{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T16:17:15Z","timestamp":1785773835987,"version":"3.56.0"},"reference-count":32,"publisher":"Frontiers Media SA","issue":"21","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Exp Biol Med (Maywood)"],"published-print":{"date-parts":[[2023,11]]},"abstract":"<jats:p>The US drug labeling document contains essential information on drug efficacy and safety, making it a crucial regulatory resource for Food and Drug Administration (FDA) drug reviewers. Due to its extensive volume and the presence of free-text, conventional text mining analysis have encountered challenges in processing these data. Recent advances in artificial intelligence (AI) for natural language processing (NLP) have provided an unprecedented opportunity to identify key information from drug labeling, thereby enhancing safety reviews and support for regulatory decisions. We developed RxBERT, a Bidirectional Encoder Representations from Transformers (BERT) model pretrained on FDA human prescription drug labeling documents for an enhanced application of drug labeling documents in both research and drug review. RxBERT was derived from BioBERT with further training on human prescription drug labeling documents. RxBERT was demonstrated in several tasks using regulatory datasets, including those involved in the National Institutes of Technology Text Analysis Challenge Dataset (NIST TAC dataset), the FDA Adverse Drug Event Evaluation Dataset (ADE Eval dataset), and the classification of texts from submission packages into labeling sections (US Drug Labeling dataset). For all these tasks, RxBERT reached 86.5 F1-scores in both TAC and ADE Eval classification, respectively, and prediction accuracy of 87% for the US Drug Labeling dataset. Overall, RxBERT was shown to be as competitive or have better performance compared to other NLP approaches such as BERT, BioBERT, etc. In summary, we developed RxBERT, a transformer-based model specific for drug labeling that outperformed the original BERT model. RxBERT has the potential to be used to assist research scientists and FDA reviewers to better process and utilize drug labeling information toward the advancement of drug effectiveness and safety for public health. This proof-of-concept study also demonstrated a potential pathway to customized large language models (LLMs) tailored to the sensitive regulatory documents for internal application.<\/jats:p>","DOI":"10.1177\/15353702231220669","type":"journal-article","created":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T07:02:45Z","timestamp":1709276565000},"page":"1937-1943","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":15,"title":["RxBERT: Enhancing drug labeling text mining and analysis with AI language modeling"],"prefix":"10.3389","volume":"248","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4093-3708","authenticated-orcid":false,"given":"Leihong","family":"Wu","sequence":"first","affiliation":[{"name":"Division of Bioinformatics and Biostatistics, FDA National Center for Toxicological Research, Jefferson, AR 72079, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6355-7627","authenticated-orcid":false,"given":"Magnus","family":"Gray","sequence":"additional","affiliation":[{"name":"Division of Bioinformatics and Biostatistics, FDA National Center for Toxicological Research, Jefferson, AR 72079, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oanh","family":"Dang","sequence":"additional","affiliation":[{"name":"Office of Surveillance and Epidemiology, FDA Center for Drug Evaluation and Research, Silver Spring, MD 20993, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5313-5847","authenticated-orcid":false,"given":"Joshua","family":"Xu","sequence":"additional","affiliation":[{"name":"Division of Bioinformatics and Biostatistics, FDA National Center for Toxicological Research, Jefferson, AR 72079, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Fang","sequence":"additional","affiliation":[{"name":"Office of Scientific Coordination, FDA National Center for Toxicological Research, Jefferson, AR 72079, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3488-6148","authenticated-orcid":false,"given":"Weida","family":"Tong","sequence":"additional","affiliation":[{"name":"Division of Bioinformatics and Biostatistics, FDA National Center for Toxicological Research, Jefferson, AR 72079, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,1,2]]},"reference":[{"key":"bibr1-15353702231220669","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-020-00751-0"},{"key":"bibr2-15353702231220669","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2016.06.006"},{"key":"bibr3-15353702231220669","doi-asserted-by":"crossref","unstructured":"Roberts K, Demner-Fushman D, Tonning JM. Overview of the TAC 2017 adverse reaction extraction from drug labels track. https:\/\/tac.nist.gov\/publications\/2017\/additional.papers\/TAC2017.ADR_overview.proceedings.pdf","DOI":"10.6028\/NIST.SP.500-324.pm-overview"},{"key":"bibr4-15353702231220669","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2011.05.007"},{"key":"bibr5-15353702231220669","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-019-2628-5"},{"key":"bibr6-15353702231220669","first-page":"3762","volume":"30","author":"Vaswani A","year":"2017","journal-title":"Adv Neur Inform Process Syst"},{"key":"bibr7-15353702231220669","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. https:\/\/arxiv.org\/abs\/1810.04805"},{"key":"bibr8-15353702231220669","first-page":"1","volume":"55","author":"Liu P","year":"2023","journal-title":"ACM Comput Surv"},{"key":"bibr9-15353702231220669","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2019.12.014"},{"key":"bibr10-15353702231220669","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1331-6"},{"key":"bibr11-15353702231220669","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"bibr12-15353702231220669","unstructured":"Huang K, Altosaar J, Ranganath R. ClinicalBERT: modeling clinical notes and predicting hospital readmission. https:\/\/arxiv.org\/abs\/1904.05342"},{"key":"bibr13-15353702231220669","unstructured":"Chalkidis I, Fergadiotis M, Malakasiotis P, Aletras N, Androutsopoulos I. LEGAL-BERT: the Muppets straight out of law school. https:\/\/arxiv.org\/abs\/2010.02559"},{"key":"bibr14-15353702231220669","unstructured":"Beltagy I, Lo K, Cohan A. SciBERT: a pretrained language model for scientific text. https:\/\/arxiv.org\/abs\/1903.10676"},{"key":"bibr15-15353702231220669","unstructured":"M\u00fcller M, Salath\u00e9 M, Kummervold PE. COVID-Twitter-BERT: a natural language processing model to analyse COVID-19 content on Twitter. https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1023281\/full"},{"key":"bibr16-15353702231220669","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad226"},{"key":"bibr17-15353702231220669","doi-asserted-by":"publisher","DOI":"10.1007\/s40264-020-00996-3"},{"key":"bibr18-15353702231220669","unstructured":"U.S. Food and Drug Administration. 21 C.F.R. \u00a7201.56, 201.57, 201.80, https:\/\/www.accessdata.fda.gov\/scripts\/cdrh\/cfdocs\/cfcfr\/cfrsearch.cfm?fr=201.56"},{"key":"bibr19-15353702231220669","doi-asserted-by":"publisher","DOI":"10.1021\/acs.chemrestox.3c00028"},{"key":"bibr20-15353702231220669","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2021.729834"},{"key":"bibr21-15353702231220669","doi-asserted-by":"publisher","DOI":"10.1016\/j.yrtph.2022.105287"},{"key":"bibr22-15353702231220669","doi-asserted-by":"publisher","DOI":"10.1016\/j.yrtph.2023.105388"},{"key":"bibr23-15353702231220669","unstructured":"Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space. https:\/\/arxiv.org\/abs\/1301.3781"},{"key":"bibr24-15353702231220669","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2021.114135"},{"key":"bibr25-15353702231220669","volume":"33","author":"Brown T","year":"2020","journal-title":"Adv Neur Inform Process Syst"},{"key":"bibr26-15353702231220669","unstructured":"Chowdhery A, Narang S, Devlin J, Bosma M, Mishra G, Roberts A, Barham P, Chung HW, Sutton C, Gehrmann S. PaLM: scaling language modeling with pathways. https:\/\/arxiv.org\/abs\/2204.02311"},{"key":"bibr27-15353702231220669","unstructured":"Zhang S, Roller S, Goyal N, Artetxe M, Chen M, Chen S, Dewa n C, Diab M, Li X, Lin XV. OPT: open pre-trained transformer language models. https:\/\/arxiv.org\/abs\/2205.01068"},{"key":"bibr28-15353702231220669","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2023.1166120"},{"key":"bibr29-15353702231220669","doi-asserted-by":"crossref","DOI":"10.1007\/s00063-023-01019-6","volume":"118","author":"Sonntagbauer M","year":"2023","journal-title":"Med Klin Intensivmed Notfmed"},{"key":"bibr30-15353702231220669","unstructured":"Vought RT. Guidance for regulation of artificial intelligence applications. https:\/\/www.whitehouse.gov\/wp-content\/uploads\/2020\/01\/Draft-OMB-Memo-on-Regulation-of-AI-1-7-19.pdf"},{"key":"bibr31-15353702231220669","unstructured":"Executive Order 13859. Maintaining American leadership in artificial intelligence. https:\/\/www.federalregister.gov\/documents\/2019\/02\/14\/2019-02544\/maintaining-american-leadership-in-artificial-intelligence"},{"key":"bibr32-15353702231220669","unstructured":"Executive Order 13960. Promoting the use of trustworthy artificial intelligence in the federal government. https:\/\/www.federalregister.gov\/documents\/2020\/12\/08\/2020-27065\/promoting-the-use-of-trustworthy-artificial-intelligence-in-the-federal-government"}],"container-title":["Experimental Biology and Medicine"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/15353702231220669","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/15353702231220669","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/15353702231220669","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:52:17Z","timestamp":1777571537000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ebm-journal.org\/journals\/experimental-biology-and-medicine\/articles\/10.1177\/15353702231220669\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":32,"journal-issue":{"issue":"21","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["10.1177\/15353702231220669"],"URL":"https:\/\/doi.org\/10.1177\/15353702231220669","relation":{},"ISSN":["1535-3702","1535-3699"],"issn-type":[{"value":"1535-3702","type":"print"},{"value":"1535-3699","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}