文献速递重症综合管理与镇静镇痛儿科与产科急症

预测儿科重症监护病房心脏骤停的初步研究

A pilot study to predict cardiac arrest in the pediatric intensive care unit.
PubMed 文献 · Resuscitation · 2023-02-16
一句话结论机器学习模型可提前3小时预测儿科ICU心脏骤停,独立测试集上XGBoost的auROC为0.971、灵敏度99.5%、特异度69.6%。

该研究纳入约翰斯·霍普金斯医院儿科ICU的1145例患者,其中15例发生心脏骤停,利用240 Hz心电波形、0.5 Hz生理时间序列、药物与人口学数据,每5分钟生成特征,评估6种机器学习模型。XGBoost表现最佳,在独立测试集上auROC为0.971、auPRC为0.797、灵敏度99.5%、特异度69.6%。作者认为这些模型可识别临床医生可能不易察觉的院内心脏骤停特征,提前最多3小时预测,从而允许更早干预。

要点

  • XGBoost在独立测试集上预测儿科ICU心脏骤停:auROC 0.971、auPRC 0.797、灵敏度99.5%、特异度69.6%。
  • 模型可提前最多3小时预测院内心脏骤停,特征每5分钟生成一次。
  • 预测特征包括23项心率变异性指标、12项生命体征的96项汇总统计量及42类治疗药物的二分类特征。
  • 共评估6种模型:逻辑回归、支持向量机、随机森林、XGBoost、LightGBM和软投票集成,XGBoost最优。
  • 研究人群为儿科ICU 1145例患者,其中15例发生心脏骤停。

适用人群与场景

  • 约翰斯·霍普金斯医院儿科重症监护病房的1145例患者,其中15例发生心脏骤停。

研究设计与关键结果

  • 研究类型为利用机器学习预测儿科ICU心脏骤停的初步研究,数据来自约翰斯·霍普金斯医院儿科ICU的1145例患者,其中15例发生心脏骤停。
  • 数据包括240 Hz心电波形、0.5 Hz生理时间序列、药物和人口学信息,数据分为训练集、验证集和测试集,特征每5分钟生成一次。
  • 从心电波形确定23项心率变异性指标,为12项生命体征(如呼吸频率和血压)计算96项汇总统计量,药物分为42个治疗药物类别并生成二分类特征。
  • 评估6种机器学习模型:逻辑回归、支持向量机、随机森林、XGBoost、LightGBM和软投票集成。
  • XGBoost表现最佳,在独立测试集上auROC为0.971、auPRC为0.797、灵敏度99.5%、特异度69.6%。

证据类型、等级与局限

  • 证据类型:初步研究(机器学习模型开发与验证)。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为这些高性能模型可识别临床医生可能不易察觉的院内心脏骤停特征,这些特征包括心率变异性指标、生命体征数据和治疗药物类别的组合。
  • 作者认为这些机器学习模型可提前最多3小时预测院内心脏骤停且性能高,使临床医生能够更早干预,改善患者结局。

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: Cardiac arrest is a leading cause of mortality prior to discharge for children admitted to the pediatric intensive care unit. To address this problem, we used machine learning to predict cardiac arrest up to three hours in advance.

METHODS: Our data consists of 240 Hz ECG waveform data, 0.5 Hz physiological time series data, medications, and demographics from 1,145 patients in the pediatric intensive care unit at the Johns Hopkins Hospital, 15 of whom experienced a cardiac arrest. The data were divided into training, validating, and testing sets, and features were generated every five minutes. 23 heart rate variability (HRV) metrics were determined from ECG waveforms. 96 summary statistics were calculated for 12 vital signs, such as respiratory rate and blood pressure. Medications were classified into 42 therapeutic drug classes. Binary features were generated to indicate the administration of these different drugs. Next, six machine learning models were evaluated: logistic regression, support vector machine, random forest, XGBoost, LightGBM, and a soft voting ensemble.

RESULTS: XGBoost performed the best, with 0.971 auROC, 0.797 auPRC, 99.5% sensitivity, and 69.6% specificity on an independent test set.

CONCLUSION: We have created high-performing models that identify signatures of in-hospital cardiac arrest (IHCA) that may not be evident to clinicians. These signatures include a combination of heart rate variability metrics, vital signs data, and therapeutic drug classes. These machine learning models can predict IHCA up to three hours prior to onset with high performance, allowing clinicians to intervene earlier, improving patient outcomes.

来源:Resuscitation,查看原文。版权归原作者所有。

参考来源

  1. Kenet AL, Pemmaraju R, Ghate S, et al. A pilot study to predict cardiac arrest in the pediatric intensive care unit. Resuscitation. 2023. PMID: 36805101. doi:10.1016/j.resuscitation.2023.109740

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。