文献速递心脑血管急症重症综合管理与镇静镇痛

院外心脏骤停后神经功能结局预测:一种可解释的机器学习方法

Prediction of neurologic outcome after out-of-hospital cardiac arrest: An interpretable approach with machine learning.
PubMed 文献 · Resuscitation · 2024-08-12
一句话结论基于入院时10个特征的XGBoost模型预测院外心脏骤停后神经功能结局,AUC 0.964,敏感度0.606、特异度0.975。

本研究基于瑞典心肺复苏登记库2010至2020年55 615例院外心脏骤停病例,采用XGBoost算法结合分层重复10折交叉验证与Optuna超参数调优,构建并验证仅使用入院时可用信息的可解释机器学习模型,以预测神经功能结局。最终模型在测试集上AUC 0.964(95%CI 0.960-0.968),敏感度0.606(95%CI 0.573-0.634),特异度0.975(95%CI 0.972-0.978),阳性预测值0.664(95%CI 0.625-0.696),阴性预测值0.969(95%CI 0.966-0.972),宏观F1 0.803(95%CI 0.788-0.816),校准良好,无过拟合迹象。SHAP分析显示对模型输出影响最大的特征为「到院时ROSC」「初始心律为无收缩」和「到院时意识清醒」。该模型为急诊/ICU早期神经功能预后判断提供了可解释的工具。

要点

  • 模型仅使用入院时10个特征预测院外心脏骤停后神经功能结局,测试集AUC 0.964(95%CI 0.960-0.968)。
  • 测试集敏感度0.606(95%CI 0.573-0.634),特异度0.975(95%CI 0.972-0.978),阳性预测值0.664(95%CI 0.625-0.696),阴性预测值0.969(95%CI 0.966-0.972)。
  • 模型校准良好,宏观F1 0.803(95%CI 0.788-0.816),无过拟合迹象。
  • SHAP显示对模型输出影响最大的特征为「到院时ROSC」「初始心律为无收缩」和「到院时意识清醒」。

适用人群与场景

  • 瑞典心肺复苏登记库中2010至2020年登记的55 615例院外心脏骤停病例,使用入院时可用信息进行预测。

研究设计与关键结果

  • 研究类型为基于登记库的机器学习模型开发与验证研究,数据来自瑞典心肺复苏登记库2010至2020年55 615例院外心脏骤停病例。
  • 数据集分为训练集与验证集(用于模型开发)和测试集(用于最终模型评估);采用XGBoost算法,分层重复10折交叉验证,Optuna框架进行超参数调优。
  • 最终模型基于重要性评分选出的10个特征进行训练,在测试集上评估区分度、校准和偏差-方差权衡。
  • 最终模型测试集AUC 0.964(95%CI 0.960-0.968),敏感度0.606(95%CI 0.573-0.634),特异度0.975(95%CI 0.972-0.978),阳性预测值0.664(95%CI 0.625-0.696),阴性预测值0.969(95%CI 0.966-0.972),宏观F1 0.803(95%CI 0.788-0.816),校准良好。
  • SHAP分析显示对模型输出影响最大的特征为「到院时ROSC」「初始心律为无收缩」和「到院时意识清醒」。

证据类型、等级与局限

  • 证据类型:基于登记库的机器学习模型开发与验证研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,基于入院时10个特征的XGBoost机器学习模型在预测院外心脏骤停后神经功能结局方面表现良好,且无过拟合迹象。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开

UNLABELLED: Out-of-hospital cardiac arrest (OHCA) is a critical condition with low survival rates. In patients with a return of spontaneous circulation, brain injury is a leading cause of death. In this study, we propose an interpretable machine learning approach for predicting neurologic outcome after OHCA, using information available at the time of hospital admission.

METHODS: The study population were 55 615 OHCA cases registered in the Swedish Cardiopulmonary Resuscitation Registry between 2010 and 2020. The dataset was split to training and validation sets (for model development) and test set (for evaluation of the final model). We used an XGBoost algorithm with stratified, repeated 10-fold cross-validation along with Optuna framework for hyperparameters tuning. The final model was trained on 10 features selected based on the importance scores and evaluated on the test set in terms of discrimination, calibration and bias-variance tradeoff. We used SHapley Additive exPlanations to address the 'black-box' model and align with eXplainable artificial intelligence.

RESULTS: The final model achieved: area under the receiver operating characteristic value 0.964 (95% confidence interval (CI) [0.960-0.968]), sensitivity 0.606 (95% CI [0.573-0.634]), specificity 0.975 (95% CI [0.972-0.978]), positive predictive value (PPV) 0.664 (95% CI [0.625-0.696]), negative predictive value (NPV) 0.969 (95% CI [0.966-0.972]), macro F1 0.803 (95% CI [0.788-0.816]), and showed a very good calibration. SHAP features with the highest impact on the model's output were:'ROSC on arrival to hospital', 'Initial rhythm asystole' and 'Conscious on arrival to hospital'.

CONCLUSIONS: The XGBoost machine learning model with 10 features available at the time of hospital admission showed good performance for predicting neurologic outcome after OHCA, with no apparent signs of overfitting.

来源:Resuscitation,查看原文。版权归原作者所有。

参考来源

  1. Rawshani A, Hessulf F, Deminger J, et al. Prediction of neurologic outcome after out-of-hospital cardiac arrest: An interpretable approach with machine learning. Resuscitation. 2024. PMID: 39142467. doi:10.1016/j.resuscitation.2024.110359

供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。