机器学习预测COVID-19危重症患者死亡
该观察性研究纳入2020年3月4日至6月29日美国68个ICU的5075例COVID-19成人患者,主要终点为28天住院死亡率(1846例,36.4%)。利用入ICU前48小时变量构建机器学习模型和简易工具,并进行外部和时间验证。eXtreme Gradient Boosting外部验证AUC最高(0.81)且校准良好;简易工具外部验证AUC 0.78,显著高于改良SOFA(0.69)、NEWS(0.60)和CURB-65(0.65)(p<0.05)。年龄、ICU床位数、肌酐、乳酸、动脉pH和PaO2/FiO2比是最重要预测因子。
要点
- 简易工具外部验证AUC 0.78,显著高于改良SOFA(0.69)、NEWS(0.60)和CURB-65(0.65)(p<0.05)。
- eXtreme Gradient Boosting外部验证AUC 0.81且校准良好,为表现最佳的机器学习算法。
- 年龄、ICU床位数、肌酐、乳酸、动脉pH和PaO2/FiO2比是eXtreme Gradient Boosting模型中最重要的预测因子。
- k-nearest neighbors表现最差,外部验证AUC 0.69。
- 模型可用于改善分诊决策和临床试验富集。
适用人群与场景
- 美国68个ICU于2020年3月4日至6月29日收治的成人COVID-19患者,共5075例。
- 排除人群原文未提及。
诊断标准与关键阈值
- 原文未提及
处置流程与药物剂量
- 原文未提及
红旗征与不能漏的情况
- 原文未提及
研究设计与关键结果
- 研究类型为观察性研究,纳入68个美国ICU的5075例成人COVID-19患者,主要终点为28天住院死亡率,1846例(36.4%)死亡。
- eXtreme Gradient Boosting外部验证AUC 0.81且校准良好;k-nearest neighbors外部验证AUC 0.69,为表现最差的机器学习算法。
- 简易工具(基于eXtreme Gradient Boosting最重要特征构建)外部验证AUC 0.78,显著高于改良SOFA(0.69)、NEWS(0.60)和CURB-65(0.65)(p<0.05)。
- 时间验证结果与外部验证相似。
证据类型、等级与局限
- 证据类型为观察性研究;原文未提及证据等级或推荐强度。
- 局限:原文未明确列出,但设计为观察性研究,模型需外部验证。
对床旁实践的改变
- 原文指出这些模型可用于改善分诊决策和临床试验富集,但未提供具体操作建议。
指南或共识出处
- 原文未提及
以上提炼依据论文摘要(全文未开放获取,或许可不允许翻译转载);全文请点「阅读原文」。
英文原文(摘要)· 点击展开
OBJECTIVES: Critically ill patients with coronavirus disease 2019 have variable mortality. Risk scores could improve care and be used for prognostic enrichment in trials. We aimed to compare machine learning algorithms and develop a simple tool for predicting 28-day mortality in ICU patients with coronavirus disease 2019.
DESIGN: This was an observational study of adult patients with coronavirus disease 2019. The primary outcome was 28-day inhospital mortality. Machine learning models and a simple tool were derived using variables from the first 48 hours of ICU admission and validated externally in independent sites and temporally with more recent admissions. Models were compared with a modified Sequential Organ Failure Assessment score, National Early Warning Score, and CURB-65 using the area under the receiver operating characteristic curve and calibration.
SETTING: Sixty-eight U.S. ICUs.
PATIENTS: Adults with coronavirus disease 2019 admitted to 68 ICUs in the United States between March 4, 2020, and June 29, 2020.
INTERVENTIONS: None.
MEASUREMENTS AND MAIN RESULTS: The study included 5,075 patients, 1,846 (36.4%) of whom died by day 28. eXtreme Gradient Boosting had the highest area under the receiver operating characteristic curve in external validation (0.81) and was well-calibrated, while k-nearest neighbors were the lowest performing machine learning algorithm (area under the receiver operating characteristic curve 0.69). Findings were similar with temporal validation. The simple tool, which was created using the most important features from the eXtreme Gradient Boosting model, had a significantly higher area under the receiver operating characteristic curve in external validation (0.78) than the Sequential Organ Failure Assessment score (0.69), National Early Warning Score (0.60), and CURB-65 (0.65; p < 0.05 for all comparisons). Age, number of ICU beds, creatinine, lactate, arterial pH, and Pao2/Fio2 ratio were the most important predictors in the eXtreme Gradient Boosting model.
CONCLUSIONS: eXtreme Gradient Boosting had the highest discrimination overall, and our simple tool had higher discrimination than a modified Sequential Organ Failure Assessment score, National Early Warning Score, and CURB-65 on external validation. These models could be used to improve triage decisions and clinical trial enrichment.
参考来源
- Churpek MM, Gupta S, Spicer AB, et al. Machine Learning Prediction of Death in Critically Ill Patients With Coronavirus Disease 2019. Crit Care Explor. 2021. PMID: 34476402. doi:10.1097/CCE.0000000000000515
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。