{"id":"https://openalex.org/W4413031079","doi":"https://doi.org/10.34133/hds.0493","title":"Comparison of Imputation Strategies for Incomplete Electronic Health Data","display_name":"Comparison of Imputation Strategies for Incomplete Electronic Health Data","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4413031079","doi":"https://doi.org/10.34133/hds.0493","pmid":"https://pubmed.ncbi.nlm.nih.gov/42973692","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13724834"},"language":"en","primary_location":{"id":"doi:10.34133/hds.0493","doi":"https://doi.org/10.34133/hds.0493","is_oa":true,"landing_page_url":"https://doi.org/10.34133/hds.0493","pdf_url":null,"source":{"id":"https://openalex.org/S4210185134","display_name":"Health Data Science","issn_l":"2097-1095","issn":["2097-1095","2765-8783"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","ki-jl-1","oarl"],"host_organization":"https://openalex.org/P4310315823","host_organization_name":"American Association for the Advancement of Science","host_organization_lineage":["https://openalex.org/P4310315823"],"host_organization_lineage_names":["American Association for the Advancement of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Data Science","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.34133/hds.0493","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101360186","display_name":"Shuo Zhang","orcid":"https://orcid.org/0009-0007-8846-1758","observed_orcids":["https://orcid.org/0009-0007-8846-1758"]},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuo Zhang","raw_affiliation_strings":["Tianjin University of Technology;","Department of Computer Science, Tianjin University of Technology, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0007-8846-1758","affiliations":[{"raw_affiliation_string":"Tianjin University of Technology;","institution_ids":["https://openalex.org/I136765683"]},{"raw_affiliation_string":"Department of Computer Science, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101764889","display_name":"Zhilong Zhang","orcid":"https://orcid.org/0000-0002-9328-9098","observed_orcids":["https://orcid.org/0000-0002-9328-9098"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhilong Zhang","raw_affiliation_strings":["Peking University;","National Institute of Health Data Science, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University;","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"National Institute of Health Data Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100711803","display_name":"Yuxi Zhou","orcid":"https://orcid.org/0000-0001-6875-726X","observed_orcids":["https://orcid.org/0000-0001-6875-726X"]},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxi Zhou","raw_affiliation_strings":["Peking University;","DCST, BNRist, RIIT, Institute of Internet Industry, Tsinghua University, Beijing, China","Department of Computer Science, Tianjin University of Technology, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-6875-726X","affiliations":[{"raw_affiliation_string":"Peking University;","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"DCST, BNRist, RIIT, Institute of Internet Industry, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shenda Hong","orcid":"https://orcid.org/0000-0001-7521-5127","observed_orcids":["https://orcid.org/0000-0001-7521-5127"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenda Hong","raw_affiliation_strings":["Peking University;","National Institute of Health Data Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7521-5127","affiliations":[{"raw_affiliation_string":"Peking University;","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"National Institute of Health Data Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101556850","display_name":"Huixin Liu","orcid":"https://orcid.org/0000-0003-1305-1977","observed_orcids":["https://orcid.org/0000-0003-1305-1977"]},"institutions":[{"id":"https://openalex.org/I4210124809","display_name":"Peking University People's Hospital","ror":"https://ror.org/035adwg89","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210124809"]},{"id":"https://openalex.org/I4210130930","display_name":"Peking University First Hospital","ror":"https://ror.org/02z1vqm45","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210130930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huixin Liu","raw_affiliation_strings":["Peking University First Hospital","Department of Clinical Epidemiology and Biostatistics, Peking University People's Hospital, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1305-1977","affiliations":[{"raw_affiliation_string":"Peking University First Hospital","institution_ids":["https://openalex.org/I4210130930"]},{"raw_affiliation_string":"Department of Clinical Epidemiology and Biostatistics, Peking University People's Hospital, Beijing, China","institution_ids":["https://openalex.org/I4210124809"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101360186"],"corresponding_institution_ids":["https://openalex.org/I136765683"],"apc_list":null,"apc_paid":null,"fwci":4.2794,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92053782,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"6","issue":null,"first_page":"0493","last_page":"0493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.448199987411499,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.448199987411499,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.18469999730587006,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.17260000109672546,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/missing-data-imputation","display_name":"missing data imputation","score":0.9879999756813049},{"id":"https://openalex.org/keywords/electronic-health-records","display_name":"electronic health records","score":0.9860000014305115},{"id":"https://openalex.org/keywords/missing-data-mechanisms","display_name":"missing data mechanisms","score":0.718999981880188},{"id":"https://openalex.org/keywords/imputation-accuracy","display_name":"imputation accuracy","score":0.6819999814033508},{"id":"https://openalex.org/keywords/classification-performance","display_name":"classification performance","score":0.8479999899864197},{"id":"https://openalex.org/keywords/gain","display_name":"gain","score":0.843999981880188},{"id":"https://openalex.org/keywords/mice","display_name":"mice","score":0.9760000109672546},{"id":"https://openalex.org/keywords/missforest","display_name":"missForest","score":0.9909999966621399},{"id":"https://openalex.org/keywords/median-imputation","display_name":"median imputation","score":0.8579999804496765},{"id":"https://openalex.org/keywords/deep-learning-imputation","display_name":"deep learning imputation","score":0.8420000076293945}],"concepts":[{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.6855614185333252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5006999969482422},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34975332021713257},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.3484569787979126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16309157013893127}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.34133/hds.0493","doi":"https://doi.org/10.34133/hds.0493","is_oa":true,"landing_page_url":"https://doi.org/10.34133/hds.0493","pdf_url":null,"source":{"id":"https://openalex.org/S4210185134","display_name":"Health Data Science","issn_l":"2097-1095","issn":["2097-1095","2765-8783"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","ki-jl-1","oarl"],"host_organization":"https://openalex.org/P4310315823","host_organization_name":"American Association for the Advancement of Science","host_organization_lineage":["https://openalex.org/P4310315823"],"host_organization_lineage_names":["American Association for the Advancement of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Data Science","raw_type":"journal-article"},{"id":"doi:10.1101/2025.08.01.25332573","doi":"https://doi.org/10.1101/2025.08.01.25332573","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.08.01.25332573","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2025/08/05/2025.08.01.25332573.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},{"id":"pmh:oai:pubmedcentral.nih.gov:13724834","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13724834/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13724834/pdf/hds.0493.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Data Sci","raw_type":"Text"},{"id":"pmid:42973692","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42973692","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health data science","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:4abee50a138f48168b54680f89a572f3","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/4abee50a138f48168b54680f89a572f3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Health Data Science, Vol 6 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.34133/hds.0493","doi":"https://doi.org/10.34133/hds.0493","is_oa":true,"landing_page_url":"https://doi.org/10.34133/hds.0493","pdf_url":null,"source":{"id":"https://openalex.org/S4210185134","display_name":"Health Data Science","issn_l":"2097-1095","issn":["2097-1095","2765-8783"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","ki-jl-1","oarl"],"host_organization":"https://openalex.org/P4310315823","host_organization_name":"American Association for the Advancement of Science","host_organization_lineage":["https://openalex.org/P4310315823"],"host_organization_lineage_names":["American Association for the Advancement of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Data Science","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.8560000061988831}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2374448338","display_name":null,"funder_award_id":"62202332","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3672206126","display_name":null,"funder_award_id":"81602939","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5370040448","display_name":null,"funder_award_id":"92048301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G586450310","display_name":null,"funder_award_id":"23JCYBJC00360","funder_id":"https://openalex.org/F4320336756","funder_display_name":"Tianjin Science and Technology Program"},{"id":"https://openalex.org/G823259848","display_name":null,"funder_award_id":"\u202a62376197\u202c","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323993","display_name":"Natural Science Foundation of Tianjin City","ror":null},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"},{"id":"https://openalex.org/F4320328813","display_name":"Peking University People's Hospital","ror":"https://ror.org/035adwg89"},{"id":"https://openalex.org/F4320336756","display_name":"Tianjin Science and Technology Program","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413031079.pdf","grobid_xml":"https://content.openalex.org/works/W4413031079.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W788217788","https://openalex.org/W1537066827","https://openalex.org/W2009432182","https://openalex.org/W2064186732","https://openalex.org/W2096863518","https://openalex.org/W2115098571","https://openalex.org/W2158698691","https://openalex.org/W2169076391","https://openalex.org/W2396881363","https://openalex.org/W2581082906","https://openalex.org/W2803403013","https://openalex.org/W2806953728","https://openalex.org/W2808622828","https://openalex.org/W2891700678","https://openalex.org/W2911964244","https://openalex.org/W2963925452","https://openalex.org/W3154315590","https://openalex.org/W3205484571","https://openalex.org/W4296631245","https://openalex.org/W4381469650","https://openalex.org/W4387407668","https://openalex.org/W4388411165","https://openalex.org/W4391741122","https://openalex.org/W4400324874","https://openalex.org/W4400935987","https://openalex.org/W4401159367"],"related_works":["https://openalex.org/W7112810230","https://openalex.org/W4323022376","https://openalex.org/W7161394445","https://openalex.org/W7125135087","https://openalex.org/W7125513692","https://openalex.org/W2791458756","https://openalex.org/W7054389202","https://openalex.org/W4392506996","https://openalex.org/W2991395312","https://openalex.org/W7161398876"],"abstract_inverted_index":{"Abstract":[0],"Missing":[1],"data":[2,14,147],"is":[3],"a":[4,131],"persistent":[5],"challenge":[6],"in":[7,23,150],"electronic":[8],"health":[9],"records":[10],"(EHRs),":[11],"often":[12],"compromising":[13],"integrity":[15],"and":[16,37,49,51,63,70,79,100,141],"limiting":[17],"the":[18,65,118],"effectiveness":[19],"of":[20],"predictive":[21],"models":[22],"healthcare.":[24],"This":[25],"study":[26],"systematically":[27],"evaluates":[28],"five":[29],"widely":[30],"used":[31],"imputation":[32,57,68,108,126],"strategies\u2014GAIN,":[33],"MICE,":[34],"Median,":[35],"MissForest,":[36],"MIWAE\u2014across":[38],"three":[39],"real-world":[40],"clinical":[41,151],"datasets":[42],"under":[43,98],"varying":[44],"missingness":[45,52,105,139],"mechanisms":[46],"(MCAR,":[47],"MAR,":[48],"MNAR)":[50],"rates":[53],"(10%\u201390%).":[54],"We":[55,128],"assessed":[56],"quality":[58,109],"using":[59],"multiple":[60],"statistical":[61],"measures":[62],"examined":[64],"relationship":[66],"between":[67],"accuracy":[69],"downstream":[71],"classification":[72,115],"performance.":[73],"Our":[74],"results":[75],"show":[76],"that":[77],"MICE":[78],"MissForest":[80],"consistently":[81],"outperform":[82],"other":[83],"methods":[84],"across":[85],"most":[86],"scenarios,":[87],"while":[88],"deep":[89],"learning-based":[90],"approaches":[91],"such":[92],"as":[93],"GAIN":[94],"exhibit":[95],"high":[96],"instability":[97],"MAR":[99],"MNAR,":[101],"particularly":[102],"at":[103],"higher":[104],"levels.":[106],"Furthermore,":[107],"does":[110],"not":[111],"always":[112],"align":[113],"with":[114],"performance,":[116],"underscoring":[117],"need":[119],"to":[120,144],"consider":[121],"task-specific":[122],"goals":[123],"when":[124],"selecting":[125],"strategies.":[127],"also":[129],"provide":[130],"practical":[132],"framework":[133],"summarizing":[134],"method":[135],"recommendations":[136],"based":[137],"on":[138],"type":[140],"rate,":[142],"aiming":[143],"support":[145],"robust":[146],"preprocessing":[148],"decisions":[149],"AI":[152],"applications.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2025-10-10T00:00:00"}