{"id":"https://openalex.org/W2912908635","doi":"https://doi.org/10.1109/bigdata.2018.8621999","title":"Retrofitting Word Embeddings with the UMLS Metathesaurus for Clinical Information Extraction","display_name":"Retrofitting Word Embeddings with the UMLS Metathesaurus for Clinical Information Extraction","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2912908635","doi":"https://doi.org/10.1109/bigdata.2018.8621999","mag":"2912908635"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2018.8621999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8621999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/1491322","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079607802","display_name":"Mohammed Alawad","orcid":"https://orcid.org/0000-0002-7491-0440"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammed Alawad","raw_affiliation_strings":["Biomedical Sciences, Engineering, and Computing Group Health Data Science Institute, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Sciences, Engineering, and Computing Group Health Data Science Institute, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103127954","display_name":"Shohedul Hasan","orcid":"https://orcid.org/0000-0002-0610-1668"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S.M. Shamimul Hasan","raw_affiliation_strings":["Biomedical Sciences, Engineering, and Computing Group Health Data Science Institute, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Sciences, Engineering, and Computing Group Health Data Science Institute, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037444677","display_name":"J. Blair Christian","orcid":"https://orcid.org/0000-0002-4658-1635"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Blair Christian","raw_affiliation_strings":["Biomedical Sciences, Engineering, and Computing Group Health Data Science Institute, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Sciences, Engineering, and Computing Group Health Data Science Institute, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014968146","display_name":"Georgia D. Tourassi","orcid":"https://orcid.org/0000-0002-9418-9638"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Georgia Tourassi","raw_affiliation_strings":["Biomedical Sciences, Engineering, and Computing Group Health Data Science Institute, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Sciences, Engineering, and Computing Group Health Data Science Institute, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8585,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.89413735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2838","last_page":"2846"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.8291016817092896},{"id":"https://openalex.org/keywords/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.7843246459960938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7370774149894714},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7311845421791077},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6245569586753845},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5711535215377808},{"id":"https://openalex.org/keywords/distributional-semantics","display_name":"Distributional semantics","score":0.527855396270752},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.47419577836990356},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.46670055389404297},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45275235176086426},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.44319653511047363},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44144442677497864},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4234811067581177},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3989224433898926},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.14900359511375427},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10532310605049133}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8291016817092896},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.7843246459960938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7370774149894714},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7311845421791077},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6245569586753845},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5711535215377808},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.527855396270752},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.47419577836990356},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.46670055389404297},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45275235176086426},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44319653511047363},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44144442677497864},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4234811067581177},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3989224433898926},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.14900359511375427},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10532310605049133},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2018.8621999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8621999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1491322","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1491322","pdf_url":"https://www.osti.gov/servlets/purl/1491322","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1491322","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1491322","pdf_url":"https://www.osti.gov/servlets/purl/1491322","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1489425746","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1719536385","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2584197162","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G675320460","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G7995982022","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8269158468","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2912908635.pdf","grobid_xml":"https://content.openalex.org/works/W2912908635.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1503259811","https://openalex.org/W1614298861","https://openalex.org/W1832693441","https://openalex.org/W1995945562","https://openalex.org/W2012560661","https://openalex.org/W2076424959","https://openalex.org/W2104321900","https://openalex.org/W2153579005","https://openalex.org/W2162311237","https://openalex.org/W2170240176","https://openalex.org/W2173884055","https://openalex.org/W2214968004","https://openalex.org/W2250930514","https://openalex.org/W2461583636","https://openalex.org/W2527825388","https://openalex.org/W2611254939","https://openalex.org/W2739271820","https://openalex.org/W2741908740","https://openalex.org/W2770260627","https://openalex.org/W2962784628","https://openalex.org/W2963012544","https://openalex.org/W2963083845","https://openalex.org/W2964232431","https://openalex.org/W4294170691","https://openalex.org/W4297790778","https://openalex.org/W6629815555","https://openalex.org/W6636510571","https://openalex.org/W6682691769","https://openalex.org/W6685053522","https://openalex.org/W6688209164","https://openalex.org/W6696511012","https://openalex.org/W6719208259","https://openalex.org/W6742033151","https://openalex.org/W6746393671"],"related_works":["https://openalex.org/W2963364736","https://openalex.org/W2808113865","https://openalex.org/W2061150891","https://openalex.org/W2118772635","https://openalex.org/W4235405867","https://openalex.org/W4366284213","https://openalex.org/W3181580843","https://openalex.org/W2555342309","https://openalex.org/W909526553","https://openalex.org/W4322735487"],"abstract_inverted_index":{"Deep":[0],"learning":[1,33],"has":[2],"surged":[3],"in":[4,62,65,73],"popularity":[5],"and":[6,38,132,157,200,207],"proven":[7],"to":[8,35,41,53,67,82,102,116,142,215,224],"be":[9,39,225],"effective":[10],"for":[11,190,202,227],"various":[12],"artificial":[13],"intelligence":[14],"applications":[15],"including":[16],"information":[17,50,70,228],"extraction":[18],"from":[19,121,231],"cancer":[20,122],"pathology":[21,123,233],"reports.":[22,234],"Since":[23],"word":[24,106,144,155,161,217],"representation":[25,45,87],"is":[26,213],"a":[27,111,164,182],"core":[28],"unit":[29],"that":[30,137],"enables":[31],"deep":[32],"algorithms":[34,56],"understand":[36],"words":[37,72,89],"able":[40],"perform":[42],"NLP,":[43],"this":[44,63],"must":[46],"include":[47],"as":[48,51],"much":[49],"possible":[52],"help":[54],"these":[55],"achieve":[57],"high":[58],"classification":[59],"performance.":[60],"Therefore,":[61],"work":[64],"addition":[66],"the":[68,84,91,178,186,191,195],"distributional":[69],"of":[71,88,146],"large":[74],"sized":[75],"corpora,":[76],"we":[77],"use":[78],"UMLS":[79,139],"vocabulary":[80,140],"resources":[81,97,141,223],"enrich":[83,143,216],"vector":[85],"space":[86],"with":[90,110,159,219],"semantic":[92],"relations":[93],"between":[94],"words.":[95],"These":[96],"provide":[98],"many":[99],"terminologies":[100],"pertaining":[101],"cancer.":[103],"The":[104,172],"refined":[105],"embeddings":[107,145,156,162,218],"are":[108,197],"used":[109,226],"convolutional":[112],"neural":[113],"(CNN)":[114],"model":[115],"extract":[117],"four":[118,170],"data":[119,222],"elements":[120],"reports;":[124],"ICD-O-3":[125],"tumor":[126,129,203],"topography":[127],"codes,":[128],"laterality,":[130],"behavior,":[131],"histological":[133,205],"grade.":[134],"We":[135],"observed":[136],"using":[138],"CNN":[147,151],"models":[148,152],"consistently":[149],"outperformed":[150],"without":[153],"pre-training":[154],"even":[158],"pre-trained":[160],"on":[163,177,185],"domain":[165],"specific":[166],"corpus":[167],"across":[168],"all":[169],"tasks.":[171],"results":[173],"show":[174],"marginal":[175],"improvement":[176,184],"laterality":[179],"task,":[180],"but":[181],"significant":[183],"other":[187],"tasks,":[188,209],"especially":[189],"macro-f":[192],"score.":[193],"Specifically,":[194],"improvements":[196],"3%,":[198],"13%,":[199],"15%":[201],"site,":[204],"grade,":[206],"behavior":[208],"respectively.":[210],"This":[211],"approach":[212],"encouraging":[214],"more":[220],"clinical":[221,232],"abstraction":[229],"tasks":[230]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-23T13:55:30.953635","created_date":"2025-10-10T00:00:00"}