{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T22:11:42Z","timestamp":1793484702081,"version":"4.5.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T00:00:00Z","timestamp":1764288000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T00:00:00Z","timestamp":1764288000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["1R01CA282793"],"award-info":[{"award-number":["1R01CA282793"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cancer Center Support Grant (CCSG) of the National Cancer Institute","award":["P30CA124435"],"award-info":[{"award-number":["P30CA124435"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-025-02009-y","type":"journal-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T15:00:23Z","timestamp":1764342023000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Leveraging large language models to extract smoking history from clinical notes for lung cancer surveillance"],"prefix":"10.1038","volume":"8","author":[{"given":"Ingrid","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Graber-Naidich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengrui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rakshit","family":"Kaushik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Grant M.","family":"Nieda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tony","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eunji","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victoria Y.","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fatma","family":"Gunturkun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mina","family":"Satoyoshi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Archana","family":"Bhat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tae Yoon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chloe C.","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timothy John","family":"Ellis-Caleo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A. Solomon","family":"Henry","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manisha","family":"Desai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leah M.","family":"Backhus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Natalie S.","family":"Lui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ann","family":"Leung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joel W.","family":"Neal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Allison W.","family":"Kurian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Curtis P.","family":"Langlotz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heather A.","family":"Wakelee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Su-Ying","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aparajita","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Summer S.","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,28]]},"reference":[{"key":"2009_CR1","unstructured":"National Center for Chronic Disease Prevention and Health Promotion (US) Office on Smoking and Health. The Health Consequences of Smoking\u201450 Years of Progress: A Report of the Surgeon General(Centers for Disease Control and Prevention (US), Atlanta (GA), (2014)."},{"key":"2009_CR2","first-page":"10","volume":"75","author":"RL Siegel","year":"2025","unstructured":"Siegel, R. L., Kratzer, T. B., Giaquinto, A. N., Sung, H. & Jemal, A. Cancer statistics, 2025. Ca. Cancer J. Clin. 75, 10\u201345 (2025).","journal-title":"Ca. Cancer J. Clin."},{"key":"2009_CR3","doi-asserted-by":"publisher","first-page":"640","DOI":"10.2188\/jea.JE20220206","volume":"33","author":"M Scala","year":"2023","unstructured":"Scala, M. et al. Dose-response relationships between cigarette smoking and breast cancer risk: a systematic review and meta-analysis. J. Epidemiol. 33, 640\u2013648 (2023).","journal-title":"J. Epidemiol."},{"key":"2009_CR4","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1007\/s10555-017-9689-6","volume":"36","author":"AR Jethwa","year":"2017","unstructured":"Jethwa, A. R. & Khariwala, S. S. Tobacco-related carcinogenesis in head and neck cancer. Cancer Metastasis Rev. 36, 411\u2013423 (2017).","journal-title":"Cancer Metastasis Rev."},{"key":"2009_CR5","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1007\/s00423-007-0266-2","volume":"393","author":"S Iodice","year":"2008","unstructured":"Iodice, S., Gandini, S., Maisonneuve, P. & Lowenfels, A. B. Tobacco and the risk of pancreatic cancer: a review and meta-analysis. Langenbecks Arch. Surg. 393, 535\u2013545 (2008).","journal-title":"Langenbecks Arch. Surg."},{"key":"2009_CR6","doi-asserted-by":"publisher","first-page":"17420","DOI":"10.18632\/oncotarget.24724","volume":"9","author":"L Jacob","year":"2018","unstructured":"Jacob, L., Freyn, M., Kalder, M., Dinas, K. & Kostev, K. Impact of tobacco smoking on the risk of developing 25 different cancers in the UK: a retrospective study of 422,010 patients followed for up to 30 years. Oncotarget 9, 17420\u201317429 (2018).","journal-title":"Oncotarget"},{"key":"2009_CR7","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1002\/cncr.35069","volume":"130","author":"E Choi","year":"2024","unstructured":"Choi, E. et al. Risk model-based management for second primary lung cancer among lung cancer survivors through a validated risk prediction model. Cancer 130, 770\u2013780 (2024).","journal-title":"Cancer"},{"key":"2009_CR8","doi-asserted-by":"publisher","first-page":"330","DOI":"10.7326\/M13-2771","volume":"160","author":"VA Moyer","year":"2014","unstructured":"Moyer, V. A. & Preventive Services Task Force, U. S. Screening for lung cancer: U.S. preventive services task force recommendation statement. Ann. Intern. Med. 160, 330\u2013338 (2014).","journal-title":"Ann. Intern. Med."},{"key":"2009_CR9","doi-asserted-by":"crossref","unstructured":"US Preventive Services Task Force. Screening for Lung Cancer: US Preventive Services Task Force Recommendation Statement. JAMA 325, 962\u2013970 (2021).","DOI":"10.1001\/jama.2021.1117"},{"key":"2009_CR10","unstructured":"Polubriaginof, F., Salmasian, H., Albert, D. A. & Vawdrey, D. K. Challenges with collecting smoking status in electronic health records. AMIA. Annu. Symp. Proc. 2017, 1392\u20131400 (2018)."},{"key":"2009_CR11","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1016\/j.amepre.2019.10.020","volume":"58","author":"N Patel","year":"2020","unstructured":"Patel, N. et al. A comparison of smoking history in the electronic health record with self-report. Am. J. Prev. Med. 58, 591\u2013595 (2020).","journal-title":"Am. J. Prev. Med."},{"key":"2009_CR12","doi-asserted-by":"publisher","DOI":"10.1186\/s13104-018-3124-0","volume":"11","author":"AM Cole","year":"2018","unstructured":"Cole, A. M., Pflugeisen, B., Schwartz, M. R. & Miller, S. C. Cross sectional study to assess the accuracy of electronic health record data to identify patients in need of lung cancer screening. BMC Res. Notes 11, 14 (2018).","journal-title":"BMC Res. Notes"},{"key":"2009_CR13","first-page":"237","volume":"15","author":"L Wang","year":"2016","unstructured":"Wang, L., Ruan, X., Yang, P. & Liu, H. Comparison of three information sources for smoking information in electronic health records. Cancer Inf. 15, 237\u2013242 (2016).","journal-title":"Cancer Inf."},{"key":"2009_CR14","doi-asserted-by":"publisher","unstructured":"Yang, X. et al. A natural language processing tool to extract quantitative smoking status from clinical narratives. in 2020 IEEE International Conference on Healthcare Informatics (ICHI) 1\u20132 https:\/\/doi.org\/10.1109\/ICHI48887.2020.9374369 (2020).","DOI":"10.1109\/ICHI48887.2020.9374369"},{"key":"2009_CR15","doi-asserted-by":"publisher","first-page":"e42477","DOI":"10.2196\/42477","volume":"11","author":"A Bazoge","year":"2023","unstructured":"Bazoge, A., Morin, E., Daille, B. & Gourraud, P.-A. Applying natural language processing to textual data from clinical data warehouses: systematic review. JMIR Med. Inform. 11, e42477 (2023).","journal-title":"JMIR Med. Inform."},{"key":"2009_CR16","doi-asserted-by":"publisher","unstructured":"Ruckdeschel, J. C. et al. Unstructured data are superior to structured data for eliciting quantitative smoking history from the electronic health record. JCO Clin. Cancer Inform. e2200155 https:\/\/doi.org\/10.1200\/CCI.22.00155 (2023).","DOI":"10.1200\/CCI.22.00155"},{"key":"2009_CR17","first-page":"1225","volume":"2021","author":"Z Yu","year":"2022","unstructured":"Yu, Z. et al. A study of social and behavioral determinants of health in lung cancer patients using transformers-based natural language processing models. Amia. Annu. Symp. Proc. 2021, 1225\u20131233 (2022).","journal-title":"Amia. Annu. Symp. Proc."},{"key":"2009_CR18","doi-asserted-by":"publisher","first-page":"8812","DOI":"10.3390\/app11198812","volume":"11","author":"YS Bae","year":"2021","unstructured":"Bae, Y. S. et al. Keyword extraction algorithm for classifying smoking status from unstructured bilingual electronic health records based on natural language processing. Appl. Sci. 11, 8812 (2021).","journal-title":"Appl. Sci."},{"key":"2009_CR19","doi-asserted-by":"publisher","unstructured":"Xue, Y. et al. SmokeBERT: a BERT-based model for quantitative smoking history extraction from clinical narratives to improve lung cancer screening. medRxiv https:\/\/doi.org\/10.1101\/2025.06.18.25329870 (2025).","DOI":"10.1101\/2025.06.18.25329870"},{"key":"2009_CR20","doi-asserted-by":"publisher","first-page":"e56243","DOI":"10.2196\/56243","volume":"12","author":"F Shah-Mohammadi","year":"2024","unstructured":"Shah-Mohammadi, F. & Finkelstein, J. Extraction of substance use information from clinical notes: generative pretrained transformer\u2013based investigation. JMIR Med. Inform. 12, e56243 (2024).","journal-title":"JMIR Med. Inform."},{"key":"2009_CR21","first-page":"509","volume":"2024","author":"N Bhagat","year":"2024","unstructured":"Bhagat, N., Mackey, O. & Wilcox, A. Large language models for efficient medical information extraction. AMIA Summits Transl. Sci. Proc. 2024, 509\u2013514 (2024).","journal-title":"AMIA Summits Transl. Sci. Proc."},{"key":"2009_CR22","doi-asserted-by":"publisher","first-page":"e65984","DOI":"10.2196\/65984","volume":"11","author":"D Chen","year":"2025","unstructured":"Chen, D., Alnassar, S. A., Avison, K. E., Huang, R. S. & Raman, S. Large language model applications for health information extraction in oncology: scoping review. JMIR Cancer 11, e65984 (2025).","journal-title":"JMIR Cancer"},{"key":"2009_CR23","doi-asserted-by":"publisher","unstructured":"Wu, J. et al. Hazard-aware adaptations bridge the generalization gap in large language models: a nationwide study. Preprint at https:\/\/doi.org\/10.1101\/2025.02.14.25322312 (2025).","DOI":"10.1101\/2025.02.14.25322312"},{"key":"2009_CR24","doi-asserted-by":"publisher","unstructured":"LeLaurin, J. H. et al. Concordance between electronic health record and tumor registry documentation of smoking status among patients with cancer. JCO Clin. Cancer Inform. 518\u2013526 https:\/\/doi.org\/10.1200\/CCI.20.00187 (2021).","DOI":"10.1200\/CCI.20.00187"},{"key":"2009_CR25","first-page":"30","volume":"46","author":"P Krebs","year":"2019","unstructured":"Krebs, P. et al. Utility of using cancer registry data to identify patients for tobacco treatment trials. J. Regist. Manag. 46, 30\u201336 (2019).","journal-title":"J. Regist. Manag."},{"key":"2009_CR26","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1038\/s41586-024-07421-0","volume":"630","author":"S Farquhar","year":"2024","unstructured":"Farquhar, S., Kossen, J., Kuhn, L. & Gal, Y. Detecting hallucinations in large language models using semantic entropy. Nature 630, 625\u2013630 (2024).","journal-title":"Nature"},{"key":"2009_CR27","doi-asserted-by":"publisher","unstructured":"Kim, Y. et al. Medical Hallucination in Foundation Models and Their Impact on Healthcare. Preprint at https:\/\/doi.org\/10.1101\/2025.02.28.25323115 (2025).","DOI":"10.1101\/2025.02.28.25323115"},{"key":"2009_CR28","first-page":"968","volume":"16","author":"JV Aredo","year":"2021","unstructured":"Aredo, J. V. et al. Tobacco smoking and risk of second primary lung cancer. J. Thorac. Oncol. Publ. Int. Assoc. Study Lung Cancer 16, 968\u2013979 (2021).","journal-title":"J. Thorac. Oncol. Publ. Int. Assoc. Study Lung Cancer"},{"key":"2009_CR29","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1093\/jnci\/djab138","volume":"114","author":"E Choi","year":"2021","unstructured":"Choi, E. et al. Development and validation of a risk prediction model for second primary lung cancer. JNCI J. Natl. Cancer Inst. 114, 87\u201396 (2021).","journal-title":"JNCI J. Natl. Cancer Inst."},{"key":"2009_CR30","doi-asserted-by":"crossref","unstructured":"Bazoge, A., Morin, E., Daille, B. & Gourraud, P. A. Applying Natural Language Processing to Textual Data From Clinical Data Warehouses: Systematic Review. JMIR Med Inform 11, e42477 (2023).","DOI":"10.2196\/42477"},{"key":"2009_CR31","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-019-0863-3","volume":"19","author":"EL Palmer","year":"2019","unstructured":"Palmer, E. L., Hassanpour, S., Higgins, J., Doherty, J. A. & Onega, T. Building a tobacco user registry by extracting multiple smoking behaviors from clinical notes. BMC Med. Inform. Decis. Mak. 19, 141 (2019).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"2009_CR32","doi-asserted-by":"publisher","first-page":"105136","DOI":"10.1016\/j.ijmedinf.2023.105136","volume":"177","author":"S Liu","year":"2023","unstructured":"Liu, S. et al. Leveraging natural language processing to identify eligible lung cancer screening patients with the electronic health record. Int. J. Med. Inf. 177, 105136 (2023).","journal-title":"Int. J. Med. Inf."},{"key":"2009_CR33","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1093\/jamia\/ocac020","volume":"29","author":"PV Kukhareva","year":"2022","unstructured":"Kukhareva, P. V. et al. Inaccuracies in electronic health records smoking data and a potential approach to address resulting underestimation in determining lung cancer screening eligibility. J. Am. Med. Inform. Assoc. JAMIA 29, 779\u2013788 (2022).","journal-title":"J. Am. Med. Inform. Assoc. JAMIA"},{"key":"2009_CR34","doi-asserted-by":"crossref","unstructured":"Martin, P. M. Can we trust electronic health records? The smoking test for commission errors. BMJ Health Care Inform. 25, 105\u2013108 (2018).","DOI":"10.14236\/jhi.v25i2.970"},{"key":"2009_CR35","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-020-1068-5","volume":"20","author":"S Garies","year":"2020","unstructured":"Garies, S. et al. Methods to improve the quality of smoking records in a primary care EMR database: exploring multiple imputation and pattern-matching algorithms. BMC Med. Inform. Decis. Mak. 20, 56 (2020).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"2009_CR36","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-024-02231-4","volume":"24","author":"A Ebrahimi","year":"2024","unstructured":"Ebrahimi, A. et al. Identification of patients\u2019 smoking status using an explainable AI approach: a Danish electronic health records case study. BMC Med. Res. Methodol. 24, 114 (2024).","journal-title":"BMC Med. Res. Methodol."},{"key":"2009_CR37","doi-asserted-by":"publisher","first-page":"101139","DOI":"10.1016\/j.imu.2022.101139","volume":"36","author":"A Turchin","year":"2023","unstructured":"Turchin, A., Masharsky, S. & Zitnik, M. Comparison of BERT implementations for natural language processing of narrative medical documents. Inform. Med. Unlocked 36, 101139 (2023).","journal-title":"Inform. Med. Unlocked"},{"key":"2009_CR38","doi-asserted-by":"publisher","first-page":"104509","DOI":"10.1016\/j.jbi.2023.104509","volume":"147","author":"Y Ramakrishnaiah","year":"2023","unstructured":"Ramakrishnaiah, Y., Macesic, N., Webb, G. I., Peleg, A. Y. & Tyagi, S. EHR-QC: A streamlined pipeline for automated electronic health records standardisation and preprocessing to predict clinical outcomes. J. Biomed. Inform. 147, 104509 (2023).","journal-title":"J. Biomed. Inform."},{"key":"2009_CR39","doi-asserted-by":"publisher","first-page":"e23292","DOI":"10.1200\/JCO.2025.43.16_suppl.e23292","volume":"43","author":"C Su","year":"2025","unstructured":"Su, C. et al. Oncoshare-lung: novel three-way linkage of neighboring academic and community medical centers to state cancer registry for lung cancer. J. Clin. Oncol. 43, e23292\u2013e23292 (2025).","journal-title":"J. Clin. Oncol."},{"key":"2009_CR40","unstructured":"Network, NationalComprehensiveCancer Treatment by Cancer Type, Accessed March 1, 2022."},{"key":"2009_CR41","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1016\/S0022-5223(19)40289-4","volume":"70","author":"N Martini","year":"1975","unstructured":"Martini, N. & Melamed, M. R. Multiple primary lung cancers. J. Thorac. Cardiovasc. Surg. 70, 606\u2013612 (1975).","journal-title":"J. Thorac. Cardiovasc. Surg."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02009-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02009-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02009-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T03:02:02Z","timestamp":1764385322000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02009-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,28]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["2009"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-02009-y","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,28]]},"assertion":[{"value":"11 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"731"}}