Royal Melbourne Hospital, Melbourne, Victoria, Australia.
Faculty of Science, Technology and Engineering, La Trobe University, Melbourne, Victoria, Australia.
PLoS One. 2022 Oct 26;17(10):e0276509. doi: 10.1371/journal.pone.0276509. eCollection 2022.
OBJECTIVE(S): To use machine learning (ML) to predict short-term requirements for invasive ventilation in patients with COVID-19 admitted to Australian intensive care units (ICUs).
A machine learning study within a national ICU COVID-19 registry in Australia.
Adult patients who were spontaneously breathing and admitted to participating ICUs with laboratory-confirmed COVID-19 from 20 February 2020 to 7 March 2021. Patients intubated on day one of their ICU admission were excluded.
Six machine learning models predicted the requirement for invasive ventilation by day three of ICU admission from variables recorded on the first calendar day of ICU admission; (1) random forest classifier (RF), (2) decision tree classifier (DT), (3) logistic regression (LR), (4) K neighbours classifier (KNN), (5) support vector machine (SVM), and (6) gradient boosted machine (GBM). Cross-validation was used to assess the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity of machine learning models.
300 ICU admissions collected from 53 ICUs across Australia were included. The median [IQR] age of patients was 59 [50-69] years, 109 (36%) were female and 60 (20%) required invasive ventilation on day two or three. Random forest and Gradient boosted machine were the best performing algorithms, achieving mean (SD) AUCs of 0.69 (0.06) and 0.68 (0.07), and mean sensitivities of 77 (19%) and 81 (17%), respectively.
Machine learning can be used to predict subsequent ventilation in patients with COVID-19 who were spontaneously breathing and admitted to Australian ICUs.
利用机器学习（ML）预测 2020 年 2 月 20 日至 2021 年 3 月 7 日期间在澳大利亚重症监护病房（ICU）接受治疗的 COVID-19 成年患者短期需要进行有创通气的情况。
在澳大利亚全国性的 ICU COVID-19 注册中心进行的一项机器学习研究。
患有实验室确诊 COVID-19 的、自主呼吸的成年患者，在 2020 年 2 月 20 日至 2021 年 3 月 7 日期间入住参与 ICU，且排除了在 ICU 入院第一天插管的患者。
6 种机器学习模型通过 ICU 入院第一天记录的变量，预测 ICU 入院后第三天需要有创通气的情况；（1）随机森林分类器（RF），（2）决策树分类器（DT），（3）逻辑回归（LR），（4）K 近邻分类器（KNN），（5）支持向量机（SVM）和（6）梯度提升机（GBM）。使用交叉验证评估了机器学习模型的接受者操作特征曲线（ROC）下面积（AUC）、敏感性和特异性。
从澳大利亚的 53 个 ICU 共收集了 300 例 ICU 入院患者，患者的中位[IQR]年龄为 59[50-69]岁，109 例（36%）为女性，60 例（20%）在第二天或第三天需要有创通气。随机森林和梯度提升机是表现最好的算法，其平均（SD）AUC 分别为 0.69（0.06）和 0.68（0.07），平均敏感度分别为 77（19%）和 81（17%）。
机器学习可用于预测自主呼吸并入住澳大利亚 ICU 的 COVID-19 患者随后的通气情况。
