文献速递胸部介入CT

开发预测同轴核心针活检(≤3 cm)气胸风险的机器学习模型

Development of a machine learning model for predicting pneumothorax risk in coaxial core needle biopsy (≤3 cm).
PubMed 文献 · Eur J Radiol · 2024-05-15

本研究回顾性纳入325例接受同轴核心针肺活检的≤3 cm肺结节患者,19.6%(64/325)术后发生气胸。采用LASSO回归筛选变量并比较多种机器学习分类器,高斯朴素贝叶斯(GNB)模型在测试集中预测气胸的AUC为0.82(95%CI 0.71-0.94),准确率0.8、敏感度0.71、特异度0.84、F1分数0.61。

要点

  • 325例≤3 cm肺结节同轴核心针活检中,19.6%(64/325)术后发生气胸。
  • 高危因素为Cancer、Lesion_type、GOLD、Size和Depth。
  • GNB模型测试集AUC 0.82(95%CI 0.71-0.94),准确率0.8、敏感度0.71、特异度0.84、F1分数0.61。

核心结论

  • 所构建的预后算法在术前预测同轴核心针肺活检所致气胸方面表现出良好效能,可能有助于完善个体化风险评估、指导临床判断并改善围术期患者管理。

研究设计与样本

  • 回顾性分析,纳入325例接受同轴核心针肺活检的≤3 cm肺结节患者,采用单因素分析和LASSO回归筛选变量,数据集按80%训练集和20%验证集划分,比较多种机器学习分类器以确定最优模型,并用SHAP展示个体化风险分析。

诊断标准与关键数值

  • 高斯朴素贝叶斯(GNB)分类器在测试队列中AUC为0.82(95%CI 0.71-0.94),准确率0.8、敏感度0.71、特异度0.84、F1分数0.61。

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

PURPOSE: The aim is to devise a machine learning algorithm exploiting preoperative clinical data to forecast the hazard of pneumothorax post-coaxial needle lung biopsy (CCNB), thereby informing clinical decision-making and enhancing perioperative care.

METHOD: This retrospective analysis aggregated clinical and imaging data from patients with lung nodules (≤3 cm) biopsies. Variable selection was done using univariate analysis and LASSO regression, with the dataset subsequently divided into training (80 %) and validation (20 %) subsets. Various machine learning (ML) classifiers were employed in a consolidated approach to ascertain the paramount model, which was followed by individualized risk profiling showcased through Shapley Additive eXplanations (SHAP).

RESULTS: Out of the 325 patients included in the study, 19.6% (64/325) experienced postoperative pneumothorax. High-risk factors determined were Cancer, Lesion_type, GOLD, Size, and Depth. The Gaussian Naive Bayes (GNB) classifier demonstrated superior prediction with an Area Under the Curve (AUC) of 0.82 (95% CI 0.71-0.94), complemented by an accuracy rate of 0.8, sensitivity of 0.71, specificity of 0.84, and an F1 score of 0.61 in the test cohort.

CONCLUSION: The formulated prognostic algorithm exhibited commendable efficacy in preoperatively prognosticating CCNB-induced pneumothorax, harboring the potential to refine personalized risk appraisals, steer clinical judgment, and ameliorate perioperative patient stewardship.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Zou X, Cui N, Ma Q, et al. Development of a machine learning model for predicting pneumothorax risk in coaxial core needle biopsy (≤3 cm). Eur J Radiol. 2024. PMID: 38759543. doi:10.1016/j.ejrad.2024.111508

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。