment stratification | PDF",1785901164,53,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"integrating-decision-modeling-and-machine-learning-to-inform-treatment-stratification","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/integrating-decision-modeling-and-machine-learning-to-inform-treatment-stratification/125779/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why move away from one size fits all (OSFA) treatment policies?","Question",{"text":75,"@type":76},"OSFA decisions often rely on average population effects, which can hide meaningful differences in both effectiveness and cost-effectiveness across patient groups.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What gap does the paper target regarding machine learning and decision modeling?",{"text":80,"@type":76},"Machine learning can estimate heterogeneity, but methods have not yet integrated those ML estimates into a decision modeling framework to reflect long-term, policy-relevant outcomes.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed approach use individual patient data in practice?",{"text":84,"@type":76},"When individual patient data are available, the method integrates ML and decision modeling to estimate treatment-specific survival time and construct policy tree-based subgroups to define treatment decisions.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]