Department of Anesthesiology, Michigan Medicine, Ann Arbor, MI, USA; Institute of Healthcare Policy & Innovation, University of Michigan, Ann Arbor, MI, USA.
Ludwig Center for Cancer Genetics and Therapeutics, Johns Hopkins University School of Medicine, Baltimore, MD, USA; Sidney Kimmel Cancer Center, Johns Hopkins University School of Medicine, Baltimore, MD, USA; Sol Goldman Pancreatic Cancer Research Center, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
Br J Anaesth. 2021 Mar;126(3):578-589. doi: 10.1016/j.bja.2020.11.034. Epub 2020 Dec 4.
Patients with coronavirus disease 2019 (COVID-19) requiring mechanical ventilation have high mortality and resource utilisation. The ability to predict which patients may require mechanical ventilation allows increased acuity of care and targeted interventions to potentially mitigate deterioration.
We included hospitalised patients with COVID-19 in this single-centre retrospective observational study. Our primary outcome was mechanical ventilation or death within 24 h. As clinical decompensation is more recognisable, but less modifiable, as the prediction window shrinks, we also assessed 4, 8, and 48 h prediction windows. Model features included demographic information, laboratory results, comorbidities, medication administration, and vital signs. We created a Random Forest model, and assessed performance using 10-fold cross-validation. The model was compared with models derived from generalised estimating equations using discrimination.
Ninety-three (23%) of 398 patients required mechanical ventilation or died within 14 days of admission. The Random Forest model predicted pending mechanical ventilation with good discrimination (C-statistic=0.858; 95% confidence interval, 0.841-0.874), which is comparable with the discrimination of the generalised estimating equation regression. Vitals sign data including SpO/FiO ratio (Random Forest Feature Importance Z-score=8.56), ventilatory frequency (5.97), and heart rate (5.87) had the highest predictive utility. In our highest-risk cohort, the number of patients needed to identify a single new case was 3.2, and for our second quintile it was 5.0.
Machine learning techniques can be leveraged to improve the ability to predict which patients with COVID-19 are likely to require mechanical ventilation, identifying unrecognised bellwethers and providing insight into the constellation of accompanying signs of respiratory failure in COVID-19.
患有 2019 年冠状病毒病（COVID-19）并需要机械通气的患者死亡率和资源利用率都很高。能够预测哪些患者可能需要机械通气，可以提高护理的敏锐度，并采取有针对性的干预措施，以减轻病情恶化的可能性。
我们纳入了这项单中心回顾性观察性研究中的住院 COVID-19 患者。我们的主要结局是在 24 小时内需要机械通气或死亡。由于随着预测窗口的缩小，临床失代偿变得更加明显，但更难改变，因此我们还评估了 4、8 和 48 小时的预测窗口。模型特征包括人口统计学信息、实验室结果、合并症、药物管理和生命体征。我们创建了一个随机森林模型，并通过 10 折交叉验证来评估性能。该模型与使用判别分析得出的广义估计方程模型进行了比较。
398 例患者中有 93 例（23%）在入院后 14 天内需要机械通气或死亡。随机森林模型预测即将发生的机械通气具有良好的判别能力（C 统计量=0.858；95%置信区间，0.841-0.874），与广义估计方程回归的判别能力相当。生命体征数据，包括 SpO/FiO 比值（随机森林特征重要性 Z 分数=8.56）、通气频率（5.97）和心率（5.87），具有最高的预测效用。在我们风险最高的队列中，需要识别一个新病例的患者人数为 3.2，而在我们的第二五分位数队列中，需要识别一个新病例的患者人数为 5.0。
机器学习技术可以被利用来提高预测 COVID-19 患者哪些患者可能需要机械通气的能力，识别未被识别的预警信号，并深入了解 COVID-19 中呼吸衰竭的伴随征象。
Zotero 插件