[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83983-en":3,"doc-seo-83983-105":29,"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":20,"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},83983,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","SafeImpute: Reliable Clinical Data Imputation via Conformal Selection","Clinical care depends on key laboratory indicators, yet irregular visits and opportunistic test ordering create pervasive missingness in longitudinal records. Many imputation approaches improve average accuracy without specifying which outputs remain safe for high-stakes decisions. SafeImpute builds a reliable imputation system that selectively releases results with statistical control over clinically unacceptable errors, using an event-graph GNN and conformal-based risk-to-pvalue selection with FDR control, validated on Mayo Clinic and MIMIC-III/IV datasets.","SafeImpute: Reliable Clinical Data Imputation via Conformal Selection  \nXinrui He University of Illinois Urbana-Champaign Champaign, IL, USA [xhe33@illinois.edu](xhe33@illinois.edu)  \nMengting Ai University of Illinois Urbana-Champaign Champaign, IL, USA [mai10@illinois.edu](mai10@illinois.edu)  \nJunting Wang University of Illinois Urbana-Champaign Champaign, IL, USA [junting3@illinois.edu](junting3@illinois.edu)  \nCurtiss B. Cook  \nMayo Clinic Scottsdale, AZ, USA [cook.curtiss@mayo.edu](cook.curtiss@mayo.edu)  \nJingrui He University of Illinois Urbana-Champaign Champaign, IL, USA [jingrui@illinois.edu](jingrui@illinois.edu)  \narXiv :2607 .056 13v 1 [ cs .LG] 6 Jul 2026  \nAbstract  \nClinical care often relies on key laboratory indicators, yet realworld patient visits are sparse and tests are ordered irregularly, leading to pervasive missingness. While many imputation methods improve average accuracy, they provide limited guidance on which imputed values are reliable enough for high-stakes downstream use. In this work, we study reliable clinical imputation, aiming to produce accurate imputations while selectively releasing the reliable results, with statistical control over clinically unacceptable errors. To achieve this goal, we propose SafeImpute, a reliable imputation framework for irregular and sparse clinical longitudinal records. SafeImpute constructs an event graph that captures both intra-patient temporal trajectories and inter-patient clinical similarity, and learns imputations with a two-relation GNN and adaptive fusion, regularized by an auxiliary masked reconstruction objective. For reliability guarantees, SafeImpute converts a proxy risk score into conformalp-values and applies the Benjamini– Hochberg procedure to control the false discovery rate (FDR) of unacceptable errors among released imputations at a user-specified tolerance. Experiments on our Mayo Clinic data, the public MIMICIII and MIMIC-IV datasets show that SafeImpute achieves strong imputation accuracy while providing reliable error control, outperforming diverse baselines in both standard imputation evaluation and FDR-controlled selective-release evaluation. Code is available at [https://github.com/Xinrui17/SafeImpute](https://github.com/Xinrui17/SafeImpute).  \nCCS Concepts  \n• Computing methodologies → Neural networks; • Applied computing → Health informatics.  \nKeywords  \nClinical Data Imputation, Graph Neural Networks, Conformal Selection, FDR Control  \nAccepted at the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2026) . This is the authors’ accepted manuscript. The final version of record will appear in the ACM Digital Library with DOI: 10.1145/3770855.3817967 .  \n1 Introduction  \nIn clinical care, key indicators, e.g., Hemoglobin A1c (HbA1c) for diabetes management [4], are crucial for disease monitoring and treatment adjustment [44], yet patient visits are irregular, and labs are often not ordered at every visit, resulting in pervasive missingness in longitudinal records. Recent years have seen growing interest in clinical data imputation, with methods ranging from statistical models [31, 47, 48] to deep generative models and representation learning [6, 15, 55, 57] . Despite this progress, most approaches emphasize overall accuracy and provide limited guarantees on error control in high-stakes use, where unreliable results can directly mislead diagnosis and treatment adjustment.  \nClinical deployment, therefore, raises a question beyond overall accuracy: which imputed results are reliable enough to support clinical decision-making, and how can we provide explicit control over imputation errors? This motivates reliable clinical imputation, which augments imputation with uncertainty or reliability assessment, thereby producing imputations with quantitative error control. Related quality-control frameworks have been studied in highstakes prediction, including Bayesian methods [9, 52], imprecise probability [3], and conform","cbCaihqq6Fjg9sBp","https://ap.wps.com/l/cbCaihqq6Fjg9sBp","pdf",2341840,1,12,"English","en",105,"# Introduction\n## Problem: Missingness in irregular clinical longitudinal records\n## Goal: Reliable selective imputation with error control\n## Proposed method: SafeImpute framework","[{\"question\":\"What problem does SafeImpute address in clinical data?\",\"answer\":\"SafeImpute addresses pervasive missingness caused by irregular patient visits and opportunistic lab test ordering in longitudinal records, where many imputation outputs may be unreliable for downstream clinical use.\"},{\"question\":\"How does SafeImpute model irregular and sparse longitudinal data?\",\"answer\":\"SafeImpute constructs an event graph that captures intra-patient temporal trajectories and inter-patient clinical similarity, then learns imputations using a two-relation GNN with adaptive fusion and an auxiliary masked reconstruction objective.\"},{\"question\":\"How does SafeImpute provide guarantees for released imputations?\",\"answer\":\"SafeImpute converts a proxy risk score into conformal p-values and applies the Benjamini–Hochberg procedure to control the false discovery rate (FDR) of clinically unacceptable errors among the released imputations at a user-specified tolerance.\"}]",1784191846,30,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":27},"safeimpute-reliable-clinical-data-imputation-via-conformal-selection","",{"@graph":35,"@context":85},[36,53,68],{"@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/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/safeimpute-reliable-clinical-data-imputation-via-conformal-selection/83983/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does SafeImpute address in clinical data?","Question",{"text":75,"@type":76},"SafeImpute addresses pervasive missingness caused by irregular patient visits and opportunistic lab test ordering in longitudinal records, where many imputation outputs may be unreliable for downstream clinical use.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does SafeImpute model irregular and sparse longitudinal data?",{"text":80,"@type":76},"SafeImpute constructs an event graph that captures intra-patient temporal trajectories and inter-patient clinical similarity, then learns imputations using a two-relation GNN with adaptive fusion and an auxiliary masked reconstruction objective.",{"name":82,"@type":73,"acceptedAnswer":83},"How does SafeImpute provide guarantees for released imputations?",{"text":84,"@type":76},"SafeImpute converts a proxy risk score into conformal p-values and applies the Benjamini–Hochberg procedure to control the false discovery rate (FDR) of clinically unacceptable errors among the released imputations at a user-specified tolerance.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":28,"slug":121},"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":106,"slug":137},19,"General","general"]