Department of Electrical Engineering and Computer Science, University of California, Berkeley, Berkeley, California, USA.
Department of Medicine, Poznan University of Medical Science, Poznan, Poland.
Sci Rep. 2018 Nov 20;8(1):17116. doi: 10.1038/s41598-018-35582-2.
Unplanned extubation (UE) can be associated with fatal outcome; however, an accurate model for predicting the mortality of UE patients in intensive care units (ICU) is lacking. Therefore, we aim to compare the performances of various machine learning models and conventional parameters to predict the mortality of UE patients in the ICU. A total of 341 patients with UE in ICUs of Chi-Mei Medical Center between December 2008 and July 2017 were enrolled and their demographic features, clinical manifestations, and outcomes were collected for analysis. Four machine learning models including artificial neural networks, logistic regression models, random forest models, and support vector machines were constructed and their predictive performances were compared with each other and conventional parameters. Of the 341 UE patients included in the study, the ICU mortality rate is 17.6%. The random forest model is determined to be the most suitable model for this dataset with F 0.860, precision 0.882, and recall 0.850 in the test set, and an area under receiver operating characteristic (ROC) curve of 0.910 (SE: 0.022, 95% CI: 0.867-0.954). The area under ROC curves of the random forest model was significantly greater than that of Acute Physiology and Chronic Health Evaluation (APACHE) II (0.779, 95% CI: 0.716-0.841), Therapeutic Intervention Scoring System (TISS) (0.645, 95% CI: 0.564-0.726), and Glasgow Coma scales (0.577, 95%: CI 0.497-0.657). The results revealed that the random forest model was the best model to predict the mortality of UE patients in ICUs.
非计划性拔管（UE）可导致致命后果；然而，目前缺乏预测 ICU 中 UE 患者死亡率的准确模型。因此，我们旨在比较各种机器学习模型和常规参数在预测 ICU 中 UE 患者死亡率方面的性能。
共纳入 2008 年 12 月至 2017 年 7 月在奇美医疗中心 ICU 中发生 UE 的 341 例患者，收集其人口统计学特征、临床表现和结局进行分析。
构建了包括人工神经网络、逻辑回归模型、随机森林模型和支持向量机在内的 4 种机器学习模型，并比较了它们的预测性能。
在研究的 341 例 UE 患者中，ICU 死亡率为 17.6%。随机森林模型被确定为最适合该数据集的模型，在测试集中 F 值为 0.860、精度为 0.882、召回率为 0.850，接受者操作特征（ROC）曲线下面积为 0.910（SE：0.022，95%CI：0.867-0.954）。随机森林模型的 ROC 曲线下面积显著大于急性生理学和慢性健康评估（APACHE）II 评分（0.779，95%CI：0.716-0.841）、治疗干预评分系统（TISS）评分（0.645，95%CI：0.564-0.726）和格拉斯哥昏迷量表（0.577，95%CI：0.497-0.657）。
结果表明，随机森林模型是预测 ICU 中 UE 患者死亡率的最佳模型。
