文献速递血栓与止血

静脉血栓栓塞症双向编码器表示从变换器(VTE-BERT)自然语言处理模型的开发与验证

Development and validation of venous thromboembolism-bidirectional encoder representations from transformers (VTE-BERT) natural language processing model.
PubMed 文献 · J Thromb Haemost · 2025-08-05

研究开发并验证了VTE-BERT自然语言处理模型,用于纵向检测新发静脉血栓栓塞症事件。模型在内部验证中精确率95%、召回率91%,外部验证中精确率85%、召回率92%。作者认为该模型可加速血栓研究。

要点

  • VTE-BERT在内部验证中精确率95%、召回率91%。
  • VTE-BERT在外部验证中精确率85%、召回率92%。
  • 模型训练至患者层面精确率95%、召回率98%。

核心结论

  • 研究训练并外部验证了一个高效的自然语言处理模型,可纵向检测新发静脉血栓栓塞症事件。
  • 作者认为采用该模型可通过大规模改进VTE检测并减少大数据流行病学研究中人工病历审查的时间和费用来加速血栓研究。

研究设计与样本

  • 研究设计了一个新型自然语言处理平台NLPMed,辅助血栓研究人员进行数据预处理、表型标注、语言模型微调和自然语言处理应用。
  • 使用来自2个医疗机构的癌症患者的临床笔记、出院小结和放射学报告,微调Bio_Clinical双向编码器表示从变换器(BERT)以开发VTE-BERT。
  • 新模型被训练以纵向检测急性VTE事件及其解剖位置,并在2个随机抽样的晚期癌症患者队列中内部和外部验证模型性能。
  • 训练队列由Harris Health System的715名患者和14 013条含至少1个VTE关键词的标注笔记组成。
  • 内部验证队列包括来自Harris Health System的另外400名患者和7190条含VTE关键词的笔记;外部验证队列包括来自国家退伍军人事务医疗系统的400名患者和7371条含VTE关键词的笔记。

主要发现

  • VTE-BERT训练至患者层面精确率95%和召回率98%。
  • 使用独立数据集,模型在内部验证中达到精确率95%和召回率91%。
  • 使用独立数据集,模型在外部验证中达到精确率85%和召回率92%。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: Accurate and rapid phenotyping of venous thromboembolism (VTE) in longitudinal studies is important. A natural language processing (NLP) tool externally validated in representative patients is lacking. OBJECTIVES: To train and validate an efficient NLP model to detect incident VTE event. METHODS: We designed a novel NLP platform, NLPMed, to assist thrombosis researchers with data preprocessing, phenotype annotation, language model finetuning, and NLP application. Using clinical notes, discharge summaries, and radiology reports from patients with cancer at 2 healthcare institutions, we finetuned Bio_Clinical Bidirectional Encoder Representations from Transformers (BERT) to develop VTE-BERT. The new model was trained to detect acute VTE events and their anatomical locations longitudinally. We internally and externally validated the model's performance in 2 randomly sampled cohorts of patients with advanced cancer. RESULTS: The training cohort consisted of 715 patients and 14 013 annotated notes with ≥1 VTE keyword from the Harris Health System. The internal validation cohort included 400 additional patients with 7190 VTE keyword-containing notes from Harris Health System. The external validation cohort included 400 patients with 7371 VTE keyword-containing notes from the national Veterans Affairs healthcare system. VTE-BERT was trained until it reached a precision of 95% and recall of 98% on the patient level. Using independent datasets, the model achieved precision and recall of 95% and 91% in internal validation and of 85% and 92% in external validation. CONCLUSION: We trained and externally validated an efficient NLP model to detect incident VTE events longitudinally. We believe its adoption will accelerate thrombosis research by improving VTE detection at scale and decreasing the time and expense involved with manual chart review in big data epidemiological studies.

来源:J Thromb Haemost,查看原文。版权归原作者所有。

引用

  1. Jafari O, Ma S, Lam BD, et al. Development and validation of venous thromboembolism-bidirectional encoder representations from transformers (VTE-BERT) natural language processing model. J Thromb Haemost. 2025. PMID: 40754035. doi:10.1016/j.jtha.2025.07.021

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。