{"id":"https://openalex.org/W7224893910","doi":"https://doi.org/10.3389/frai.2026.1927272","title":"Granular by design: a fine-grained NER approach to context-aware medication extraction","display_name":"Granular by design: a fine-grained NER approach to context-aware medication extraction","publication_year":2026,"publication_date":"2026-10-30","ids":{"openalex":"https://openalex.org/W7224893910","doi":"https://doi.org/10.3389/frai.2026.1927272"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2026.1927272","doi":"https://doi.org/10.3389/frai.2026.1927272","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2026.1927272","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2026.1927272/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2026.1927272/pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117771498","display_name":"Andr\u00e1s Berzi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I132735039","display_name":"University of Debrecen","ror":"https://ror.org/02xf66n48","country_code":"HU","type":"education","lineage":["https://openalex.org/I132735039"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Andr\u00e1s Berzi","raw_affiliation_strings":["Department of Nuclear Medicine and Translational Imaging, Institute of Medical Imaging, Faculty of Medicine, University of Debrecen","Doctoral School of Informatics, University of Debrecen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Nuclear Medicine and Translational Imaging, Institute of Medical Imaging, Faculty of Medicine, University of Debrecen","institution_ids":["https://openalex.org/I132735039"]},{"raw_affiliation_string":"Doctoral School of Informatics, University of Debrecen","institution_ids":["https://openalex.org/I132735039"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056977355","display_name":"Ervin L. Ber\u00e9nyi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I132735039","display_name":"University of Debrecen","ror":"https://ror.org/02xf66n48","country_code":"HU","type":"education","lineage":["https://openalex.org/I132735039"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Ervin Ber\u00e9nyi","raw_affiliation_strings":["Department of Radiology and Imaging Science, Institute of Medical Imaging, Faculty of Medicine, University of Debrecen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology and Imaging Science, Institute of Medical Imaging, Faculty of Medicine, University of Debrecen","institution_ids":["https://openalex.org/I132735039"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160213586","display_name":"Vikt\u00f3ria Arat\u00f3","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I132735039","display_name":"University of Debrecen","ror":"https://ror.org/02xf66n48","country_code":"HU","type":"education","lineage":["https://openalex.org/I132735039"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Vikt\u00f3ria Arat\u00f3","raw_affiliation_strings":["Nuclear Medicine, Department of Medical Imaging, Diagnostic Units, University of Debrecen Clinical Centre"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuclear Medicine, Department of Medical Imaging, Diagnostic Units, University of Debrecen Clinical Centre","institution_ids":["https://openalex.org/I132735039"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009085432","display_name":"Piroska Kallos-Balogh","orcid":"https://orcid.org/0000-0001-6893-0026","observed_orcids":["https://orcid.org/0000-0001-6893-0026"]},"institutions":[{"id":"https://openalex.org/I132735039","display_name":"University of Debrecen","ror":"https://ror.org/02xf66n48","country_code":"HU","type":"education","lineage":["https://openalex.org/I132735039"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Piroska Kallos-Balogh","raw_affiliation_strings":["Department of Nuclear Medicine and Translational Imaging, Institute of Medical Imaging, Faculty of Medicine, University of Debrecen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Nuclear Medicine and Translational Imaging, Institute of Medical Imaging, Faculty of Medicine, University of Debrecen","institution_ids":["https://openalex.org/I132735039"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160236397","display_name":"S\u00e1ndor Csaba Aranyi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I132735039","display_name":"University of Debrecen","ror":"https://ror.org/02xf66n48","country_code":"HU","type":"education","lineage":["https://openalex.org/I132735039"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"S\u00e1ndor Csaba Aranyi","raw_affiliation_strings":["Department of Nuclear Medicine and Translational Imaging, Institute of Medical Imaging, Faculty of Medicine, University of Debrecen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Nuclear Medicine and Translational Imaging, Institute of Medical Imaging, Faculty of Medicine, University of Debrecen","institution_ids":["https://openalex.org/I132735039"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072763171","display_name":"Zita K\u00e9pes","orcid":"https://orcid.org/0000-0003-2889-8521","observed_orcids":["https://orcid.org/0000-0003-2889-8521"]},"institutions":[{"id":"https://openalex.org/I132735039","display_name":"University of Debrecen","ror":"https://ror.org/02xf66n48","country_code":"HU","type":"education","lineage":["https://openalex.org/I132735039"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Zita K\u00e9pes","raw_affiliation_strings":["Department of Nuclear Medicine and Translational Imaging, Institute of Medical Imaging, Faculty of Medicine, University of Debrecen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Nuclear Medicine and Translational Imaging, Institute of Medical Imaging, Faculty of Medicine, University of Debrecen","institution_ids":["https://openalex.org/I132735039"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073201261","display_name":"Mikl\u00f3s Emri","orcid":"https://orcid.org/0000-0001-9884-9202","observed_orcids":["https://orcid.org/0000-0001-9884-9202"]},"institutions":[{"id":"https://openalex.org/I132735039","display_name":"University of Debrecen","ror":"https://ror.org/02xf66n48","country_code":"HU","type":"education","lineage":["https://openalex.org/I132735039"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Mikl\u00f3s Emri","raw_affiliation_strings":["Department of Nuclear Medicine and Translational Imaging, Institute of Medical Imaging, Faculty of Medicine, University of Debrecen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Nuclear Medicine and Translational Imaging, Institute of Medical Imaging, Faculty of Medicine, University of Debrecen","institution_ids":["https://openalex.org/I132735039"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5117771498"],"corresponding_institution_ids":["https://openalex.org/I132735039"],"apc_list":{"value":1950,"currency":"CHF","value_usd":2353},"apc_paid":{"value":1950,"currency":"CHF","value_usd":2353},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7562972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9208999872207642,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9208999872207642,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.0568000003695488,"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":0.007699999958276749,"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/named-entity-recognition","display_name":"named entity recognition","score":0.8799999952316284},{"id":"https://openalex.org/keywords/clinical-narratives","display_name":"clinical text","score":0.8199999928474426},{"id":"https://openalex.org/keywords/adverse-events","display_name":"adverse events","score":0.6349999904632568},{"id":"https://openalex.org/keywords/allergy","display_name":"allergy","score":0.6510000228881836},{"id":"https://openalex.org/keywords/medication-history","display_name":"drug history","score":0.5230000019073486},{"id":"https://openalex.org/keywords/unstructured-clinical-data","display_name":"unstructured clinical data","score":0.5450000166893005},{"id":"https://openalex.org/keywords/minority-class-oversampling","display_name":"minority class oversampling","score":0.7580000162124634},{"id":"https://openalex.org/keywords/spacy","display_name":"spaCy","score":0.5590000152587891},{"id":"https://openalex.org/keywords/clinical-research-data-extraction","display_name":"clinical research data extraction","score":0.5149999856948853},{"id":"https://openalex.org/keywords/over-the-counter-supplements","display_name":"over-the-counter supplements","score":0.7300000190734863}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6237000226974487},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6033999919891357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5975000262260437},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5774000287055969},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5568000078201294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5174999833106995},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4526999890804291},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.4323999881744385},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4262999892234802},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.3856000006198883},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C3020144179","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic health record","level":3,"score":0.3824999928474426},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.3714999854564667},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36959999799728394},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.33469998836517334},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3336000144481659},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.3086000084877014},{"id":"https://openalex.org/C535046627","wikidata":"https://www.wikidata.org/wiki/Q30612","display_name":"Clinical trial","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2935999929904938},{"id":"https://openalex.org/C151243789","wikidata":"https://www.wikidata.org/wiki/Q17148646","display_name":"Multiple baseline design","level":3,"score":0.2930000126361847},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C133652896","wikidata":"https://www.wikidata.org/wiki/Q7251300","display_name":"Protected health information","level":5,"score":0.25859999656677246},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2567000091075897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3389/frai.2026.1927272","doi":"https://doi.org/10.3389/frai.2026.1927272","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2026.1927272","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2026.1927272/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ab5ff76350d9421dbb63bafccaaa10ba","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/ab5ff76350d9421dbb63bafccaaa10ba","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Artificial Intelligence, Vol 9 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/frai.2026.1927272","doi":"https://doi.org/10.3389/frai.2026.1927272","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2026.1927272","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2026.1927272/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6240000128746033,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224893910.pdf","grobid_xml":"https://content.openalex.org/works/W7224893910.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2911489562","https://openalex.org/W2979250794","https://openalex.org/W4221149706","https://openalex.org/W4366824871","https://openalex.org/W4379514196","https://openalex.org/W4381849850","https://openalex.org/W4391124783","https://openalex.org/W4394996828","https://openalex.org/W4410890293","https://openalex.org/W4414748562","https://openalex.org/W4415964446","https://openalex.org/W4416255260"],"related_works":["https://openalex.org/W4380738738","https://openalex.org/W4385570842","https://openalex.org/W4200136492","https://openalex.org/W4391229549","https://openalex.org/W2251184341","https://openalex.org/W118100082","https://openalex.org/W4378761559","https://openalex.org/W7166522014","https://openalex.org/W4381849850","https://openalex.org/W4376620295"],"abstract_inverted_index":{"Introduction":[0],"While":[1],"structured":[2,84,445],"electronic":[3],"health":[4],"records":[5],"(EHRs)":[6],"provide":[7],"a":[8,65,93,163,185,246,376,424,449],"baseline":[9,248,379],"for":[10,87,202,256,265,430,451],"medication":[11,23,130,211,266,412,427,442,446],"history,":[12],"they":[13],"often":[14],"fail":[15],"to":[16,61,128],"capture":[17],"clinically":[18],"important":[19],"contextual":[20,134],"information":[21,39,77,267],"about":[22],"use":[24],"that":[25],"is":[26],"documented":[27],"only":[28,189],"in":[29,53,154,177,332,345],"free-text":[30,55],"clinical":[31,38,56,81,88,432],"notes.":[32,57],"A":[33,121],"significant":[34],"portion":[35],"of":[36,74,116,119,218,261,280,326,338,367,411,440,465,478,485,500],"critical":[37],"\u2013":[40,50],"such":[41,503],"as":[42,234,504],"unreported":[43],"adverse":[44],"events":[45],"or":[46],"over-the-counter":[47],"supplement":[48],"usage":[49],"resides":[51],"exclusively":[52,201],"unstructured":[54,79,441],"Our":[58],"objective":[59],"was":[60,126,199,224],"develop":[62],"and":[63,142,151,161,229,243,311,455,468,475,497,506],"evaluate":[64,158],"fine-grained":[66,94,123,270,425],"context-aware":[67,95,271,426],"Named":[68,96],"Entity":[69,97],"Recognition":[70,98],"(NER)":[71,99],"framework":[72,100],"capable":[73],"transforming":[75],"medication-related":[76],"from":[78,110,190,250,414],"Hungarian":[80,431],"narratives":[82,443],"into":[83,132,403,444],"data":[85,406,462],"suitable":[86],"research.":[89],"Methods":[90],"We":[91],"developed":[92,435],"using":[101,148,226],"the":[102,111,117,191,207,240,251,288,293,316,319,346,357,381,404,438,476,498],"spaCy":[103],"NLP":[104],"library.":[105],"Clinical":[106],"documents":[107,413,417],"were":[108,146,263],"sourced":[109],"UDBD-Health":[112],"Research":[113],"Data":[114],"Repository":[115],"University":[118],"Debrecen.":[120],"dedicated":[122],"annotation":[124],"scheme":[125],"designed":[127],"categorize":[129],"mentions":[131],"4":[133],"classes:":[135],"Current":[136],"Medication,":[137,139],"Discontinued/No":[138],"Adverse":[140],"Events,":[141],"Allergies":[143],"(CAVE).":[144],"Documents":[145],"pre-annotated":[147],"rule-based":[149,247,377],"vocabularies":[150],"manually":[152],"refined":[153],"Label":[155],"Studio.":[156],"To":[157,205],"model":[159,179,272,353],"generalization":[160],"obtain":[162],"robust,":[164],"leakage-free":[165],"performance":[166,223],"estimate,":[167],"we":[168,214],"employed":[169],"5-fold":[170],"cross-validation":[171,473],"with":[172,342,371],"an":[173,275,333,363],"inner":[174],"validation":[175,186],"split,":[176],"which":[178,390,482],"selection":[180],"via":[181],"early":[182],"stopping":[183],"used":[184,255],"subset":[187],"drawn":[188],"training":[192,220],"folds,":[193,242],"while":[194],"each":[195],"outer":[196],"held-out":[197],"fold":[198],"reserved":[200],"final":[203],"evaluation.":[204],"address":[206],"pronounced":[208],"imbalance":[209],"between":[210],"context":[212],"classes,":[213],"applied":[215],"document-level":[216,324],"oversampling":[217,325],"minority-class":[219,327,347],"examples.":[221],"Model":[222],"assessed":[225],"Precision,":[227],"Recall,":[228],"F":[230,277,295,335,348,364],"1":[231,278,296,336,349,365,385],"-score,":[232],"reported":[233],"mean":[235],"\u00b1":[236,282,299,305,309,314,340,369,388],"standard":[237],"deviation":[238],"across":[239,284],"five":[241],"compared":[244],"against":[245],"built":[249],"same":[252,382],"vocabulary-matching":[253,378],"procedure":[254],"pre-annotation.":[257],"Results":[258],"Two":[259],"types":[260],"models":[262,399,436],"trained":[264,355],"extraction.":[268],"The":[269,351,398,434],"(CME)":[273],"achieved":[274],"overall":[276,334],"-score":[279,297,337,366],"0.944":[281],"0.001":[283,370],"five-fold":[285],"cross-validation.":[286],"At":[287],"entity":[289],"level,":[290],"CURRENT_MED":[291],"yielded":[292],"highest":[294],"(0.958":[298],"0.001),":[300],"followed":[301],"by":[302],"CAVE_MED":[303],"(0.900":[304],"0.023),":[306],"NO_MED":[307],"(0.820":[308],"0.005),":[310],"AE_MED":[312],"(0.689":[313],"0.026),":[315],"latter":[317],"exhibiting":[318],"greatest":[320],"fold-to-fold":[321],"variance.":[322],"Applying":[323],"examples":[328],"(CME":[329],"OS)":[330],"resulted":[331],"0.946":[339],"0.002,":[341],"modest":[343],"improvements":[344],"-scores.":[350],"coarse-grained":[352],"(ME),":[354],"on":[356,380,492],"single-entity":[358],"MEDICATION":[359],"recognition":[360],"task,":[361],"attained":[362],"0.968":[368],"minimal":[372],"variance,":[373],"substantially":[374],"outperforming":[375],"task":[383],"(F":[384],"=":[386],"0.860":[387],"0.003),":[389],"showed":[391],"high":[392],"Precision":[393],"but":[394],"comparatively":[395],"low":[396],"Recall.":[397],"have":[400],"been":[401],"deployed":[402],"institutional":[405,461],"pipeline,":[407],"enabling":[408],"automated":[409],"structuring":[410],"over":[415],"700,000":[416],"per":[418],"year.":[419],"Discussion":[420],"This":[421],"study":[422],"presents":[423],"extraction":[428],"system":[429],"documents.":[433],"facilitate":[437],"transformation":[439],"data,":[447],"providing":[448],"foundation":[450],"downstream":[452],"pharmacological,":[453],"epidemiological,":[454],"real-world":[456],"evidence":[457],"studies.":[458],"Limitations":[459],"include":[460],"specificity,":[463],"underrepresentation":[464],"adverse-event":[466],"contexts,":[467],"document-":[469],"rather":[470],"than":[471],"patient-level":[472],"splitting,":[474],"lack":[477],"independent":[479],"parallel":[480],"annotation,":[481],"prevented":[483],"calculation":[484],"inter-annotator":[486],"agreement.":[487],"Future":[488],"work":[489],"will":[490],"focus":[491],"corpus":[493],"expansion,":[494],"inter-institutional":[495],"validation,":[496],"inclusion":[499],"additional":[501],"attributes":[502],"dosage":[505],"duration.":[507]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-10-31T00:00:00"}