{"id":"https://openalex.org/W7171497237","doi":"https://doi.org/10.1145/3807503.3819371","title":"HarmoMed: An Agentic Framework for Auditable Multimodal Biomedical Data Harmonization","display_name":"HarmoMed: An Agentic Framework for Auditable Multimodal Biomedical Data Harmonization","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7171497237","doi":"https://doi.org/10.1145/3807503.3819371"},"language":null,"primary_location":{"id":"doi:10.1145/3807503.3819371","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819371","pdf_url":null,"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 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3807503.3819371","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072301043","display_name":"Ismael Villanueva-Miranda","orcid":"https://orcid.org/0000-0002-6776-5484"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ismael Villanueva-Miranda","raw_affiliation_strings":["Health Data Science and Biostatistics, University of Texas Southwestern Medical Center, Dallas, Texas, USA"],"raw_orcid":"https://orcid.org/0000-0002-6776-5484","affiliations":[{"raw_affiliation_string":"Health Data Science and Biostatistics, University of Texas Southwestern Medical Center, Dallas, Texas, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068615078","display_name":"Zifan Gu","orcid":"https://orcid.org/0000-0002-8024-2629"},"institutions":[{"id":"https://openalex.org/I4210096815","display_name":"Southwestern Medical Center","ror":"https://ror.org/00t9vx427","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210096815"]},{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zifan Gu","raw_affiliation_strings":["Health Data Science and Biostatistics, University of Texas Southwestern Medical Center, Dallas, USA"],"raw_orcid":"https://orcid.org/0000-0002-8024-2629","affiliations":[{"raw_affiliation_string":"Health Data Science and Biostatistics, University of Texas Southwestern Medical Center, Dallas, USA","institution_ids":["https://openalex.org/I4210096815","https://openalex.org/I867280407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009964025","display_name":"Guanghua Xiao","orcid":"https://orcid.org/0000-0001-9387-9883"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanghua Xiao","raw_affiliation_strings":["Health Data Science and Biostatistics, University of Texas Southwestern Medical Center, Dallas, Texas, USA"],"raw_orcid":"https://orcid.org/0000-0001-9387-9883","affiliations":[{"raw_affiliation_string":"Health Data Science and Biostatistics, University of Texas Southwestern Medical Center, Dallas, Texas, USA","institution_ids":["https://openalex.org/I867280407"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100661771","display_name":"Yang Xie","orcid":"https://orcid.org/0000-0001-9456-1762"},"institutions":[{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Xie","raw_affiliation_strings":["Health Data Science and Biostatistics, University of Texas Southwestern Medical Center, Dallas, Texas, USA"],"raw_orcid":"https://orcid.org/0000-0001-9456-1762","affiliations":[{"raw_affiliation_string":"Health Data Science and Biostatistics, University of Texas Southwestern Medical Center, Dallas, Texas, USA","institution_ids":["https://openalex.org/I867280407"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/harmonization","display_name":"Harmonization","score":0.37130001187324524},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3321000039577484},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3301999866962433},{"id":"https://openalex.org/keywords/agency","display_name":"Agency (philosophy)","score":0.29580000042915344},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.26980000734329224},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.26420000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49939998984336853},{"id":"https://openalex.org/C2779962950","wikidata":"https://www.wikidata.org/wiki/Q5659376","display_name":"Harmonization","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.33059999346733093},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.32739999890327454},{"id":"https://openalex.org/C108170787","wikidata":"https://www.wikidata.org/wiki/Q3951828","display_name":"Agency (philosophy)","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2524000108242035},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3807503.3819371","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819371","pdf_url":null,"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 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3807503.3819371","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819371","pdf_url":null,"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 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2165748167","https://openalex.org/W2619383789","https://openalex.org/W2735812740","https://openalex.org/W2873590835","https://openalex.org/W2888828233","https://openalex.org/W2974544900","https://openalex.org/W2980112834","https://openalex.org/W3027572331","https://openalex.org/W3036508534","https://openalex.org/W3197731842","https://openalex.org/W4312460555","https://openalex.org/W4414452963"],"related_works":[],"abstract_inverted_index":{"Harmonizing":[0],"biomedical":[1,58],"datasets":[2,11,59,198],"remains":[3],"a":[4,50,61,77,155],"major":[5],"bottleneck":[6],"for":[7,54,94,194],"integrative":[8,195],"analysis":[9,184,196],"because":[10],"often":[12,28],"differ":[13],"in":[14],"column":[15],"names,":[16],"value":[17],"encodings,":[18],"terminologies,":[19],"and":[20,41,72,102,104,122,131,144,150,171,174,182,202,207],"table":[21],"structure.":[22],"In":[23],"practice,":[24],"these":[25],"differences":[26],"are":[27,36,210],"handled":[29],"with":[30,67,199],"custom":[31],"dataset-specific":[32],"curation":[33],"pipelines":[34],"that":[35],"difficult":[37],"to":[38,90,109,146],"validate,":[39],"audit,":[40],"reuse.":[42],"To":[43],"address":[44],"this":[45],"problem,":[46],"we":[47],"present":[48],"HarmoMed,":[49],"standards-aware,":[51],"agent-driven":[52],"framework":[53],"harmonizing":[55],"heterogeneous":[56],"multimodal":[57],"into":[60],"canonical":[62],"five-table":[63],"intermediate":[64],"representation":[65],"(IR)":[66],"Subject,":[68],"Study,":[69],"Artifact,":[70],"Label,":[71],"Evidence":[73],"tables.":[74],"HarmoMed":[75,133,168],"follows":[76],"schema-first":[78],"design.":[79],"It":[80],"first":[81],"summarizes":[82],"dataset":[83,95],"evidence":[84],"deterministically,":[85],"then":[86],"uses":[87,106],"LLM":[88],"agents":[89],"generate":[91],"typed":[92],"artifacts":[93],"profiling,":[96],"field":[97],"mapping,":[98],"normalization,":[99],"concept":[100],"linking,":[101],"constraints,":[103],"finally":[105],"deterministic":[107,123],"modules":[108],"construct":[110],"the":[111,126],"IR":[112],"from":[113],"those":[114],"validated":[115],"specifications.":[116],"This":[117],"separation":[118],"between":[119],"semantic":[120],"decisions":[121],"execution":[124],"makes":[125],"harmonization":[127],"process":[128],"explicit,":[129],"reproducible,":[130],"auditable.":[132],"also":[134],"integrates":[135],"local":[136],"terminology":[137],"resources,":[138],"including":[139],"LOINC,":[140],"SNOMED":[141],"CT,":[142],"RadLex,":[143],"UCUM,":[145],"support":[147],"standards-aware":[148],"coding":[149],"unit":[151],"validation":[152],"while":[153],"preserving":[154],"controlled":[156],"LOCAL":[157],"fallback":[158],"when":[159],"no":[160],"reliable":[161],"standard":[162],"match":[163],"is":[164],"available.":[165],"We":[166],"evaluate":[167],"on":[169],"PTB-XL":[170],"CheXpert":[172],"Plus":[173],"assess":[175],"structural":[176],"fidelity,":[177,181],"terminology-aware":[178],"coding,":[179],"unified-view":[180],"cross-dataset":[183],"readiness.":[185],"The":[186],"resulting":[187],"harmonized":[188],"layer":[189],"supports":[190],"unified":[191],"SQL":[192],"views":[193],"across":[197],"different":[200],"modalities":[201],"source":[203],"schemas.":[204],"Implementation":[205],"details":[206],"project":[208],"resources":[209],"available":[211],"at":[212],"https://github.com/ismaelvillanuevamiranda/HarmoMed.":[213]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2026-07-29T00:00:00"}
