{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T13:59:15Z","timestamp":1768571955205,"version":"3.49.0"},"posted":{"date-parts":[[2025,6,20]]},"group-title":"Health Informatics","reference-count":24,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T00:00:00Z","timestamp":1750377600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,6,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Tobacco use is a critical risk factor for diseases such as cancer and cardiovascular disorders. While electronic health records can capture categorical smoking statuses accurately, granular quantitative details, such as pack years and years since quitting, are often embedded in clinical narratives. This information is crucial for assessing disease risk and determining eligibility for lung cancer screening (LCS). Existing natural language processing (NLP) tools excelled at identifying smoking statuses but struggled with extracting detailed quantitative data. To address this, we developed SmokeBERT, a fine-tuned BERT-based model optimized for extracting detailed smoking histories. Evaluations against a state-of-the-art rule-based NLP model demonstrated its superior performance on F1 scores (0.97 vs. 0.88 on the hold-out test set) and identification of LCS-eligible patients (e.g., 98% vs. 60% for \u226520 pack years). Future work includes creating a multilingual, language-agnostic version of SmokeBERT by incorporating datasets in multiple languages, exploring ensemble methods, and testing on larger datasets.<\/jats:p>","DOI":"10.1101\/2025.06.18.25329870","type":"posted-content","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T14:56:16Z","timestamp":1750431376000},"source":"Crossref","is-referenced-by-count":1,"title":["SmokeBERT: A BERT-based Model for Quantitative Smoking History Extraction from Clinical Narratives to Improve Lung Cancer Screening"],"prefix":"10.64898","author":[{"given":"Yiming","family":"Xue","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunzheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luoting","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"YongKyung","family":"Oh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ricky","family":"Taira","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Denise R.","family":"Aberle","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashley E.","family":"Prosper","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yannan","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2025062301301729000_2025.06.18.25329870v1.1","unstructured":"Force USPST. Lung cancer: Screening. Accessed June 18, 2025. https:\/\/www.uspreventiveservicestaskforce.org\/uspstf\/recommendation\/lung-cancer-screening"},{"key":"2025062301301729000_2025.06.18.25329870v1.2","unstructured":"State of Lung Cancer 2024 Report. Accessed June 18, 2025. https:\/\/www.lung.org\/getmedia\/12020193-7fb3-46b8-8d78-0e5d9cd8f93c\/SOLC-2024.pdf"},{"key":"2025062301301729000_2025.06.18.25329870v1.3","unstructured":"Reynolds A. New Measure Coming for Lung Cancer Screening - NCQA. Accessed June 18, 2025. https:\/\/www.ncqa.org\/blog\/new-measure-coming-for-lung-cancer-screening\/"},{"key":"2025062301301729000_2025.06.18.25329870v1.4","unstructured":"NCQA Responds to CMS\u2019s CY 2025 Medicare Advantage Advance Notice - NCQA. Accessed June 18, 2025. https:\/\/www.ncqa.org\/comment-letter\/ncqa-responds-to-cmss-cy-2025-medicare-advantage-advance-notice\/"},{"key":"2025062301301729000_2025.06.18.25329870v1.5","doi-asserted-by":"publisher","DOI":"10.4137\/CIN.S40604"},{"key":"2025062301301729000_2025.06.18.25329870v1.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2023.105136"},{"key":"2025062301301729000_2025.06.18.25329870v1.7","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2009.001560"},{"key":"2025062301301729000_2025.06.18.25329870v1.8","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocx132"},{"key":"2025062301301729000_2025.06.18.25329870v1.9","doi-asserted-by":"publisher","DOI":"10.1109\/ICHI48887.2020.9374369"},{"key":"2025062301301729000_2025.06.18.25329870v1.10","doi-asserted-by":"publisher","DOI":"10.1145\/3458754"},{"key":"2025062301301729000_2025.06.18.25329870v1.11","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2004.10964"},{"key":"2025062301301729000_2025.06.18.25329870v1.12","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume":"1","year":"2019","journal-title":"2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Naacl Hlt 2019)"},{"key":"2025062301301729000_2025.06.18.25329870v1.13","doi-asserted-by":"publisher","DOI":"10.1197\/jamia.M2408"},{"key":"2025062301301729000_2025.06.18.25329870v1.14","unstructured":"Data Sets | National NLP Clinical Challenges (n2c2). Harvard.edu. Accessed June 18, 2025. https:\/\/n2c2.dbmi.hms.harvard.edu\/data-sets"},{"key":"2025062301301729000_2025.06.18.25329870v1.15","doi-asserted-by":"crossref","unstructured":"Edin J , Maistro M , Maaloe L , Borgholt L , Havtorn JD , Ruotsalo T. An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records. 2024 Conference on Empirical Methods in Natural Language Processing, Emnlp 2024. 2024:4869\u20134890.","DOI":"10.18653\/v1\/2024.emnlp-main.280"},{"key":"2025062301301729000_2025.06.18.25329870v1.16","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1705.04524"},{"key":"2025062301301729000_2025.06.18.25329870v1.17","unstructured":"Arunmozhi. tecoholic\/ner-annotator. GitHub. Accessed June 18, 2025. https:\/\/github.com\/tecoholic\/ner-annotator"},{"key":"2025062301301729000_2025.06.18.25329870v1.18","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"2025062301301729000_2025.06.18.25329870v1.19","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1904.03323"},{"key":"2025062301301729000_2025.06.18.25329870v1.20","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00455-y"},{"key":"2025062301301729000_2025.06.18.25329870v1.21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1910.03771"},{"key":"2025062301301729000_2025.06.18.25329870v1.22","unstructured":"Natural Language Toolkit \u2014 NLTK 3.4.4 documentation. Nltk.org. Accessed June 18, 2025."},{"key":"2025062301301729000_2025.06.18.25329870v1.23","unstructured":"seqeval. GitHub. Accessed June 18, 2025."},{"key":"2025062301301729000_2025.06.18.25329870v1.24","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-024-02231-4"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.06.18.25329870","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:38:48Z","timestamp":1768509528000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.06.18.25329870"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1101\/2025.06.18.25329870","relation":{},"subject":[],"published":{"date-parts":[[2025,6,20]]},"subtype":"preprint"}}