{"id":"https://openalex.org/W4200098147","doi":"https://doi.org/10.3389/frai.2021.729834","title":"BERT-Based Natural Language Processing of Drug Labeling Documents: A Case Study for Classifying Drug-Induced Liver Injury Risk","display_name":"BERT-Based Natural Language Processing of Drug Labeling Documents: A Case Study for Classifying Drug-Induced Liver Injury Risk","publication_year":2021,"publication_date":"2021-12-06","ids":{"openalex":"https://openalex.org/W4200098147","doi":"https://doi.org/10.3389/frai.2021.729834","pmid":"https://pubmed.ncbi.nlm.nih.gov/34939028"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2021.729834","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2021.729834","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2021.729834/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,"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"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/frai.2021.729834/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068335374","display_name":"Yue Wu","orcid":"https://orcid.org/0000-0001-7770-9331"},"institutions":[{"id":"https://openalex.org/I1304557061","display_name":"National Center for Toxicological Research","ror":"https://ror.org/05jmhh281","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1304557061","https://openalex.org/I1320320070"]},{"id":"https://openalex.org/I1320320070","display_name":"United States Food and Drug Administration","ror":"https://ror.org/034xvzb47","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yue Wu","raw_affiliation_strings":["Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, United States Food and Drug Administration, Jefferson, AR, United States"],"affiliations":[{"raw_affiliation_string":"Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, United States Food and Drug Administration, Jefferson, AR, United States","institution_ids":["https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459808","display_name":"Zhichao Liu","orcid":"https://orcid.org/0000-0003-0630-821X"},"institutions":[{"id":"https://openalex.org/I1320320070","display_name":"United States Food and Drug Administration","ror":"https://ror.org/034xvzb47","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1320320070"]},{"id":"https://openalex.org/I1304557061","display_name":"National Center for Toxicological Research","ror":"https://ror.org/05jmhh281","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhichao Liu","raw_affiliation_strings":["Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, United States Food and Drug Administration, Jefferson, AR, United States"],"affiliations":[{"raw_affiliation_string":"Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, United States Food and Drug Administration, Jefferson, AR, United States","institution_ids":["https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101869895","display_name":"Leihong Wu","orcid":"https://orcid.org/0000-0002-4093-3708"},"institutions":[{"id":"https://openalex.org/I1320320070","display_name":"United States Food and Drug Administration","ror":"https://ror.org/034xvzb47","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1320320070"]},{"id":"https://openalex.org/I1304557061","display_name":"National Center for Toxicological Research","ror":"https://ror.org/05jmhh281","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leihong Wu","raw_affiliation_strings":["Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, United States Food and Drug Administration, Jefferson, AR, United States"],"affiliations":[{"raw_affiliation_string":"Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, United States Food and Drug Administration, Jefferson, AR, United States","institution_ids":["https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035030398","display_name":"Minjun Chen","orcid":"https://orcid.org/0000-0002-6453-2351"},"institutions":[{"id":"https://openalex.org/I1304557061","display_name":"National Center for Toxicological Research","ror":"https://ror.org/05jmhh281","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1304557061","https://openalex.org/I1320320070"]},{"id":"https://openalex.org/I1320320070","display_name":"United States Food and Drug Administration","ror":"https://ror.org/034xvzb47","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minjun Chen","raw_affiliation_strings":["Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, United States Food and Drug Administration, Jefferson, AR, United States"],"affiliations":[{"raw_affiliation_string":"Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, United States Food and Drug Administration, Jefferson, AR, United States","institution_ids":["https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068886380","display_name":"Weida Tong","orcid":"https://orcid.org/0000-0003-3488-6148"},"institutions":[{"id":"https://openalex.org/I1304557061","display_name":"National Center for Toxicological Research","ror":"https://ror.org/05jmhh281","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1304557061","https://openalex.org/I1320320070"]},{"id":"https://openalex.org/I1320320070","display_name":"United States Food and Drug Administration","ror":"https://ror.org/034xvzb47","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weida Tong","raw_affiliation_strings":["Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, United States Food and Drug Administration, Jefferson, AR, United States"],"affiliations":[{"raw_affiliation_string":"Division of Bioinformatics and Biostatistics, National Center for Toxicological Research, United States Food and Drug Administration, Jefferson, AR, United States","institution_ids":["https://openalex.org/I1304557061","https://openalex.org/I1320320070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068335374"],"corresponding_institution_ids":["https://openalex.org/I1304557061","https://openalex.org/I1320320070"],"apc_list":{"value":1150,"currency":"USD","value_usd":1150},"apc_paid":{"value":1150,"currency":"USD","value_usd":1150},"fwci":2.3257,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.87072358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"4","issue":null,"first_page":"729834","last_page":"729834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11943","display_name":"Pharmacovigilance and Adverse Drug Reactions","score":0.972599983215332,"subfield":{"id":"https://openalex.org/subfields/3005","display_name":"Toxicology"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11943","display_name":"Pharmacovigilance and Adverse Drug Reactions","score":0.972599983215332,"subfield":{"id":"https://openalex.org/subfields/3005","display_name":"Toxicology"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9110000133514404,"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/drug","display_name":"Drug","score":0.6842126846313477},{"id":"https://openalex.org/keywords/liver-injury","display_name":"Liver injury","score":0.6424499750137329},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4970143139362335},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4806200861930847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4103609621524811},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.3065759241580963},{"id":"https://openalex.org/keywords/pharmacology","display_name":"Pharmacology","score":0.20391413569450378}],"concepts":[{"id":"https://openalex.org/C2780035454","wikidata":"https://www.wikidata.org/wiki/Q8386","display_name":"Drug","level":2,"score":0.6842126846313477},{"id":"https://openalex.org/C2776637226","wikidata":"https://www.wikidata.org/wiki/Q6658207","display_name":"Liver injury","level":2,"score":0.6424499750137329},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4970143139362335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4806200861930847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4103609621524811},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.3065759241580963},{"id":"https://openalex.org/C98274493","wikidata":"https://www.wikidata.org/wiki/Q128406","display_name":"Pharmacology","level":1,"score":0.20391413569450378}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/frai.2021.729834","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2021.729834","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2021.729834/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,"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":"pmid:34939028","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34939028","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":"Frontiers in artificial intelligence","raw_type":null},{"id":"pmh:oai:doaj.org/article:0420db0639784d25bd83f7d46c097387","is_oa":true,"landing_page_url":"https://doaj.org/article/0420db0639784d25bd83f7d46c097387","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Artificial Intelligence, Vol 4 (2021)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8685544","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8685544","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Artif Intell","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/frai.2021.729834","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2021.729834","pdf_url":"https://www.frontiersin.org/articles/10.3389/frai.2021.729834/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,"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":[{"display_name":"Quality Education","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8509642997","display_name":null,"funder_award_id":"E0767701","funder_id":"https://openalex.org/F4320332163","funder_display_name":"U.S. Food and Drug Administration"}],"funders":[{"id":"https://openalex.org/F4320332163","display_name":"U.S. Food and Drug Administration","ror":"https://ror.org/034xvzb47"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4200098147.pdf","grobid_xml":"https://content.openalex.org/works/W4200098147.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W569080582","https://openalex.org/W1565605888","https://openalex.org/W2064671306","https://openalex.org/W2087561463","https://openalex.org/W2092058382","https://openalex.org/W2109879824","https://openalex.org/W2289901683","https://openalex.org/W2295940487","https://openalex.org/W2333276533","https://openalex.org/W2794085611","https://openalex.org/W2895763047","https://openalex.org/W2896457183","https://openalex.org/W2921465693","https://openalex.org/W2923978210","https://openalex.org/W2939507640","https://openalex.org/W2945542139","https://openalex.org/W2952357537","https://openalex.org/W2962398326","https://openalex.org/W2962862931","https://openalex.org/W2966109107","https://openalex.org/W2970597249","https://openalex.org/W2979826702","https://openalex.org/W2980708516","https://openalex.org/W3080297463","https://openalex.org/W3108846574","https://openalex.org/W3110130679","https://openalex.org/W4385245566","https://openalex.org/W6762836198"],"related_works":["https://openalex.org/W2977813901","https://openalex.org/W2384026722","https://openalex.org/W3204784468","https://openalex.org/W2960526624","https://openalex.org/W2365324359","https://openalex.org/W2169494313","https://openalex.org/W2356350029","https://openalex.org/W3126593080","https://openalex.org/W3204019825","https://openalex.org/W2089349728"],"abstract_inverted_index":{"<b>Background":[0],"&":[1],"Aims:</b>":[2],"The":[3,28,108,139],"United":[4,25],"States":[5,26],"Food":[6],"and":[7,35,47,71,119,123,147,165,223,251],"Drug":[8],"Administration":[9],"(FDA)":[10],"regulates":[11],"a":[12,38,77,89,161,166,246],"broad":[13],"range":[14],"of":[15,23,37,41,65,163,168,204,219,227],"consumer":[16],"products,":[17],"which":[18,43],"account":[19],"for":[20,68,135],"about":[21],"25%":[22],"the":[24,103,126,130,177,179,185,195,201,225],"market.":[27],"FDA":[29,82,144],"regulatory":[30,52,66,91,243,253],"activities":[31,244],"often":[32],"involve":[33],"producing":[34],"reading":[36],"large":[39],"number":[40],"documents,":[42],"is":[44,245],"time":[45],"consuming":[46],"labor":[48],"intensive.":[49],"To":[50],"support":[51],"science":[53],"at":[54],"FDA,":[55],"we":[56],"evaluated":[57,148],"artificial":[58],"intelligence":[59],"(AI)-based":[60],"natural":[61],"language":[62,105],"processing":[63],"(NLP)":[64],"documents":[67,85,146,222],"text":[69,229],"classification":[70,111,159,218],"compared":[72],"deep":[73],"learning-based":[74,211],"models":[75,213],"with":[76,116,160],"conventional":[78],"keywords-based":[79],"model.":[80],"<b>Methods:</b>":[81],"drug":[83,207,220,231],"labeling":[84,127,145,221],"were":[86,173],"used":[87,174],"as":[88],"representative":[90],"data":[92,128,172],"source":[93],"to":[94,125,175,199,241,249],"classify":[95],"drug-induced":[96],"liver":[97],"injury":[98],"(DILI)":[99],"risk":[100],"by":[101,149],"employing":[102],"state-of-the-art":[104],"model":[106,112,141,186,196],"BERT.":[107],"resulting":[109],"NLP-DILI":[110,140],"was":[113,187,197],"statistically":[114],"validated":[115],"both":[117],"internal":[118],"external":[120],"validation":[121],"procedures":[122],"applied":[124],"from":[129],"European":[131],"Medicines":[132],"Agency":[133],"(EMA)":[134],"cross-agency":[136,171],"application.":[137],"<b>Results:</b>":[138],"developed":[142],"using":[143,238],"cross-validations":[150],"in":[151,157,206,216,230],"this":[152],"study":[153],"showed":[154],"remarkable":[155],"performance":[156,180],"DILI":[158,217],"recall":[162],"1":[164],"precision":[167],"0.78.":[169],"When":[170],"validate":[176],"model,":[178],"remained":[181],"comparable,":[182],"demonstrating":[183],"that":[184,194,237],"portable":[188],"across":[189],"agencies.":[190],"Results":[191],"also":[192],"suggested":[193],"able":[198],"capture":[200],"semantic":[202],"meanings":[203,226],"sentences":[205],"labeling.":[208,232],"<b>Conclusion:</b>":[209],"Deep":[210],"NLP":[212],"performed":[214],"well":[215],"learned":[224],"complex":[228],"This":[233],"proof-of-concept":[234],"work":[235],"demonstrated":[236],"AI":[239],"technologies":[240],"assist":[242],"promising":[247],"approach":[248],"modernize":[250],"advance":[252],"science.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}