使用机器学习模型预测院内心脏骤停幸存者一年内复发性心脏骤停
本研究基于瑞典心肺复苏注册库(SRCR)2010至2021年数据,纳入7302例>18岁院内心脏骤停(IHCA)后存活出院的患者,使用极端梯度提升(XGBoost)模型预测一年内复发性心脏骤停或死亡。模型纳入与指数IHCA、合并症、社会经济数据和处方药物相关的1241个变量。结果显示22%的患者发生结局,最佳模型ROC-AUC为0.72(95%CI 0.70-0.75)。重要性最高的特征为IHCA前最高血清肌酐、年龄和未知婚姻状况;合并症和心脏骤停情况是重要特征类别。作者认为,若结果可验证,该模型可能用于临床评估IHCA幸存者再次心脏骤停的风险。
要点
- 在7302例IHCA存活出院患者中,22%在一年内发生复发性心脏骤停或死亡。
- XGBoost模型使用1241个变量预测一年内复发性心脏骤停或死亡,最佳ROC-AUC为0.72(95%CI 0.70-0.75),性能中等。
- 模型重要性最高的特征为IHCA前最高血清肌酐、年龄和未知婚姻状况。
- 合并症和心脏骤停情况是模型的重要特征类别。
- 作者认为若结果可验证,该模型可能用于临床评估IHCA幸存者再次心脏骤停的风险。
适用人群与场景
- 纳入2010至2021年瑞典心肺复苏注册库(SRCR)中所有>18岁、IHCA后存活出院的患者。
研究设计与关键结果
- 研究类型为基于瑞典注册库的机器学习模型开发研究,纳入7302例IHCA存活出院患者,22%发生一年内复发性心脏骤停或死亡。
- 使用极端梯度提升(XGBoost)模型,纳入1241个变量,最佳模型ROC-AUC为0.72(95%CI 0.70-0.75)。
- 模型重要性最高的特征为IHCA前最高血清肌酐、年龄和未知婚姻状况;合并症和心脏骤停情况是重要特征类别。
证据类型、等级与局限
- 证据类型为基于注册库的机器学习模型开发研究。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,若这些结果可验证,该模型可能用于临床评估IHCA幸存者再次心脏骤停的风险。
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
BACKGROUND: Patients discharged alive after in-hospital cardiac arrest (IHCA) have an increased mortality up to a year after hospital discharge. Improving our ability to identify patients at high risk of death one year after IHCA may improve survival through secondary prevention. We aimed to evaluate the possibility to predict recurrent cardiac arrest or death among in-hospital cardiac arrest survivors with support from a machine learning model.
METHOD: All patients (>18 year) discharged alive after IHCA in the Swedish registry for cardiopulmonary resuscitation (SRCR) from 2010 to 2021 were included. Potential predictors included in the model were data related to the index IHCA, comorbidities, socioeconomic data and prescription medication obtained from national Swedish registries. Extreme gradient boosting (XGBoost) model was trained to predict the outcome. Receiver operating characteristics and area under the curve (ROC-AUC) was used to evaluate model performance.
RESULTS: Of the 7302 included patients, 22% had developed the outcome. The best performing model with 1241 variables had ROC-AUC 0.72 (95% CI 0.70-0.75). Features of greatest importance were highest serum creatinine measured before IHCA, age and unknown civil status. Comorbidity and cardiac arrest circumstances were important classes of features for this model.
CONCLUSION: In this dataset, an XGBoost model could predict recurrent cardiac arrest or death within one year after IHCA with a modest performance and good accuracy. If these results can be validated, this model could potentially be used clinically to assess the risk of another cardiac arrest in survivors of IHCA.
参考来源
- Thuccani M, Hellsén G, Herlitz J, et al. Predicting recurrent cardiac arrest within one year after surviving in-hospital cardiac arrest using a machine learning model. Resuscitation. 2026. PMID: 41655735. doi:10.1016/j.resuscitation.2026.111006
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。