{"id":"https://openalex.org/W3114962450","doi":"https://doi.org/10.1093/jamia/ocaa309","title":"UMLS-based data augmentation for natural language processing of clinical research literature","display_name":"UMLS-based data augmentation for natural language processing of clinical research literature","publication_year":2020,"publication_date":"2020-11-23","ids":{"openalex":"https://openalex.org/W3114962450","doi":"https://doi.org/10.1093/jamia/ocaa309","mag":"3114962450","pmid":"https://pubmed.ncbi.nlm.nih.gov/33367705"},"language":"en","primary_location":{"id":"doi:10.1093/jamia/ocaa309","is_oa":false,"landing_page_url":"https://doi.org/10.1093/jamia/ocaa309","pdf_url":null,"source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7973470","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000333588","display_name":"Tian Kang","orcid":"https://orcid.org/0000-0002-8460-7525"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Kang","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University, New York, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University, New York, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021255571","display_name":"Adler Perotte","orcid":"https://orcid.org/0000-0002-6695-0282"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adler Perotte","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University, New York, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University, New York, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087205663","display_name":"Youlan Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youlan Tang","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University, New York, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University, New York, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051450267","display_name":"Casey Ta","orcid":"https://orcid.org/0000-0002-4679-805X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Casey Ta","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University, New York, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University, New York, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009604048","display_name":"Chunhua Weng","orcid":"https://orcid.org/0000-0002-9624-0214"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chunhua Weng","raw_affiliation_strings":["Department of Biomedical Informatics, Columbia University, New York, New York, USA"],"raw_orcid":"https://orcid.org/0000-0002-9624-0214","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Columbia University, New York, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5009604048"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":null,"fwci":4.3024,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.95353338,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"28","issue":"4","first_page":"812","last_page":"823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.43689998984336853,"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":0.43689998984336853,"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":0.24959999322891235,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.18770000338554382,"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/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.9420638084411621},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8085297346115112},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.73773592710495},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6919077634811401},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6284009218215942},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5777908563613892},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43089088797569275},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4300718605518341},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.41559216380119324}],"concepts":[{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.9420638084411621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8085297346115112},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.73773592710495},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6919077634811401},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6284009218215942},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5777908563613892},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43089088797569275},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4300718605518341},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.41559216380119324},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000079803","descriptor_name":"Data Management","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000079803","descriptor_name":"Data Management","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000079803","descriptor_name":"Data Management","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/jamia/ocaa309","is_oa":false,"landing_page_url":"https://doi.org/10.1093/jamia/ocaa309","pdf_url":null,"source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},{"id":"pmid:33367705","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33367705","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":"Journal of the American Medical Informatics Association : JAMIA","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:7973470","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7973470","pdf_url":null,"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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Am Med Inform Assoc","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:7973470","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7973470","pdf_url":null,"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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Am Med Inform Assoc","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2912063694","display_name":null,"funder_award_id":"R01 LM009886","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G5922379911","display_name":null,"funder_award_id":"5R01LM009886-11","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1572319397","https://openalex.org/W1583116580","https://openalex.org/W2035682999","https://openalex.org/W2062458775","https://openalex.org/W2088212219","https://openalex.org/W2134568263","https://openalex.org/W2146668368","https://openalex.org/W2147994374","https://openalex.org/W2593758073","https://openalex.org/W2595840341","https://openalex.org/W2624697962","https://openalex.org/W2776581140","https://openalex.org/W2905810301","https://openalex.org/W2911489562","https://openalex.org/W2914123081","https://openalex.org/W2927032858","https://openalex.org/W2947607756","https://openalex.org/W2964179635","https://openalex.org/W2965166224","https://openalex.org/W2968771432","https://openalex.org/W2980993994","https://openalex.org/W6768822636"],"related_works":["https://openalex.org/W4206357785","https://openalex.org/W3192840557","https://openalex.org/W4281381188","https://openalex.org/W2951211570","https://openalex.org/W3149011051","https://openalex.org/W4375928479","https://openalex.org/W3167935049","https://openalex.org/W3023427754","https://openalex.org/W3131673289","https://openalex.org/W3198847674"],"abstract_inverted_index":{"OBJECTIVE:":[0],"The":[1,139],"study":[2,160],"sought":[3],"to":[4,13,65,86,149],"develop":[5],"and":[6,57,80,112,129,179,182],"evaluate":[7,67],"a":[8,162],"knowledge-based":[9],"data":[10,29,38,164],"augmentation":[11,39,165],"method":[12,41,60],"improve":[14],"the":[15,36,50,68,97,115,131,134],"performance":[16,132],"of":[17,70,133],"deep":[18,74,173,190],"learning":[19,75,125,174,191],"models":[20,175],"for":[21,42,77,93,176,186,193],"biomedical":[22,43,195],"natural":[23],"language":[24],"processing":[25],"by":[26,48,126],"overcoming":[27],"training":[28],"scarcity.":[30],"MATERIALS":[31],"AND":[32],"METHODS:":[33],"We":[34,62,82],"extended":[35],"easy":[37],"(EDA)":[40],"named":[44],"entity":[45],"recognition":[46],"(NER)":[47],"incorporating":[49],"Unified":[51],"Medical":[52],"Language":[53],"System":[54],"(UMLS)":[55],"knowledge":[56],"called":[58],"this":[59],"UMLS-EDA.":[61,167],"designed":[63],"experiments":[64],"systematically":[66],"effect":[69],"UMLS-EDA":[71,85,89],"on":[72,142],"popular":[73],"architectures":[76],"both":[78,177],"NER":[79,94,178],"classification.":[81],"also":[83],"compared":[84],"BERT.":[87],"RESULTS:":[88],"enables":[90],"substantial":[91],"improvement":[92],"tasks":[95],"from":[96,147],"original":[98,184],"long":[99],"short-term":[100],"memory":[101],"conditional":[102],"random":[103],"fields":[104],"(LSTM-CRF)":[105],"model":[106,117],"(micro-F1":[107,118],"score:":[108,119],"+5%,":[109],"+":[110],"17%,":[111],"+15%),":[113],"helps":[114],"LSTM-CRF":[116,122],"0.66)":[120],"outperform":[121],"with":[123,154],"transfer":[124],"BERT":[127,155],"(0.63),":[128],"improves":[130],"state-of-the-art":[135],"sentence":[136,180],"classification":[137],"model.":[138],"largest":[140],"gain":[141],"micro-F1":[143],"score":[144],"is":[145,169],"9%,":[146],"0.75":[148],"0.84,":[150],"better":[151],"than":[152],"classifiers":[153],"pretraining":[156],"(0.82).":[157],"CONCLUSIONS:":[158],"This":[159],"presents":[161],"UMLS-based":[163],"method,":[166],"It":[168],"effective":[170],"at":[171],"improving":[172],"classification,":[181],"contributes":[183],"insights":[185],"designing":[187],"new,":[188],"superior":[189],"approaches":[192],"low-resource":[194],"domains.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":7}],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2025-10-10T00:00:00"}