EUVIMEDEUVIMED entdecken
Open Access

SmokeBERT: A Bidirectional Encoder Representations From Transformers–Based Model for Quantitative Smoking History Extraction From Clinical Narratives to Improve Lung Cancer Screening

Yiming Xue, Yunzheng Zhu iD, Luoting Zhuang iD, YongKyung Oh iD, Ricky Taira, Denise R Aberle iD, Ashley Elizabeth Prosper iD, William Hsu iD, Yannan Lin iD

JCO Clinical Cancer Informatics · 2025

DOI: 10.1200/cci-25-00223 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JCO Clinical Cancer Informatics, 2025. Verfasst von Yiming Xue und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistics and Data Science, University of California, Los Angeles, CA. Hauptthemen laut MEDLINE: Lung Neoplasms, Natural Language Processing, Early Detection of Cancer, Smoking. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCATS NIH HHS, NCI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE 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. METHODS We cross-validated four pretrained Bidirectional Encoder Representations from Transformers (BERT)–based models—BERT, BioBERT, ClinicalBERT, and MedBERT—by 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. RESULTS 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 v 0.88-0.90; external validation: 0.86 v 0.72-0.79) and in identifying LCS-eligible patients (97% v 59%-97% for ≥20 pack-years and 100% v 60%-84% for ≤15 years since quitting). CONCLUSION 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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Lung NeoplasmsNatural Language ProcessingEarly Detection of CancerSmokingHumansMaleFemaleNarration

Autor:innen und Institutionen

  • Department of Statistics and Data Science, University of California, Los Angeles, CA.
  • Medical and Imaging Informatics, Department of Radiological Sciences, David Geffen School of Medicine at UCLA, Los Angeles, CA.

ORCID-Profile: Yunzheng Zhu, Luoting Zhuang, YongKyung Oh, Denise R Aberle, Ashley Elizabeth Prosper, William Hsu, Yannan Lin

Förderung

  • NCATS NIH HHS
  • NCI NIH HHS

Zitieren

APA

Xue, Y., Zhu, Y., Zhuang, L., Oh, Y., Taira, R., Aberle, D. R., Prosper, A. E., Hsu, W., & Lin, Y. (2025). SmokeBERT: A Bidirectional Encoder Representations From Transformers–Based Model for Quantitative Smoking History Extraction From Clinical Narratives to Improve Lung Cancer Screening. JCO Clinical Cancer Informatics. https://doi.org/10.1200/cci-25-00223

Vancouver

Xue Y, Zhu Y, Zhuang L, Oh Y, Taira R, Aberle DR, et al. SmokeBERT: A Bidirectional Encoder Representations From Transformers–Based Model for Quantitative Smoking History Extraction From Clinical Narratives to Improve Lung Cancer Screening. JCO Clinical Cancer Informatics. 2025. doi:10.1200/cci-25-00223

BibTeX
@article{Xue2025,
  author = {Xue, Yiming and Zhu, Yunzheng and Zhuang, Luoting and Oh, YongKyung and Taira, Ricky and Aberle, Denise R and Prosper, Ashley Elizabeth and Hsu, William and Lin, Yannan},
  title = {SmokeBERT: A Bidirectional Encoder Representations From Transformers–Based Model for Quantitative Smoking History Extraction From Clinical Narratives to Improve Lung Cancer Screening},
  journal = {JCO Clinical Cancer Informatics},
  year = {2025},
  doi = {10.1200/cci-25-00223}
}
Kostenlos starten →