文献速递神经介入DSA

预测颅内动脉瘤破裂:结合Radscore、形态学与PHASES参数的多因素分析

Predicting Intracranial Aneurysm Rupture: A Multifactor Analysis Combining Radscore, Morphology, and PHASES Parameters.
PubMed 文献 · Acad Radiol · 2024-08-10

研究纳入2015至2023年本院440例患者的475个颅内动脉瘤(214个破裂、261个未破裂),基于DSA提取的影像组学评分、形态学参数和PHASES构建列线图及四种机器学习模型预测破裂。测试集中多因素LR模型R+M+P的AUC为0.887,四种机器学习模型AUC为0.880至0.892,列线图与机器学习模型在决策曲线分析和校准曲线中表现良好。

要点

  • 基于DSA的影像组学评分联合形态学与PHASES可预测颅内动脉瘤破裂。
  • 测试集中LR模型R+M+P的AUC为0.887,R+M为0.818,R+P为0.899。
  • 测试集中四种机器学习模型AUC为0.880至0.892,与LR模型无统计学显著差异。

核心结论

  • 基于Radscore、形态学和PHASES的列线图与机器学习模型在预测动脉瘤破裂方面表现出高精度。

研究设计与样本

  • 研究为在本院收集2015至2023年440例患者的475个颅内动脉瘤(214个破裂、261个未破裂)的预测模型开发与验证研究。
  • 采用7:3随机划分将参与者分为训练集和测试集。
  • 从数字减影血管造影(DSA)提取影像组学特征,采用t检验和LASSO回归优化特征选择。
  • 构建单因素和多因素逻辑回归模型及列线图,并采用四种机器学习算法。
  • 通过AUC、校准曲线、决策曲线分析(DCA)等指标综合评估确定最佳模型。

诊断标准与关键数值

  • 测试集中逻辑回归模型P(PHASES)、M(形态学)、R(Radscore)的AUC分别为0.859、0.755、0.803。
  • 测试集中多因素模型R+M(Radscore与形态学)、R+P(Radscore与PHASES)、R+M+P(Radscore、形态学与PHASES)的AUC分别为0.818、0.899、0.887。
  • 测试集中随机森林、极端梯度提升、梯度提升机、轻量梯度提升机的AUC分别为0.880、0.888、0.891、0.892。
  • 训练集中逻辑回归模型与四种机器学习模型的AUC差异有统计学意义(均p < 0.05),测试集中无统计学显著差异(均p > 0.05)。

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

RATIONALE AND OBJECTIVES: We aimed at developing and validating a nomogram and machine learning (ML) models based on radiomics score (Radscore), morphology, and PHASES to predict intracranial aneurysm (IA) rupture.

MATERIALS AND METHODS: We collected 440 patients with IAs in our hospital from 2015 to 2023, totaling 475 IAs (214 ruptured and 261 unruptured). A 7:3 random split was utilized to allocate participants into training and testing sets. To optimize the selection of radiomics features extracted from digital subtraction angiography, we employed t-tests and LASSO regression. Subsequently, we built single-factor and multifactor logistic regression (LR) models, alongside a nomogram. Furthermore, we employed four ML algorithms. After a comprehensive evaluation, including area under the curve (AUC), calibration curves, decision curve analysis (DCA), and other metrics, the best model was determined.

RESULTS: The AUCs for LR models P (PHASES), M (Morphology), and R (Radscore) in the testing set were 0.859, 0.755, and 0.803, respectively, while those for multifactor models R+M (Radscore and Morphology), R+P (Radscore and PHASES), and R+M+P (Radscore, Morphology, and PHASES) were 0.818, 0.899, and 0.887, respectively. The AUCs of random forest, extreme gradient boosting, gradient boosting machine, and light gradient boosting machine were 0.880, 0.888, 0.891, and 0.892 in testing set, respectively. In the training set, the LR model showed significant differences in AUCs compared with the four ML models (all p < 0.05). However, in the testing set, no statistically significant differences were found between them (all p > 0.05). Both ML models and the nomogram exhibit excellent performance in DCA and calibration curves.

CONCLUSION: Nomogram and ML models based on Radscore, morphology, and PHASES show high precision in predicting aneurysm rupture.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Zhang Z, Li H, Zhou X, et al. Predicting Intracranial Aneurysm Rupture: A Multifactor Analysis Combining Radscore, Morphology, and PHASES Parameters. Acad Radiol. 2024. PMID: 39127524. doi:10.1016/j.acra.2024.07.043

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。