[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120206-en":3,"doc-seo-120206-105":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},120206,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Causal machine learning for predicting treatment outcomes","Causal machine learning (ML) provides data-driven methods for assessing treatment effectiveness and supporting drug safety. The work explains how causal ML estimates individualized treatment effects and predicts patient outcomes under alternative treatments, enabling fine-grained insights into when therapies are beneficial or harmful. It also covers how causal ML can combine clinical trial evidence with real-world data such as registries and electronic health records, and offers recommendations for reliable medical use.","Causal machine learning for predicting treatment  \noutcomes  \nStefan Feuerriegel* ,1,2 , Dennis Frauen1,2 , Valentyn Melnychuk1,2 , Jonas Schweisthal1,2 , Konstantin Hess1,2 , Alicia Curth3 , Stefan Bauer4,5 , Niki Kilbertus2,4,5 , Isaac S. Kohane6 , and Mihaela van der Schaar7,8  \n1LMU Munich, Munich, Germany  \n2Munich Center for Machine Learning, Munich, Germany  \n3Department of Applied Mathematics & Theoretical Physics, University of Cambridge, Cambridge, United Kingdom 4 School of Computation, Information and Technology, TU Munich, Munich Germany 5Helmholtz Munich, Munich, Germany  \n6Department of Biomedical Informatics, Harvard Medical School, Boston, USA 7Cambridge Centre for AI in Medicine, University of Cambridge, Cambridge, United Kingdom 8The Alan Turing Institute, London, United Kingdom  \nAbstract  \nCausal machine learning (ML) offers flexible, data-driven methods for predicting treatment outcomes. Here, we present how methods from causal ML can be used to understand the effectiveness of treatments, thereby supporting the assessment and safety of drugs. A key benefit of causal ML is that allows for estimating individualized treatment effects, as well as personalized predictions of potential patient outcomes under different treatments. This offers granular insights into when treatments are effective, so that decision-making in patient care can be personalized to individual patient profiles. We further discuss how causal ML can be used in combination with both clinical trial data as well as real-world data such as clinical registries and electronic health records. We finally provide recommendations for the reliable use of causal ML in medicine.  \nFirst published in Nature Medicine, 30, 958–968 (2024) by Springer Nature. Link: [https://doi.org/10.1038/s41591-024-02902-1](https://doi.org/10.1038/s41591-024-02902-1)  \n* Corresponding author: [feuerriegel@lmu.de](feuerriegel@lmu.de)  \nMain  \nAssessing the effectiveness of treatments is crucial to ensure patient safety and personalize patient care. Recent innovations in machine learning (ML) offer new, data-driven methods to estimate treatment effects from data. This branch in ML is commonly referred to as causal ML as it aims to predict a causal quantity, namely, the patient outcomes due to treatment [1] . Causal ML can be used in order to estimate treatment effects from both experimental data obtained through randomized controlled trials (RCTs) and observational data obtained from clinical registries, electronic health records, and other real-world data (RWD) sources to generate clinical evidence. A key strength of causal ML is that it allows to estimate individualized treatment effects, as well as to make personalized predictions of potential patient outcomes under different treatments. This offers a granular understanding of when treatments are effective or harmful, so that decision-making inpatient care can be personalized to individual patient profiles.  \nBox 1. Glossary of common terms in causal ML  \n• Causal graph: A graphical representation of the causal relationships between variables, typically using directed acyclic graphs to depict causal paths.  \n• Causal ML: A branch of machine learning that aims at the estimation of causal quantities (e.g., average treatment effect, conditional average treatment effect) or at predicting potential outcomes. Here,“causal” implies that the target is a causal quantity when certain assumptions about the data-generating mechanism are satisfied. For alternative definitionsand use cases of causal ML, see [1] .  \n• Confounder: A variable that influences both the treatment assignment and the outcome.  \n• Consistency: The potential outcome is equal to the observed patient outcome under the selected treatment, which implies that the outcomes are clearly defined.  \n• Counterfactual outcome: The unobservable patient outcome that would have occurred, hada patient received a different treatment.  \n• Factual outcome: The observed patient ou","cbCaiq3B1Y2Katjr","https://ap.wps.com/l/cbCaiq3B1Y2Katjr","pdf",3074227,1,33,"English","en",105,"# Assessing the effectiveness of treatments\n## Comparison to traditional ML\n## Causal ML in medicine\n## Glossary of common terms in causal ML\n## Figure overview: Causal ML for predicting treatment outcomes","[{\"question\":\"What is causal machine learning in the context of predicting treatment outcomes?\",\"answer\":\"Causal ML targets causal quantities such as patient outcomes under specific treatments, rather than only statistical prediction. It supports estimating treatment effects and potential outcomes under different therapy options.\"},{\"question\":\"How does causal ML differ from traditional machine learning for medical prediction?\",\"answer\":\"Traditional ML focuses on predicting outcomes from data, while causal ML quantifies how outcomes change due to treatment so that treatment effects can be estimated. This distinction helps connect predictions to causal impact.\"},{\"question\":\"Which data sources can be used with causal ML to build clinical evidence?\",\"answer\":\"Causal ML can use randomized controlled trial data and observational real-world data, including clinical registries and electronic health records. Combining these sources supports evidence for treatment effectiveness and safety.\"}]","Causal machine learning for predicting treatment outcomes | PDF",1785728721,83,{"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},"causal-machine-learning-for-predicting-treatment-outcomes","",{"@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/causal-machine-learning-for-predicting-treatment-outcomes/120206/",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","2026-08-03",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},"What is causal machine learning in the context of predicting treatment outcomes?","Question",{"text":75,"@type":76},"Causal ML targets causal quantities such as patient outcomes under specific treatments, rather than only statistical prediction. It supports estimating treatment effects and potential outcomes under different therapy options.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does causal ML differ from traditional machine learning for medical prediction?",{"text":80,"@type":76},"Traditional ML focuses on predicting outcomes from data, while causal ML quantifies how outcomes change due to treatment so that treatment effects can be estimated. This distinction helps connect predictions to causal impact.",{"name":82,"@type":73,"acceptedAnswer":83},"Which data sources can be used with causal ML to build clinical evidence?",{"text":84,"@type":76},"Causal ML can use randomized controlled trial data and observational real-world data, including clinical registries and electronic health records. Combining these sources supports evidence for treatment effectiveness and safety.","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"]