[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-339979-105":59,"doc-detail-339979-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","multi-metric-comparison-of-machine-learning-imputation-methods-with-application-to-breast-cancer-survival","Multi-metric comparison of machine learning imputation methods with application to breast cancer survival","","Handling missing data in clinical prognostic studies is essential yet challenging. This study assessed the effectiveness and reliability of different machine learning (ML) imputation methods from multiple analytical perspectives. It evaluated three metric classes: post-imputation bias of regression estimates, post-imputation predictive accuracy, and substantive model-free metrics using a real breast cancer survival dataset and a simulated dataset with 30% MAR values.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/multi-metric-comparison-of-machine-learning-imputation-methods-with-application-to-breast-cancer-survival/339979/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/multi-metric-comparison-of-machine-learning-imputation-methods-with-application-to-breast-cancer-survival/339979.png","ImageObject",300,407,{"name":92,"@type":93},"Levi","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-01","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What was the main goal of the study?","Question",{"text":112,"@type":113},"To comprehensively assess the effectiveness and reliability of different machine learning imputation methods across multiple analytical perspectives in time-to-event research using breast cancer survival data.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Which imputation methods and data setup were evaluated?",{"text":117,"@type":113},"Single imputation methods (e.g., KNN, missMDA, CART, missForest, missRanger, missCforest) and multiple imputation methods (miceCART, miceRF) were evaluated, including simulated data with 30% Missing At Random (MAR) values.",{"name":119,"@type":110,"acceptedAnswer":120},"How did the study judge performance across methods?",{"text":121,"@type":113},"By comparing multiple performance metrics, including post-imputation bias and predictive accuracy (e.g., Gower’s distance, bias, coverage, AUC, and C-index) as well as substantive model-free metrics.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},339979,1790510798,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":44,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145,"preview_page_count":19,"preview_urls":146},7971461740909,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","El Badisy et al. BMC Medical Research Methodology (2024) 24:191  \n[https://doi.org/10.1186/s12874-024-02305-3](https://doi.org/10.1186/s12874-024-02305-3)  \nBMC Medical Research Methodology  \nRESEARCH Open Access  \nMulti-metric comparison of machine learning imputation methods with application to breast cancer survival  \nImad El Badisy 1,2,3*, Nathalie Graffeo3, Mohamed Khalis 1,2 and Roch Giorgi3,4  \nAbstract  \nHandling missing data in clinical prognostic studies is an essential yet challenging task. This study aimed to provide a comprehensive assessment of the effectiveness and reliability of different machine learning (ML) imputation methods across various analytical perspectives. Specifically, it focused on three distinct classes of performance metrics used to evaluate ML imputation methods: post-imputation bias of regression estimates, post-imputation predictive accuracy, and substantive model-free metrics. As an illustration, we applied data from a real-world breast cancer survival study. This comprehensive approach aimed to provide a thorough assessment of the effectiveness and reliability of ML imputation methods across various analytical perspectives. A simulated dataset with 30% Missing At Random (MAR) values was used. A number of single imputation (SI) methods-specifically KNN, missMDA, CART, missForest, missRanger, missCforest-and multiple imputation (MI) methods-specifically miceCART and miceRF-were evaluated. The performance metrics used were Gower’s distance, estimation bias, empirical standard error, coverage rate, length of confidence interval, predictive accuracy, proportion of falsely classified (PFC), normalized root mean squared error (NRMSE), AUC, and C-index scores. The analysis revealed that in terms of Gower’s distance, CART and missForest were the most accurate, while missMDA and CART excelled for binary covariates; missForest and miceCART were superior for continuous covariates. When assessing bias and accuracy in regression estimates, miceCART and miceRF exhibited the least bias. Overall, the various imputation methods demonstrated greater efficiency than complete-case analysis (CCA), with MICE methods providing optimal confidence interval coverage. In terms of predictive accuracy for Cox models, missMDA and missForest had superior AUC and C-index scores. Despite offering better predictive accuracy, the study found that SI methods introduced more bias into the regression coefficients compared to MI methods. This study underlines the importance of selecting appropriate imputation methods based on study goals and data types in time-to-event research. The varying effectiveness of methods across the different performance metrics studied highlights the value of using advanced machine learning algorithms within a multiple imputation framework to enhance research integrity and the robustness of findings.  \nKeywords Machine learning, Imputation methods, Single and multiple imputation, Performance metrics, Breast cancer survival, Survival analysis  \n*Correspondence: Imad El Badisy[ielbadisy@um6ss. ma](ielbadisy@um6ss. ma)  \nFull list of author information is available at the end of the article  \n© The Author(s) 2024. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitt","cbCaivXyJMmffXwe","https://ap.wps.com/l/cbCaivXyJMmffXwe","pdf",2015815,17,"English","# Abstract\n# Background\n## Missing data mechanisms (MCAR, MAR, MNAR)\n## Imputation methods and complete-case analysis","[{\"question\":\"What was the main goal of the study?\",\"answer\":\"To comprehensively assess the effectiveness and reliability of different machine learning imputation methods across multiple analytical perspectives in time-to-event research using breast cancer survival data.\"},{\"question\":\"Which imputation methods and data setup were evaluated?\",\"answer\":\"Single imputation methods (e.g., KNN, missMDA, CART, missForest, missRanger, missCforest) and multiple imputation methods (miceCART, miceRF) were evaluated, including simulated data with 30% Missing At Random (MAR) values.\"},{\"question\":\"How did the study judge performance across methods?\",\"answer\":\"By comparing multiple performance metrics, including post-imputation bias and predictive accuracy (e.g., Gower’s distance, bias, coverage, AUC, and C-index) as well as substantive model-free metrics.\"}]","Multi-metric comparison of machine learning imputation methods with application to breast cancer survival | PDF",1790033494,43,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0864b41b8568aa838047e8e829f7e845.webp",983,1310,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/285b54fb0a7b579c3c1c60e6f3c98ddd.webp",982,1309,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/46bed0fd20f6f32670a5f16d0e6bf65e.webp",981,1308,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/bc0eb9c92f74530fd3d4d88a9cf038f2.webp",980,1306]