{"id":"https://openalex.org/W7129006460","doi":"https://doi.org/10.1109/tcbbio.2026.3665199","title":"SCImputation: Mitigating Feature Confounding From a Structural Causal Perspective for Data Imputation","display_name":"SCImputation: Mitigating Feature Confounding From a Structural Causal Perspective for Data Imputation","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129006460","doi":"https://doi.org/10.1109/tcbbio.2026.3665199","pmid":"https://pubmed.ncbi.nlm.nih.gov/41697814"},"language":"en","primary_location":{"id":"doi:10.1109/tcbbio.2026.3665199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbbio.2026.3665199","pdf_url":null,"source":{"id":"https://openalex.org/S5407042751","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"2998-4165","issn":["2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106902083","display_name":"Yue Yin","orcid":"https://orcid.org/0000-0001-5049-5468"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Yin","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5049-5468","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079824167","display_name":"Jiaoyun Yang","orcid":"https://orcid.org/0000-0002-0233-590X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaoyun Yang","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-0233-590X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126134292","display_name":"Ning An","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning An","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-3317-5299","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1983866,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"2","first_page":"891","last_page":"903"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.18070000410079956,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.18070000410079956,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.11980000138282776,"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/T10136","display_name":"Statistical Methods and Inference","score":0.08129999786615372,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/imputation","display_name":"Imputation (statistics)","score":0.8823000192642212},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.7942000031471252},{"id":"https://openalex.org/keywords/confounding","display_name":"Confounding","score":0.5659000277519226},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4993000030517578},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.48170000314712524},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.29600000381469727}],"concepts":[{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.8823000192642212},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.7942000031471252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5753999948501587},{"id":"https://openalex.org/C77350462","wikidata":"https://www.wikidata.org/wiki/Q1125472","display_name":"Confounding","level":2,"score":0.5659000277519226},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.557200014591217},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.48170000314712524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3944999873638153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3926999866962433},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.27149999141693115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.251800000667572}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbbio.2026.3665199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbbio.2026.3665199","pdf_url":null,"source":{"id":"https://openalex.org/S5407042751","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"2998-4165","issn":["2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41697814","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41697814","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,"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":"IEEE transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6515849855","display_name":"\u5927\u6570\u636e\u5e94\u7528\u4e2d\u975e\u6982\u7387\u6027\u62bd\u6837\u7684\u8bc4\u4f30\u53ca\u7b97\u6cd5\u7814\u7a76","funder_award_id":"62072153","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6942414739","display_name":null,"funder_award_id":"B14025","funder_id":"https://openalex.org/F4320335785","funder_display_name":"Project 211"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335785","display_name":"Project 211","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Missing":[0],"data":[1,7,76,215],"remain":[2],"a":[3,70,90,107,122,210],"critical":[4],"challenge":[5],"in":[6,57,180,185,217],"analysis,":[8],"often":[9,55],"leading":[10,196],"to":[11,48,74,116],"biased":[12],"estimates":[13,129],"and":[14,61,92,113,120,148,150,162,182,191,220],"reduced":[15],"reliability.":[16],"Many":[17],"imputation":[18,216],"methods,":[19],"operating":[20],"under":[21],"the":[22,32,36,40,81,131,136,140,152,163,188],"assumption":[23],"that":[24,79,109,126,207],"similar":[25,28],"instances":[26],"share":[27],"feature":[29,37,83],"values,":[30],"overlook":[31],"pivotal":[33],"role":[34],"of":[35],"associated":[38],"with":[39,130,146,167],"missing":[41,50],"value.":[42],"Consequently,":[43],"they":[44],"apply":[45],"uniform":[46],"strategies":[47],"all":[49],"values":[51],"within":[52],"an":[53],"instance,":[54],"resulting":[56,153],"suboptimal":[58],"neighbor":[59,85,118],"sets":[60],"less":[62],"accurate":[63],"predictions.":[64],"In":[65,170],"this":[66,99],"paper,":[67],"we":[68,101],"adopt":[69],"structural":[71],"causal":[72],"perspective":[73],"examine":[75],"imputation,":[77],"revealing":[78],"once":[80],"target":[82,141],"guides":[84],"selection,":[86,119],"it":[87],"acts":[88],"as":[89],"confounder":[91],"biases":[93],"subsequent":[94],"missing-value":[95],"estimations.":[96],"Building":[97],"on":[98,155],"insight,":[100],"propose":[102],"Structural":[103],"Causal":[104],"Imputation":[105],"(SCImputation),":[106],"strategy":[108,213],"leverages":[110],"both":[111,218],"instance-level":[112],"feature-level":[114],"information":[115],"refine":[117],"applies":[121],"back-door":[123],"adjustment":[124],"formula":[125],"reweights":[127],"local":[128],"global":[132],"distribution,":[133],"thereby":[134],"mitigating":[135],"confounding":[137],"introduced":[138],"by":[139],"feature.":[142],"We":[143],"integrate":[144],"SCImputation":[145,176,208],"KNNimpute":[147],"LLSimpute,":[149],"evaluate":[151],"variants":[154],"five":[156],"datasets":[157],"(NACC,":[158],"three":[159],"NCBI":[160],"microarrays,":[161],"Turkiye":[164],"Student":[165],"Evaluation)":[166],"ablation":[168],"studies.":[169],"comparative":[171],"evaluations":[172],"against":[173,195],"12":[174],"baselines,":[175],"achieves":[177],"3.0%-4.6%":[178],"gains":[179],"accuracy":[181],"0.009-0.059":[183],"reductions":[184],"RMSE":[186],"over":[187],"established":[189],"approaches,":[190],"demonstrates":[192],"competitive":[193],"performance":[194],"deep":[197],"learning":[198],"baselines":[199],"across":[200],"diverse":[201],"missingness":[202],"mechanisms.":[203],"These":[204],"results":[205],"suggest":[206],"provides":[209],"causally":[211],"grounded":[212],"for":[214],"biomedical":[219],"general":[221],"applications.":[222]},"counts_by_year":[],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2026-02-17T00:00:00"}