Machine Learning for Prediction of Successful Extubation of Mechanical Ventilated Patients in an Intensive Care Unit: A Retrospective Observational Study
Machine Learning for Prediction of Successful Extubation of Mechanical Ventilated Patients in an Intensive Care Unit: A Retrospective Observational Study
复制标题
DOI：
10.1272/jnms.jnms.2021_88-508
复制
发表时间：
2021-10-01
影响因子：
1
通讯作者：
Yokota, Hiroyuki
中科院分区：
文献类型：
--
作者：
Otaguro, Takanobu;Tanaka, Hidenori;Yokota, Hiroyuki
背景：接受机械通气的患者通常会实施呼吸机脱机方案。然而，尽管有这样的方案，拔管失败率仍然很高。本研究分析了机器学习在预测拔管成功方面的有用性和准确性。方法：我们回顾性评估了因呼吸衰竭而接受插管并在重症监护室 (ICU) 接受机械通气的患者的数据。提取了 57 个特征的信息，包括患者人口统计、生命体征、实验室数据和呼吸机数据。拔管失败定义为拔管后 72 小时内重新插管。对于监督学习，数据被标记为是否需要插管。我们使用三种学习算法（随机森林、XGBoost 和 LightGBM）来预测成功拔管。我们还分析了重要特征并评估了曲线下面积 (AUC) 和预测指标。结果：总体而言，117 名患者中有 13 名需要重新插管。 LightGBM 的 AUC 最高（0.950），其次是 XGBoost（0.946）和随机森林（0.930）。随机森林的准确度、精确度和召回率分别为 0.897、0.910 和 0.909； XGBoost 为 0.910、0.912 和 0.931； LightGBM 分别为 0.927、0.915 和 0.960。最重要的特征是机械通气持续时间，其次是吸入氧分数、呼气末正压、最大和平均气道压力以及格拉斯哥昏迷量表。结论：机器学习预测 ICU 患者机械通气成功拔管。 LightGBM 的整体性能最好。机械通气的持续时间是所有模型中最重要的特征。
Background: Ventilator weaning protocols are commonly implemented for patients receiving mechanical ventilation. However, despite such protocols, the rate of extubation failure remains high. This study analyzed the usefulness and accuracy of machine learning in predicting extubation success.Methods: We retrospectively evaluated data from patients who underwent intubation for respiratory failure and received mechanical ventilation in an intensive care unit (ICU). Information on 57 features, including patient demographics, vital signs, laboratory data, and ventilator data, were extracted. Extubation failure was defined as re-intubation within 72 hours of extubation. For supervised learning, data were labeled as intubation-required or not. We used three learning algorithms (Random Forest, XGBoost, and LightGBM) to predict successful extubation. We also analyzed important features and evaluated the area under curve (AUC) and prediction metrics.Results: Overall, 13 of the 117 included patients required re-intubation. LightGBM had the highest AUC (0.950), followed by XGBoost (0.946) and Random Forest (0.930). The accuracy, precision, and recall performance were 0.897, 0.910, and 0.909 for Random Forest; 0.910, 0.912, and 0.931 for XGBoost; and 0.927, 0.915, and 0.960 for LightGBM, respectively. The most important feature was duration of mechanical ventilation, followed by fraction of inspired oxygen, positive end-expiratory pressure, maximum and mean airway pressures, and Glasgow Coma Scale.Conclusions: Machine learning predicted successful extubation of ICU patients on mechanical ventilation. LightGBM had the best overall performance. Duration of mechanical ventilation was the most important feature in all models.