{"id":"https://openalex.org/W7167790825","doi":"https://doi.org/10.1109/access.2026.3711902","title":"Toward Language-Aware Pharmaceutical Informatics: End-to-End ATC Code Classification From Regulatory Documents","display_name":"Toward Language-Aware Pharmaceutical Informatics: End-to-End ATC Code Classification From Regulatory Documents","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7167790825","doi":"https://doi.org/10.1109/access.2026.3711902"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3711902","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3711902","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3711902","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064003383","display_name":"Damla B\u00fc\u015fra \u00d6zs\u00f6nmez","orcid":"https://orcid.org/0000-0002-6848-0245"},"institutions":[{"id":"https://openalex.org/I94294566","display_name":"Galatasaray University","ror":"https://ror.org/00btgsb62","country_code":"TR","type":"education","lineage":["https://openalex.org/I94294566"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Damla Busra Ozsonmez","raw_affiliation_strings":["Galatasaray University"],"raw_orcid":"https://orcid.org/0000-0002-6848-0245","affiliations":[{"raw_affiliation_string":"Galatasaray University","institution_ids":["https://openalex.org/I94294566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077999862","display_name":"F\u0131rat Bozkaya","orcid":"https://orcid.org/0000-0002-4310-9490"},"institutions":[{"id":"https://openalex.org/I94294566","display_name":"Galatasaray University","ror":"https://ror.org/00btgsb62","country_code":"TR","type":"education","lineage":["https://openalex.org/I94294566"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Firat Bozkaya","raw_affiliation_strings":["Galatasaray University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Galatasaray University","institution_ids":["https://openalex.org/I94294566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084367490","display_name":"Tankut Acarman","orcid":"https://orcid.org/0000-0003-4169-1189"},"institutions":[{"id":"https://openalex.org/I94294566","display_name":"Galatasaray University","ror":"https://ror.org/00btgsb62","country_code":"TR","type":"education","lineage":["https://openalex.org/I94294566"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Tankut Acarman","raw_affiliation_strings":["Galatasaray University"],"raw_orcid":"https://orcid.org/0000-0003-4169-1189","affiliations":[{"raw_affiliation_string":"Galatasaray University","institution_ids":["https://openalex.org/I94294566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046972938","display_name":"\u0130smail Burak Parlak","orcid":"https://orcid.org/0000-0002-0887-4226"},"institutions":[{"id":"https://openalex.org/I94294566","display_name":"Galatasaray University","ror":"https://ror.org/00btgsb62","country_code":"TR","type":"education","lineage":["https://openalex.org/I94294566"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ismail Burak Parlak","raw_affiliation_strings":["Galatasaray University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Galatasaray University","institution_ids":["https://openalex.org/I94294566"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102710247","display_name":"Mouloud Adel","orcid":"https://orcid.org/0000-0003-2840-0172"},"institutions":[{"id":"https://openalex.org/I94294566","display_name":"Galatasaray University","ror":"https://ror.org/00btgsb62","country_code":"TR","type":"education","lineage":["https://openalex.org/I94294566"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mouloud Adel","raw_affiliation_strings":["Galatasaray University"],"raw_orcid":"https://orcid.org/0000-0003-2840-0172","affiliations":[{"raw_affiliation_string":"Galatasaray University","institution_ids":["https://openalex.org/I94294566"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94294566"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79482691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"107351","last_page":"107368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.4611000120639801,"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":0.4611000120639801,"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":0.06289999932050705,"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":0.055399999022483826,"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/code","display_name":"Code (set theory)","score":0.5436999797821045},{"id":"https://openalex.org/keywords/electronic-mail","display_name":"Electronic mail","score":0.2806999981403351},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.25450000166893005},{"id":"https://openalex.org/keywords/air-traffic-control","display_name":"Air traffic control","score":0.2533000111579895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7807999849319458},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5436999797821045},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36329999566078186},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35019999742507935},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3449999988079071},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C166961238","wikidata":"https://www.wikidata.org/wiki/Q221395","display_name":"Air traffic control","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24560000002384186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3711902","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3711902","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:cb7ff8ad610d4666b962f3e9e0bc881b","is_oa":false,"landing_page_url":"https://doaj.org/article/cb7ff8ad610d4666b962f3e9e0bc881b","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,"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":"IEEE Access, Vol 14, Pp 107351-107368 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3711902","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3711902","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1038669747","https://openalex.org/W1976582164","https://openalex.org/W2066201260","https://openalex.org/W2084267598","https://openalex.org/W2094791588","https://openalex.org/W2149684865","https://openalex.org/W2186971834","https://openalex.org/W2295598076","https://openalex.org/W2493916176","https://openalex.org/W2607357445","https://openalex.org/W2621574814","https://openalex.org/W2896457183","https://openalex.org/W2911489562","https://openalex.org/W2946276693","https://openalex.org/W2950784811","https://openalex.org/W2979645924","https://openalex.org/W2990275322","https://openalex.org/W2995439439","https://openalex.org/W2997591727","https://openalex.org/W3035032094","https://openalex.org/W3045285347","https://openalex.org/W3094581225","https://openalex.org/W3129383795","https://openalex.org/W3168656614","https://openalex.org/W3183426088","https://openalex.org/W4226371412","https://openalex.org/W4239510810","https://openalex.org/W4312969018","https://openalex.org/W4380589720","https://openalex.org/W4385245566","https://openalex.org/W4386845189","https://openalex.org/W4387460638","https://openalex.org/W4409341505","https://openalex.org/W7160293660"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"classification":[1,80,111,146],"of":[2,28,118,135],"Anatomical":[3],"Therapeutic":[4],"Chemical":[5],"(ATC)":[6],"codes":[7],"from":[8],"pharmaceutical":[9,39,149],"documents":[10],"remains":[11],"a":[12,24,44,140],"challenging":[13],"task,":[14],"particularly":[15],"in":[16,38,110,148],"low":[17],"resource":[18],"linguistic":[19],"contexts.":[20],"This":[21,41],"study":[22],"introduces":[23],"newly":[25],"curated":[26],"dataset":[27,71],"drug":[29],"manuals":[30],"encompassing":[31],"all":[32],"ATC":[33,52,144],"categories":[34],"to":[35,74,107],"support":[36],"research":[37,147],"informatics.":[40],"paper":[42],"proposes":[43],"Natural":[45],"Language":[46],"Processing":[47],"(NLP)-based":[48],"framework":[49],"for":[50,142],"end-to-end":[51],"code":[53,145],"classification,":[54],"addressing":[55],"key":[56],"challenges":[57],"such":[58,91],"as":[59,92],"contextual":[60],"ambiguity":[61],"and":[62,76,88,99,103,124,133],"limited":[63],"labeled":[64],"data":[65],"availability.":[66],"Leveraging":[67],"NLP":[68],"methodologies,":[69],"the":[70,131,136],"was":[72],"used":[73],"train":[75],"evaluate":[77],"various":[78],"text":[79,150],"models,":[81],"including":[82],"Support":[83],"Vector":[84],"Classifier":[85],"(SVC),":[86],"FastText,":[87],"transformer-based":[89],"architectures":[90],"BERTurk":[93,95,120],"Uncased,":[94],"Large,":[96],"ConvBERTurk,":[97],"ElectroBERTurk,":[98],"DistilBERTurk.":[100],"Extensive":[101],"preprocessing":[102],"model":[104],"optimization":[105],"led":[106],"significant":[108],"improvements":[109],"performance,":[112],"with":[113],"FastText":[114],"achieving":[115],"an":[116],"F1-score":[117],"96.0%,":[119],"Uncased":[121],"reaching":[122],"95.9%,":[123],"SVC":[125],"attaining":[126],"94.0%.":[127],"These":[128],"results":[129],"validate":[130],"usefulness":[132],"effectiveness":[134],"proposed":[137],"dataset,":[138],"establishing":[139],"benchmark":[141],"future":[143],"analytics.":[151]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-07-10T00:00:00"}
