{"id":"https://openalex.org/W7155162547","doi":"https://doi.org/10.1016/j.jbi.2026.105050","title":"Clinical document metadata extraction: A scoping review","display_name":"Clinical document metadata extraction: A scoping review","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7155162547","doi":"https://doi.org/10.1016/j.jbi.2026.105050","pmid":"https://pubmed.ncbi.nlm.nih.gov/42031124"},"language":"en","primary_location":{"id":"doi:10.1016/j.jbi.2026.105050","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.jbi.2026.105050","pdf_url":null,"source":{"id":"https://openalex.org/S11622463","display_name":"Journal of Biomedical Informatics","issn_l":"1532-0464","issn":["1532-0464","1532-0480"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.jbi.2026.105050","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110049408","display_name":"Kurt Miller","orcid":null},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"funder","lineage":["https://openalex.org/I1330342723"]},{"id":"https://openalex.org/I4210120349","display_name":"University of Minnesota Rochester","ror":"https://ror.org/02rh4fw73","country_code":"US","type":"education","lineage":["https://openalex.org/I4210120349"]},{"id":"https://openalex.org/I4210125099","display_name":"Mayo Clinic in Arizona","ror":"https://ror.org/03jp40720","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723","https://openalex.org/I4210125099"]},{"id":"https://openalex.org/I4210146710","display_name":"Mayo Clinic in Florida","ror":"https://ror.org/03zzw1w08","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723","https://openalex.org/I4210146710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kurt Miller","raw_affiliation_strings":["Bioinformatics and Computational Biology Program, University of Minnesota, Rochester, MN, USA; Center for Digital Health, Mayo Clinic, Rochester, MN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics and Computational Biology Program, University of Minnesota, Rochester, MN, USA; Center for Digital Health, Mayo Clinic, Rochester, MN, USA","institution_ids":["https://openalex.org/I4210146710","https://openalex.org/I4210120349","https://openalex.org/I4210125099","https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134294270","display_name":"Qiuhao Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiuhao Lu","raw_affiliation_strings":["McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134295214","display_name":"William Hersh","orcid":null},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Hersh","raw_affiliation_strings":["Division of Informatics, Clinical Epidemiology and Translational Data Science, Department of Medicine, Oregon Health & Science University, Portland, OR, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Informatics, Clinical Epidemiology and Translational Data Science, Department of Medicine, Oregon Health & Science University, Portland, OR, USA","institution_ids":["https://openalex.org/I165690674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134303483","display_name":"Kirk Roberts","orcid":null},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kirk Roberts","raw_affiliation_strings":["McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130640504","display_name":"Steven Bedrick","orcid":null},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Bedrick","raw_affiliation_strings":["Division of Informatics, Clinical Epidemiology and Translational Data Science, Department of Medicine, Oregon Health & Science University, Portland, OR, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Informatics, Clinical Epidemiology and Translational Data Science, Department of Medicine, Oregon Health & Science University, Portland, OR, USA","institution_ids":["https://openalex.org/I165690674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134224613","display_name":"Andrew Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Wen","raw_affiliation_strings":["McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101585391","display_name":"Hongfang Liu","orcid":"https://orcid.org/0000-0003-2570-3741"},"institutions":[{"id":"https://openalex.org/I4210159031","display_name":"The University of Texas Health Science Center","ror":"https://ror.org/05cwbxa29","country_code":"US","type":"education","lineage":["https://openalex.org/I4210159031"]},{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hongfang Liu","raw_affiliation_strings":["McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, USA. Electronic address: Hongfang.Liu@uth.tmc.edu"],"raw_orcid":"https://orcid.org/0000-0003-2570-3741","affiliations":[{"raw_affiliation_string":"McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, USA. Electronic address: Hongfang.Liu@uth.tmc.edu","institution_ids":["https://openalex.org/I4210159031","https://openalex.org/I919571938"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101585391"],"corresponding_institution_ids":["https://openalex.org/I4210159031","https://openalex.org/I919571938"],"apc_list":{"value":2980,"currency":"USD","value_usd":2980},"apc_paid":{"value":2980,"currency":"USD","value_usd":2980},"fwci":5.1191,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95232491,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"179","issue":null,"first_page":"105050","last_page":"105050"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.5370000004768372,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.5370000004768372,"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/T10350","display_name":"Electronic Health Records Systems","score":0.06159999966621399,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.031099999323487282,"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/metadata","display_name":"Metadata","score":0.9230999946594238},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.597599983215332},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.527999997138977},{"id":"https://openalex.org/keywords/geospatial-metadata","display_name":"Geospatial metadata","score":0.45680001378059387},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.44290000200271606},{"id":"https://openalex.org/keywords/meta-data-services","display_name":"Meta Data Services","score":0.40230000019073486},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.38370001316070557},{"id":"https://openalex.org/keywords/database-catalog","display_name":"Database catalog","score":0.3831999897956848}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9230999946594238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677000164985657},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6254000067710876},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.597599983215332},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.527999997138977},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4713999927043915},{"id":"https://openalex.org/C193150823","wikidata":"https://www.wikidata.org/wiki/Q1477538","display_name":"Geospatial metadata","level":5,"score":0.45680001378059387},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4180999994277954},{"id":"https://openalex.org/C136976847","wikidata":"https://www.wikidata.org/wiki/Q6822297","display_name":"Meta Data Services","level":4,"score":0.40230000019073486},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C65610166","wikidata":"https://www.wikidata.org/wiki/Q5227399","display_name":"Database catalog","level":4,"score":0.3831999897956848},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.38109999895095825},{"id":"https://openalex.org/C98143201","wikidata":"https://www.wikidata.org/wiki/Q1147639","display_name":"Data dictionary","level":3,"score":0.31779998540878296},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.2989000082015991},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.26930001378059387},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.257999986410141},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.25110000371932983}],"mesh":[{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D009323","descriptor_name":"Natural Language Processing","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":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1016/j.jbi.2026.105050","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.jbi.2026.105050","pdf_url":null,"source":{"id":"https://openalex.org/S11622463","display_name":"Journal of Biomedical Informatics","issn_l":"1532-0464","issn":["1532-0464","1532-0480"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Informatics","raw_type":"journal-article"},{"id":"pmid:42031124","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42031124","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 biomedical informatics","raw_type":null}],"best_oa_location":{"id":"doi:10.1016/j.jbi.2026.105050","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.jbi.2026.105050","pdf_url":null,"source":{"id":"https://openalex.org/S11622463","display_name":"Journal of Biomedical Informatics","issn_l":"1532-0464","issn":["1532-0464","1532-0480"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Informatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5187827348709106}],"awards":[],"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":60,"referenced_works":["https://openalex.org/W1019512417","https://openalex.org/W1541954861","https://openalex.org/W1752751552","https://openalex.org/W1929032064","https://openalex.org/W1971360647","https://openalex.org/W1983850915","https://openalex.org/W2091398914","https://openalex.org/W2106419350","https://openalex.org/W2120989936","https://openalex.org/W2167357104","https://openalex.org/W2293452551","https://openalex.org/W2343760456","https://openalex.org/W2396881363","https://openalex.org/W2463981085","https://openalex.org/W2772121968","https://openalex.org/W2778088240","https://openalex.org/W2883657435","https://openalex.org/W2888318791","https://openalex.org/W2891378911","https://openalex.org/W2901669506","https://openalex.org/W2950509749","https://openalex.org/W2958747773","https://openalex.org/W2967034651","https://openalex.org/W2969234416","https://openalex.org/W2971538598","https://openalex.org/W3092930902","https://openalex.org/W3101984434","https://openalex.org/W3139245306","https://openalex.org/W3183363647","https://openalex.org/W3206672312","https://openalex.org/W3208292737","https://openalex.org/W4294215472","https://openalex.org/W4294713542","https://openalex.org/W4313171360","https://openalex.org/W4313492037","https://openalex.org/W4317614181","https://openalex.org/W4318617392","https://openalex.org/W4362467159","https://openalex.org/W4365517815","https://openalex.org/W4385496630","https://openalex.org/W4386855366","https://openalex.org/W4387707777","https://openalex.org/W4389281288","https://openalex.org/W4390097263","https://openalex.org/W4390388749","https://openalex.org/W4391116490","https://openalex.org/W4394912543","https://openalex.org/W4399994870","https://openalex.org/W4401542090","https://openalex.org/W4403278709","https://openalex.org/W4405350114","https://openalex.org/W4406985394","https://openalex.org/W4408145721","https://openalex.org/W4410397695","https://openalex.org/W4410977016","https://openalex.org/W4411183236","https://openalex.org/W4411203672","https://openalex.org/W4413784171","https://openalex.org/W4414709732","https://openalex.org/W4415321968"],"related_works":[],"abstract_inverted_index":{"OBJECTIVES:":[0],"Clinical":[1,234],"document":[2,6,38,63,113,171,182,209,235,279],"metadata,":[3],"such":[4],"as":[5,118,123,173],"type,":[7],"structure,":[8],"author":[9],"role,":[10],"medical":[11],"specialty,":[12],"and":[13,31,69,71,88,107,136,143,179,192,216,258,282,288],"encounter":[14],"setting,":[15],"is":[16],"essential":[17],"for":[18,85,91,126,131,189,202,207],"accurate":[19],"interpretation":[20],"of":[21,37,105,246,254,263],"information":[22],"captured":[23],"in":[24,161,175],"clinical":[25,62,112,265,286],"documents.":[26],"However,":[27],"vast":[28],"documentation":[29],"heterogeneity":[30],"drift":[32],"over":[33,241],"time":[34],"challenge":[35],"harmonization":[36],"metadata.":[39],"Automated":[40],"extraction":[41,237],"methods":[42],"have":[43,211],"emerged":[44],"to":[45,58,95,152,224,275],"coalesce":[46],"metadata":[47,64,114,172,183,210,236,280],"from":[48,98,213],"disparate":[49],"practices":[50],"into":[51,277,285],"target":[52],"schema.":[53],"This":[54],"scoping":[55],"review":[56],"aims":[57],"catalog":[59],"research":[60,238,272],"on":[61],"extraction,":[65,115],"identify":[66,96],"methodological":[67,190],"trends":[68],"applications,":[70],"highlight":[72],"gaps":[73],"warranting":[74],"further":[75,284],"investigation.":[76],"METHODS:":[77],"We":[78,133,185,269],"followed":[79],"the":[80,157,261],"PRISMA-ScR":[81],"(Preferred":[82],"Reporting":[83],"Items":[84],"Systematic":[86],"Reviews":[87],"Meta-Analyses":[89],"Extension":[90],"Scoping":[92],"Reviews)":[93],"guidelines":[94],"articles":[97,139,159],"Ovid":[99,101],"MEDLINE,":[100],"EMBASE,":[102],"Scopus,":[103],"Web":[104],"Science":[106],"external":[108],"sources":[109],"that":[110,271],"perform":[111],"either":[116],"primarily":[117],"a":[119,124,127,176],"methodology":[120],"study,":[121],"secondarily":[122],"feature":[125,222,229],"downstream":[128,177],"application,":[129,178],"or":[130],"analysis.":[132],"initially":[134],"identified":[135],"screened":[137],"342":[138],"published":[140],"between":[141],"2011":[142],"2025,":[144],"then":[145],"comprehensively":[146],"reviewed":[147],"77":[148,158],"we":[149],"deemed":[150],"relevant":[151],"our":[153,162],"study.":[154],"RESULTS:":[155],"Among":[156],"included":[160],"full":[163],"text":[164,266],"review,":[165],"49":[166],"were":[167],"methodological,":[168],"22":[169],"used":[170],"features":[174],"6":[180],"analyzed":[181],"composition.":[184],"observe":[186],"myriad":[187],"purposes":[188],"study":[191],"application":[193],"types.":[194],"Available":[195],"labelled":[196],"public":[197],"data":[198],"remains":[199],"sparse":[200],"except":[201],"structural":[203],"section":[204],"datasets.":[205],"Methods":[206],"extracting":[208],"progressed":[212],"largely":[214],"rule-based":[215],"traditional":[217],"machine":[218],"learning":[219],"with":[220,227],"ample":[221],"engineering":[223],"transformer-based":[225],"architectures":[226],"minimal":[228],"engineering.":[230],"DISCUSSION":[231],"AND":[232],"CONCLUSION:":[233],"has":[239,250],"accelerated":[240],"recent":[242],"years.":[243],"The":[244],"emergence":[245],"large":[247],"language":[248],"models":[249],"enabled":[251],"broader":[252],"exploration":[253],"generalizability":[255],"across":[256],"tasks":[257],"datasets,":[259],"allowing":[260],"possibility":[262],"advanced":[264],"processing":[267],"systems.":[268],"anticipate":[270],"will":[273],"continue":[274],"expand":[276],"richer":[278],"representations":[281],"integrate":[283],"applications":[287],"workflows.":[289]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-08T13:12:06.581006","created_date":"2026-04-23T00:00:00"}
