Graduate Institute of Clinical Medicine, College of Medicine, National Taiwan University, Taipei 10002, Taiwan.
Department of Critical Care Medicine, MacKay Memorial Hospital, Taipei 10449, Taiwan.
Medicina (Kaunas). 2022 Mar 1;58(3):360. doi: 10.3390/medicina58030360.
: Traditional assessment of the readiness for the weaning from the mechanical ventilator (MV) needs respiratory parameters in a spontaneous breath. Exempted from the MV disconnecting and manual measurements of weaning parameters, a prediction model based on parameters from MV and electronic medical records (EMRs) may help the assessment before spontaneous breath trials. The study aimed to develop prediction models using machine learning techniques with parameters from the ventilator and EMRs for predicting successful ventilator mode shifting in the medical intensive care unit. : A retrospective analysis of 1483 adult patients with mechanical ventilators for acute respiratory failure in three medical intensive care units between April 2015 and October 2017 was conducted by machine learning techniques to establish the predicting models. The input candidate parameters included ventilator setting and measurements, patients' demographics, arterial blood gas, laboratory results, and vital signs. Several classification algorithms were evaluated to fit the models, including Lasso Regression, Ridge Regression, Elastic Net, Random Forest, Extreme Gradient Boosting (XGBoost), Support Vector Machine, and Artificial Neural Network according to the area under the Receiver Operating Characteristic curves (AUROC). : Two models were built to predict the success shifting from full to partial support ventilation (WPMV model) or from partial support to the T-piece trial (sSBT model). In total, 3 MV and 13 nonpulmonary features were selected for the WPMV model with the XGBoost algorithm. The sSBT model was built with 8 MV and 4 nonpulmonary features with the Random Forest algorithm. The AUROC of the WPMV model and sSBT model were 0.76 and 0.79, respectively. : The weaning predictions using machine learning and parameters from MV and EMRs have acceptable performance. Without manual measurements, a decision-making system would be feasible for the continuous prediction of mode shifting when the novel models process real-time data from MV and EMRs.
: 传统的机械通气（MV）脱机评估需要在自主呼吸时使用呼吸参数。如果不进行 MV 脱机和脱机参数的手动测量，基于 MV 和电子病历（EMR）参数的预测模型可能有助于在自主呼吸试验前进行评估。本研究旨在使用机器学习技术，结合 MV 和 EMR 参数，开发预测模型，以预测重症监护病房中机械通气模式转换的成功。
: 通过机器学习技术对 2015 年 4 月至 2017 年 10 月期间三家重症监护病房 1483 例急性呼吸衰竭患者的机械通气进行回顾性分析，建立预测模型。输入候选参数包括通气机设置和测量、患者人口统计学、动脉血气、实验室结果和生命体征。根据接收者操作特征曲线（AUROC）下的面积，评估了几种分类算法来拟合模型，包括 Lasso 回归、岭回归、弹性网络、随机森林、极端梯度提升（XGBoost）、支持向量机和人工神经网络。
: 建立了两个模型来预测从完全支持通气到部分支持通气（WPMV 模型）或从部分支持到 T 型管试验（sSBT 模型）的成功转换。总共使用 XGBoost 算法选择了 3 个 MV 和 13 个非肺部特征用于 WPMV 模型。sSBT 模型使用 8 个 MV 和 4 个非肺部特征使用随机森林算法构建。WPMV 模型和 sSBT 模型的 AUROC 分别为 0.76 和 0.79。
: 使用机器学习和 MV 及 EMR 参数进行的脱机预测具有良好的性能。如果不进行手动测量，当新型模型处理来自 MV 和 EMR 的实时数据时，基于决策的系统对于连续预测模式转换是可行的。
