文献速递心脑血管急症重症综合管理与镇静镇痛

使用机器学习为急诊科急性心力衰竭患者开发风险分层工具

Use of Machine Learning to Develop a Risk-Stratification Tool for Emergency Department Patients With Acute Heart Failure.
PubMed 文献 · Ann Emerg Med · 2020-12-24
一句话结论在大型多中心急诊队列中,基于电子健康记录附加变量的机器学习模型较传统logistic回归提高了急性心衰30天严重不良事件的预测准确性(AUC 0.85 vs 0.80)。

本研究为回顾性队列设计,纳入2017年1月1日至2018年12月31日期间在21个急诊科就诊的成年急性心衰患者共26,189例次,主要结局为30天严重不良事件(死亡、心肺复苏、球囊泵置入、插管、新透析、心肌梗死或冠脉血运重建)。以STRATIFY规则的13个变量为基础模型,其AUC为0.76(95%CI 0.74–0.77);加入额外电子健康记录变量后,logistic回归AUC提高至0.80(95%CI 0.79–0.82),机器学习模型AUC达0.85(95%CI 0.83–0.86)。预测风险≤3%、≤5%、≤10%的人群分别占11.1%、25.7%、48.9%,其中预测风险≤3%者仍有28%被收住院。结论认为机器学习模型可改善30天风险预测。

要点

  • 在26,189例次急诊急性心衰就诊中,30天严重不良事件总发生率为18.8%。
  • 基础模型(STRATIFY 13变量)AUC 0.76(95%CI 0.74–0.77),加入电子健康记录附加变量后logistic回归AUC 0.80(95%CI 0.79–0.82),机器学习模型AUC 0.85(95%CI 0.83–0.86)。
  • 预测30天严重不良事件风险≤3%、≤5%、≤10%的患者分别占11.1%、25.7%、48.9%,但预测风险≤3%者中仍有28%被收住院。
  • 该机器学习风险分层工具基于21个急诊科就诊人群开发,其床旁应用价值需进一步验证。

适用人群与场景

  • 2017年1月1日至2018年12月31日期间,在拥有21个急诊科的大型系统内就诊的成年健康计划成员中,所有因急性心力衰竭就诊的急诊患者。

研究设计与关键结果

  • 研究类型为回顾性队列设计,共纳入26,189例次急诊就诊,平均年龄74岁,女性占51.7%,白人占60.7%。
  • 主要结局为30天严重不良事件(包括死亡、心肺复苏、球囊泵置入、插管、新透析、心肌梗死或冠脉血运重建),总发生率为18.8%。
  • 基础模型(STRATIFY规则的13个变量)AUC为0.76(95%CI 0.74–0.77)。
  • 加入额外电子健康记录变量后,logistic回归模型AUC为0.80(95%CI 0.79–0.82),机器学习模型AUC为0.85(95%CI 0.83–0.86)。
  • 预测30天严重不良事件风险≤3%、≤5%、≤10%的患者分别占11.1%、25.7%、48.9%;在预测风险≤3%的患者中,28%被收住院。

证据类型、等级与局限

  • 证据类型:回顾性队列研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,使用包含额外变量的机器学习模型较传统方法改善了30天风险预测。
  • 预测风险≤3%的患者中仍有28%被收住院,提示该风险分层工具在临床决策中的适用性需进一步研究。

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

STUDY OBJECTIVE: We use variables from a recently derived acute heart failure risk-stratification rule (STRATIFY) as a basis to develop and optimize risk prediction using additional patient clinical data from electronic health records and machine-learning models.

METHODS: Using a retrospective cohort design, we identified all emergency department (ED) visits for acute heart failure between January 1, 2017, and December 31, 2018, among adult health plan members of a large system with 21 EDs. The primary outcome was any 30-day serious adverse event, including death, cardiopulmonary resuscitation, balloon-pump insertion, intubation, new dialysis, myocardial infarction, or coronary revascularization. Starting with the 13 variables from the STRATIFY rule (base model), we tested whether predictive accuracy in a different population could be enhanced with additional electronic health record-based variables or machine-learning approaches (compared with logistic regression). We calculated our derived model area under the curve (AUC), calculated test characteristics, and assessed admission rates across risk categories.

RESULTS: Among 26,189 total ED encounters, mean patient age was 74 years, 51.7% were women, and 60.7% were white. The overall 30-day serious adverse event rate was 18.8%. The base model had an AUC of 0.76 (95% confidence interval 0.74 to 0.77). Incorporating additional variables led to improved accuracy with logistic regression (AUC 0.80; 95% confidence interval 0.79 to 0.82) and machine learning (AUC 0.85; 95% confidence interval 0.83 to 0.86). We found that 11.1%, 25.7%, and 48.9% of the study population had predicted serious adverse event risk of less than or equal to 3%, less than or equal to 5%, and less than or equal to 10%, respectively, and 28% of those with less than or equal to 3% risk were admitted.

CONCLUSION: Use of a machine-learning model with additional variables improved 30-day risk prediction compared with conventional approaches.

来源:Ann Emerg Med,查看原文。版权归原作者所有。

参考来源

  1. Sax DR, Mark DG, Huang J, et al. Use of Machine Learning to Develop a Risk-Stratification Tool for Emergency Department Patients With Acute Heart Failure. Ann Emerg Med. 2020. PMID: 33349492. doi:10.1016/j.annemergmed.2020.09.436

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。