Department of Surgery, University of Miami Miller School of Medicine, USA.
Division of Trauma Surgery and Surgical Critical Care, Department of Surgery, University of Miami Miller School of Medicine, USA.
J Crit Care. 2018 Jun;45:156-162. doi: 10.1016/j.jcrc.2018.02.010. Epub 2018 Feb 21.
The purpose of this study was to compare machine learning techniques for predicting central line-associated bloodstream infection (CLABSI).
The Multiparameter Intelligent Monitoring in Intensive Care III database was queried for all ICU admissions. The variables included six different severities of illness scores calculated on the first day of ICU admission with their components and comorbidities. The outcomes of interest were in-hospital mortality, central line placement, and CLABSI. Predictive models were created for these outcomes using classifiers with different algorithms: logistic regression, gradient boosted trees, and deep learning.
There were 57,786 total hospital admissions and the mortality rate was 10.1%. There were 38.4% patients with a central line and the rate of CLABSI was 1.5%. The classifiers using deep learning performed with the highest AUC for mortality, 0.885±0.010 (p<0.01) and central line placement, 0.816±0.006 (p<0.01). The classifier using logistic regression for predicting CLABSI performed with an AUC of 0.722±0.048 (p<0.01).
This study demonstrates models for identifying patients who will develop CLABSI. Early identification of these patients has implications for quality, cost, and outcome improvements.
本研究旨在比较用于预测中心静脉导管相关性血流感染（CLABSI）的机器学习技术。
从重症监护多参数智能监测 III 数据库中查询所有 ICU 入院患者的信息。纳入的变量包括 ICU 入院第一天计算的六种不同严重程度的疾病评分及其组成部分和合并症。感兴趣的结局包括院内死亡率、中心静脉导管置管和 CLABSI。使用具有不同算法的分类器（逻辑回归、梯度提升树和深度学习）为这些结局创建预测模型。
共有 57786 例住院患者，死亡率为 10.1%。有 38.4%的患者有中心静脉导管，CLABSI 的发生率为 1.5%。使用深度学习的分类器在死亡率（AUC=0.885±0.010，p<0.01）和中心静脉导管置管（AUC=0.816±0.006，p<0.01）方面的表现最佳。使用逻辑回归预测 CLABSI 的分类器的 AUC 为 0.722±0.048（p<0.01）。
本研究展示了用于识别可能发生 CLABSI 的患者的模型。早期识别这些患者对改善质量、降低成本和改善结局具有重要意义。
