文献速递胸部介入CT

机器学习预测支气管镜肺活检无诊断结果后CT引导肺活检的严重不良事件与补救活检成功

Machine learning predicts severe adverse events and salvage success of CT-guided lung biopsy after nondiagnostic transbronchial lung biopsy.
PubMed 文献 · Eur Radiol · 2025-09-22

这项多中心预测建模研究纳入2910例接受CT引导经皮肺活检(PNLB)的病例,开发双机器学习模型:模型1预测严重不良事件(SAE),模型2预测经支气管镜肺活检(TBLB)失败后补救PNLB的诊断成功。外部验证显示模型1的ROC-AUC为0.717、模型2的ROC-AUC为0.884,XGBoost算法表现最优。

要点

  • 模型1预测PNLB严重不良事件,外部验证ROC-AUC 0.717(95%CI 0.609-0.825)。
  • 模型2预测TBLB失败后补救PNLB诊断成功,外部验证ROC-AUC 0.884(95%CI 0.784-0.984)。
  • 双XGBoost系统可量化SAE风险与诊断成功率,辅助个体化补救活检决策。

核心结论

  • 双XGBoost系统通过量化SAE风险(AUC=0.717)与诊断成功率(AUC=0.884)对补救PNLB候选者进行分层,回应了个体化活检路径优化的未满足需求。

研究设计与样本

  • 多中心预测建模研究,纳入2910例接受PNLB的病例(中心1:n=2653,2016-2020年;中心2:n=257,2017-2022年),影像与临床资料完整并符合预设纳入和排除标准。

诊断标准与关键数值

  • 模型1纳入性别、吸烟、胸膜接触、病灶大小和穿刺深度,外部验证ROC-AUC 0.717(95%CI 0.609-0.825)、PR-AUC 0.258(95%CI 0.0365-0.708)。

临床应用与阅片要点

  • 模型2纳入年龄、病灶大小、病灶特征和支气管镜后病理分类(PBPCs),外部验证ROC-AUC 0.884(95%CI 0.784-0.984)、PR-AUC 0.852(95%CI 0.784-0.896),XGBoost优于其他算法。

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)。

英文原文(摘要)· 点击展开

OBJECTIVES: To address the unmet clinical need for validated risk stratification tools in salvage CT-guided percutaneous lung biopsy (PNLB) following nondiagnostic transbronchial lung biopsy (TBLB). We aimed to develop machine learning models predicting severe adverse events (SAEs) in PNLB (Model 1) and diagnostic success of salvage PNLB post-TBLB failure (Model 2).

MATERIALS AND METHODS: This multicenter predictive modeling study enrolled 2910 cases undergoing PNLB across two centers (Center 1: n = 2653 (2016-2020); Center 2: n = 257 (2017-2022)) with complete imaging and clinical documentation meeting predefined inclusion and exclusion criteria. Key variables were selected via LASSO regression, followed by development and validation of Model 1 (incorporating sex, smoking, pleural contact, lesion size, and puncture depth) and Model 2 (including age, lesion size, lesion characteristics, and post-bronchoscopic pathological categories (PBPCs)) using ten machine learning algorithms. Model performance was rigorously evaluated through discrimination metrics, calibration curves, and decision curve analysis to assess clinical applicability.

RESULTS: A total of 2653 and 257 PNLB cases were included from two centers, where Model 1 achieved external validation ROC-AUC 0.717 (95% CI: 0.609-0.825) and PR-AUC 0.258 (95% CI: 0.0365-0.708), while Model 2 exhibited ROC-AUC 0.884 (95% CI: 0.784-0.984) and PR-AUC 0.852 (95% CI: 0.784-0.896), with XGBoost outperforming other algorithms.

CONCLUSION: The dual XGBoost system stratifies salvage PNLB candidates by quantifying SAE risks (AUC = 0.717) versus diagnostic yield (AUC = 0.884), addressing the unmet need for personalized biopsy pathway optimization.

KEY POINTS: Question Current tools cannot quantify severe adverse event (SAE) risks versus salvage diagnostic success for CT-guided lung biopsy (PNLB) after failed transbronchial biopsy (TBLB). Findings Dual XGBoost models successfully predicted the risks of PNLB SAEs (AUC = 0.717) and diagnostic success post-TBLB failure (AUC = 0.884) with validated clinical stratification benefits. Clinical relevance The dual XGBoost system guides clinical decision-making by integrating individual risk of SAEs with predictors of diagnostic success, enabling personalized salvage biopsy strategies that balance safety and diagnostic yield.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Yang S, Hua Z, Chen Y, et al. Machine learning predicts severe adverse events and salvage success of CT-guided lung biopsy after nondiagnostic transbronchial lung biopsy. Eur Radiol. 2025. PMID: 40981990. doi:10.1007/s00330-025-12000-6

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。