{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T21:24:31Z","timestamp":1790803471779,"version":"4.1.0"},"reference-count":24,"publisher":"American Society of Clinical Oncology (ASCO)","issue":"9","content-domain":{"domain":["ascopubs.org"],"crossmark-restriction":true},"short-container-title":["JCO Clin Cancer Inform"],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:sec>\n                    <jats:title>PURPOSE<\/jats:title>\n                    <jats:p>Tobacco use is a major risk factor for diseases such as cancer. Granular quantitative details of smoking (eg, pack years and years since quitting) are essential for assessing disease risk and determining eligibility for lung cancer screening (LCS). However, existing natural language processing (NLP) tools struggle to extract detailed quantitative smoking data from clinical narratives.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>METHODS<\/jats:title>\n                    <jats:p>We cross-validated four pretrained Bidirectional Encoder Representations from Transformers (BERT)\u2013based models\u2014BERT, BioBERT, ClinicalBERT, and MedBERT\u2014by fine-tuning them on 90% of 3,261 sentences mentioning smoking history to extract six quantitative smoking history variables from clinical narratives. The model with the highest cross-validated micro-averaged F1 scores across most variables was selected as the final SmokeBERT model and was further fine-tuned on the 90% training data. Model performance was evaluated on a 10% holdout test set and an external validation set containing 3,191 sentences.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>RESULTS<\/jats:title>\n                    <jats:p>\n                      ClinicalBERT was selected as the final model based on cross-validation and was fine-tuned on the training data to create the SmokeBERT model. Compared with the state-of-the-art rule-based NLP model and the Generative Pre-trained Transformer Open Source Series 20 billion parameter model, SmokeBERT demonstrated superior performance in smoking data extraction (overall F1 score, holdout test: 0.97\n                      <jats:italic toggle=\"yes\">v<\/jats:italic>\n                      0.88-0.90; external validation: 0.86\n                      <jats:italic toggle=\"yes\">v<\/jats:italic>\n                      0.72-0.79) and in identifying LCS-eligible patients (97%\n                      <jats:italic toggle=\"yes\">v<\/jats:italic>\n                      59%-97% for \u226520 pack-years and 100%\n                      <jats:italic toggle=\"yes\">v<\/jats:italic>\n                      60%-84% for \u226415 years since quitting).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>CONCLUSION<\/jats:title>\n                    <jats:p>We developed SmokeBERT, a fine-tuned BERT-based model optimized for extracting detailed quantitative smoking histories. Future work includes evaluating performance on larger clinical data sets and developing a multilingual, language-agnostic version of SmokeBERT.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1200\/cci-25-00223","type":"journal-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T21:00:16Z","timestamp":1764622816000},"update-policy":"https:\/\/doi.org\/10.1200\/crossmark","source":"Crossref","is-referenced-by-count":1,"title":["SmokeBERT: A Bidirectional Encoder Representations From Transformers\u2013Based Model for Quantitative Smoking History Extraction From Clinical Narratives to Improve Lung Cancer Screening"],"prefix":"10.1200","author":[{"given":"Yiming","family":"Xue","sequence":"first","affiliation":[{"name":"Department of Statistics and Data Science, University of California, Los Angeles, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9143-7137","authenticated-orcid":true,"given":"Yunzheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Medical and Imaging Informatics, Department of Radiological Sciences, David Geffen School of Medicine at UCLA, Los Angeles, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3714-3174","authenticated-orcid":true,"given":"Luoting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Medical and Imaging Informatics, Department of Radiological Sciences, David Geffen School of Medicine at UCLA, Los Angeles, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8027-3433","authenticated-orcid":true,"given":"YongKyung","family":"Oh","sequence":"additional","affiliation":[{"name":"Medical and Imaging Informatics, Department of Radiological Sciences, David Geffen School of Medicine at UCLA, Los Angeles, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ricky","family":"Taira","sequence":"additional","affiliation":[{"name":"Medical and Imaging Informatics, Department of Radiological Sciences, David Geffen School of Medicine at UCLA, Los Angeles, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8858-3401","authenticated-orcid":true,"given":"Denise R.","family":"Aberle","sequence":"additional","affiliation":[{"name":"Medical and Imaging Informatics, Department of Radiological Sciences, David Geffen School of Medicine at UCLA, Los Angeles, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8615-5246","authenticated-orcid":true,"given":"Ashley Elizabeth","family":"Prosper","sequence":"additional","affiliation":[{"name":"Medical and Imaging Informatics, Department of Radiological Sciences, David Geffen School of Medicine at UCLA, Los Angeles, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5168-070X","authenticated-orcid":true,"given":"William","family":"Hsu","sequence":"additional","affiliation":[{"name":"Medical and Imaging Informatics, Department of Radiological Sciences, David Geffen School of Medicine at UCLA, Los Angeles, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3514-6475","authenticated-orcid":true,"given":"Yannan","family":"Lin","sequence":"additional","affiliation":[{"name":"Medical and Imaging Informatics, Department of Radiological Sciences, David Geffen School of Medicine at UCLA, Los Angeles, CA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"233","reference":[{"key":"e_1_3_7_2_2","unstructured":"U.S. Preventive Services Task Force: Lung cancer: Screening. https:\/\/www.uspreventiveservicestaskforce.org\/uspstf\/recommendation\/lung-cancer-screening"},{"key":"e_1_3_7_3_2","unstructured":"State of lung cancer 2024 report. https:\/\/www.lung.org\/getmedia\/12020193-7fb3-46b8-8d78-0e5d9cd8f93c\/SOLC-2024.pdf"},{"key":"e_1_3_7_4_2","unstructured":"Reynolds A: New measure coming for lung cancer screening\u2014NCQA. https:\/\/www.ncqa.org\/blog\/new-measure-coming-for-lung-cancer-screening\/"},{"key":"e_1_3_7_5_2","unstructured":"NCQA responds to CMS\u2019s CY 2025 Medicare advantage advance notice\u2014NCQA. https:\/\/www.ncqa.org\/comment-letter\/ncqa-responds-to-cmss-cy-2025-medicare-advantage-advance-notice\/"},{"key":"e_1_3_7_6_2","doi-asserted-by":"publisher","DOI":"10.4137\/CIN.S40604"},{"key":"e_1_3_7_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2023.105136"},{"key":"e_1_3_7_8_2","article-title":"Unstructured data are superior to structured data for eliciting quantitative smoking history from the electronic health record","author":"Ruckdeschel JC","unstructured":"Ruckdeschel JC, Riley M, Parsatharathy S, et al: Unstructured data are superior to structured data for eliciting quantitative smoking history from the electronic health record. JCO Clin Cancer Inform 10.1200\/CCI.22.00155","journal-title":"JCO Clin Cancer Inform"},{"key":"e_1_3_7_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICHI48887.2020.9374369"},{"key":"e_1_3_7_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458754"},{"key":"e_1_3_7_11_2","unstructured":"Gururangan S Marasovi\u0107 A Swayamdipta S et al: Don\u2019t stop pretraining: Adapt language models to domains and tasks. arXiv 10.48550\/arxiv.2004.10964"},{"key":"e_1_3_7_12_2","doi-asserted-by":"crossref","unstructured":"Devlin J Chang MW Lee K et al: BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the NAACL-HLT 2019 Minneapolis MN June 2-7 2019 pp 4171-4186","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_7_13_2","doi-asserted-by":"publisher","DOI":"10.1197\/jamia.M2408"},{"key":"e_1_3_7_14_2","unstructured":"Data Sets | National NLP Clinical Challenges (n2c2). Harvard.edu. https:\/\/n2c2.dbmi.hms.harvard.edu\/data-sets"},{"key":"e_1_3_7_15_2","doi-asserted-by":"crossref","unstructured":"Edin J Maistro M Maal\u00f8e L et al: An unsupervised approach to achieve supervised-level explainability in healthcare records. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing Association for Computational Linguistics Miami FL November 2024 pp 4869-4890","DOI":"10.18653\/v1\/2024.emnlp-main.280"},{"key":"e_1_3_7_16_2","unstructured":"Su P Ding X Zhang Y et al: Long-term blood pressure prediction with deep recurrent neural networks. arXiv 10.48550\/arxiv.1705.04524"},{"key":"e_1_3_7_17_2","unstructured":"Arunmozhi. Tecoholic\/ner-annotator. GitHub. https:\/\/github.com\/tecoholic\/ner-annotator"},{"key":"e_1_3_7_18_2","unstructured":"Introducing gpt-oss. Openai.com. https:\/\/openai.com\/index\/introducing-gpt-oss\/"},{"key":"e_1_3_7_19_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"e_1_3_7_20_2","unstructured":"Alsentzer E Murphy JR Boag W et al: Publicly available clinical BERT embeddings. arXiv 10.48550\/arxiv.1904.03323"},{"key":"e_1_3_7_21_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00455-y"},{"key":"e_1_3_7_22_2","unstructured":"Wolf T Debut L Sanh V et al: HuggingFace\u2019s transformers: State-of-the-art natural language processing. arXiv 10.48550\/arXiv.1910.03771"},{"key":"e_1_3_7_23_2","volume-title":"Natural Language Processing with Python","author":"Steven B","year":"2009","unstructured":"Steven B, Loper E, Klein E: Natural Language Processing with Python. Sebastopol, CA, O'Reilly Media, 2009"},{"key":"e_1_3_7_24_2","unstructured":"Nakayama H: seqeval: A python framework for sequence labeling evaluation. 2018. https:\/\/github.com\/chakki-works\/seqeval"},{"key":"e_1_3_7_25_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-024-02231-4"}],"container-title":["JCO Clinical Cancer Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ascopubs.org\/doi\/pdfdirect\/10.1200\/CCI-25-00223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T21:00:17Z","timestamp":1764622817000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascopubs.org\/doi\/10.1200\/CCI-25-00223"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":24,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["10.1200\/CCI-25-00223"],"URL":"https:\/\/doi.org\/10.1200\/cci-25-00223","relation":{},"ISSN":["2473-4276"],"issn-type":[{"value":"2473-4276","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"2025-07-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-28","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2500223"}}