{"id":"https://openalex.org/W4416035601","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1465","title":"Causal Representation Learning from Multimodal Clinical Records under Non-Random Modality Missingness","display_name":"Causal Representation Learning from Multimodal Clinical Records under Non-Random Modality Missingness","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035601","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1465"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1465","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1465","pdf_url":"https://aclanthology.org/2025.emnlp-main.1465.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1465.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057994068","display_name":"Zihan Liang","orcid":"https://orcid.org/0009-0003-2373-1439"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]},{"id":"https://openalex.org/I177855293","display_name":"Emory and Henry College","ror":"https://ror.org/018rbev86","country_code":"US","type":"education","lineage":["https://openalex.org/I177855293"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zihan Liang","raw_affiliation_strings":["Emory University Emory University Emory University"],"affiliations":[{"raw_affiliation_string":"Emory University Emory University Emory University","institution_ids":["https://openalex.org/I150468666","https://openalex.org/I177855293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114071953","display_name":"Ziwen Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]},{"id":"https://openalex.org/I177855293","display_name":"Emory and Henry College","ror":"https://ror.org/018rbev86","country_code":"US","type":"education","lineage":["https://openalex.org/I177855293"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziwen Pan","raw_affiliation_strings":["Emory University Emory University Emory University"],"affiliations":[{"raw_affiliation_string":"Emory University Emory University Emory University","institution_ids":["https://openalex.org/I150468666","https://openalex.org/I177855293"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036061838","display_name":"Ruoxuan Xiong","orcid":"https://orcid.org/0000-0002-3701-4428"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]},{"id":"https://openalex.org/I177855293","display_name":"Emory and Henry College","ror":"https://ror.org/018rbev86","country_code":"US","type":"education","lineage":["https://openalex.org/I177855293"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruoxuan Xiong","raw_affiliation_strings":["Emory University Emory University Emory University"],"affiliations":[{"raw_affiliation_string":"Emory University Emory University Emory University","institution_ids":["https://openalex.org/I150468666","https://openalex.org/I177855293"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057994068"],"corresponding_institution_ids":["https://openalex.org/I150468666","https://openalex.org/I177855293"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18406531,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28779","last_page":"28796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.5788000226020813,"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"}},"topics":[{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.5788000226020813,"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/T10028","display_name":"Topic Modeling","score":0.06970000267028809,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.049800001084804535,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.5365999937057495},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4814999997615814},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46810001134872437},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.3310000002384186},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.30000001192092896},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2985000014305115}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5916000008583069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5428000092506409},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.5365999937057495},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.503000020980835},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46810001134872437},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3619999885559082},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.326200008392334},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.26570001244544983},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1465","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1465","pdf_url":"https://aclanthology.org/2025.emnlp-main.1465.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1465","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1465","pdf_url":"https://aclanthology.org/2025.emnlp-main.1465.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035601.pdf","grobid_xml":"https://content.openalex.org/works/W4416035601.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Clinical":[0],"notes":[1,36],"contain":[2],"rich":[3],"patient":[4,15,133],"information,":[5],"such":[6,56,65],"as":[7,66],"diagnoses":[8],"or":[9,71],"medications,":[10],"making":[11],"them":[12],"valuable":[13],"for":[14,165,191,198],"representation":[16,97,151],"learning.Recent":[17],"advances":[18],"in":[19,41,89,107,150],"large":[20],"language":[21],"models":[22],"have":[23,51],"further":[24],"improved":[25],"the":[26,45,74,182],"ability":[27],"to":[28,131,146,187,203],"extract":[29],"meaningful":[30],"representations":[31,58],"from":[32,62,168],"clinical":[33,35,82,109],"texts.However,":[34],"are":[37],"often":[38],"missing.For":[39],"example,":[40],"our":[42],"analysis":[43],"of":[44,49,76],"MIMIC-IV":[46,175],"dataset,":[47],"24.5%":[48],"patients":[50],"no":[52],"available":[53],"discharge":[54],"summaries.In":[55],"cases,":[57],"can":[59],"be":[60],"learned":[61],"other":[63],"modalities":[64,78],"structured":[67,121],"data,":[68,122],"chest":[69],"X-rays,":[70],"radiology":[72],"reports.Yet":[73],"availability":[75],"these":[77],"is":[79],"influenced":[80],"by":[81],"decision-making":[83],"and":[84,104,124,135,153,176,194],"varies":[85],"across":[86,174],"patients,":[87],"resulting":[88],"modality":[90,116,140,170],"missingnot-at-random":[91],"(MMNAR)":[92],"patterns.We":[93],"propose":[94],"a":[95,139,155,161],"causal":[96],"learning":[98,145],"framework":[99],"that":[100,119,163],"leverages":[101],"observed":[102],"data":[103],"informative":[105],"missingness":[106,129],"multimodal":[108],"records.It":[110],"consists":[111],"of:":[112],"(1)":[113],"an":[114],"MMNAR-aware":[115],"fusion":[117],"component":[118,142],"integrates":[120],"imaging,":[123],"text":[125],"while":[126],"conditioning":[127],"on":[128],"patterns":[130],"capture":[132],"health":[134],"clinician-driven":[136],"assignment;":[137],"(2)":[138],"reconstruction":[141],"with":[143,160],"contrastive":[144],"ensure":[147],"semantic":[148],"sufficiency":[149],"learning;":[152],"(3)":[154],"multitask":[156],"outcome":[157],"prediction":[158],"model":[159],"rectifier":[162],"corrects":[164],"residual":[166],"bias":[167],"specific":[169],"observation":[171],"patterns.Comprehensive":[172],"evaluations":[173],"eICU":[177],"show":[178],"consistent":[179],"gains":[180],"over":[181],"strongest":[183],"baselines,":[184],"achieving":[185],"up":[186],"13":[188,195],".8%":[189],"improvement":[190],"hospital":[192],"readmission":[193],".1":[196],"%":[197],"ICU":[199],"admission":[200],"(AUC,":[201],"relative":[202],"best":[204],"baseline).":[205]},"counts_by_year":[],"updated_date":"2026-03-10T14:07:55.174380","created_date":"2025-11-08T00:00:00"}