文献速递脑血管病

急性缺血性卒中患者无效再通治疗的多变量预测模型

Multivariable Prediction Model for Futile Recanalization Therapies in Patients With Acute Ischemic Stroke.
PubMed 文献 · Neurology · 2022-09-05

本研究基于单中心前瞻性观察登记数据,纳入接受机械取栓和/或静脉溶栓的急性缺血性卒中患者,开发并内部验证梯度提升决策树机器学习模型,以预测3个月改良Rankin量表5-6分的无效再通治疗。模型区分度良好(AUC 0.87,95%CI 0.87-0.88),校准良好(Brier 0.12,95%CI 0.11-0.12),但总体性能中等(F1-score 0.63±0.004)。

要点

  • 无效再通治疗总体发生率为24%,单纯机械取栓组34%高于单纯静脉溶栓组11%。
  • 预测因子包括卒中严重程度、年龄、活动性癌症、卒中前残疾、血糖、C反应蛋白、肌酐、白质高信号及发病至入院时间。
  • 模型区分度AUC 0.87(95%CI 0.87-0.88),校准Brier 0.12(95%CI 0.11-0.12),总体性能中等(F1-score 0.63±0.004)。

核心结论

  • 该无效再通治疗预测模型有助于共同决策并识别急诊场景中最相关的特征。
  • 模型可能对低资源医疗环境特别有用,但需纳入更多多维度变量以进一步提高预测性能。

研究设计与样本

  • 单中心前瞻性观察登记研究,纳入接受机械取栓和/或静脉溶栓的急性缺血性卒中患者。
  • 数据集按80%训练(N=1,808)和20%内部验证(N=453)拆分,共纳入2,261例患者。
  • 采用k近邻插补后对入院时32个变量使用梯度提升决策树机器学习模型,预测3个月改良Rankin量表5-6分的无效再通治疗。

主要发现

  • 中位年龄75岁(四分位距64-83岁),女性46%,中位NIH卒中量表评分9分(四分位距4-17分)。
  • 34%接受单纯静脉溶栓,41%接受单纯机械取栓,25%接受桥接治疗。
  • 总体无效再通治疗539例(24%),单纯机械取栓组34%高于单纯静脉溶栓组11%。
  • 最重要的预测因子包括卒中严重程度、年龄、活动性癌症、卒中前残疾、血糖、C反应蛋白、肌酐、白质高信号及发病至入院时间。
  • 模型预测3个月无效再通治疗的AUC为0.87(95%CI 0.87-0.88),Brier为0.12(95%CI 0.11-0.12),F1-score为0.63±0.004;决策曲线分析提示在较低治疗阈值(最高至0.8)下平均净获益更高。

临床怎么用

  • 该模型可帮助共同决策并识别急诊场景中最相关的特征。
  • 模型可能对低资源医疗环境特别有用。
  • 作者认为需纳入更多多维度变量以进一步提高预测性能。

局限性

  • 作者指出需纳入更多多维度变量以进一步提高预测性能。

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 AND OBJECTIVES: Very poor outcome despite IV thrombolysis (IVT) and mechanical thrombectomy (MT) occurs in approximately 1 of 4 patients with ischemic stroke and is associated with a high logistic and economic burden. We aimed to develop and validate a multivariable prognostic model to identify futile recanalization therapies (FRTs) in patients undergoing those therapies. METHODS: Patients from a prospectively collected observational registry of a single academic stroke center treated with MT and/or IVT were included. The data set was split into a training (N = 1,808, 80%) and internal validation (N = 453, 20%) cohort. We used gradient boosted decision tree machine learning models after k-nearest neighbor imputation of 32 variables available at admission to predict FRT defined as modified Rankin scale 5-6 at 3 months. We report feature importance, ability for discrimination, calibration, and decision curve analysis. RESULTS: A total of 2,261 patients with a median (interquartile range) age of 75 years (64-83 years), 46% female, median NIH Stroke Scale 9 (4-17), 34% IVT alone, 41% MT alone, and 25% bridging were included. Overall, 539 (24%) had FRT, more often in MT alone (34%) as compared with IVT alone (11%). Feature importance identified clinical variables (stroke severity, age, active cancer, prestroke disability), laboratory values (glucose, C-reactive protein, creatinine), imaging biomarkers (white matter hyperintensities), and onset-to-admission time as the most important predictors. The final model was discriminatory for predicting 3-month FRT (area under the curve 0.87, 95% CI 0.87-0.88) and had good calibration (Brier 0.12, 0.11-0.12). Overall performance was moderate (F1-score 0.63 ± 0.004), and decision curve analyses suggested higher mean net benefit at lower thresholds of treatment (up to 0.8). CONCLUSIONS: This FRT prediction model can help inform shared decision making and identify the most relevant features in the emergency setting. Although it might be particularly useful in low resource healthcare settings, incorporation of further multifaceted variables is necessary to further increase the predictive performance.

来源:Neurology,查看原文。版权归原作者所有。

引用

  1. Meinel TR, Lerch C, Fischer U, et al. Multivariable Prediction Model for Futile Recanalization Therapies in Patients With Acute Ischemic Stroke. Neurology. 2022. PMID: 35803722. doi:10.1212/WNL.0000000000200815

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。