Department of Emergency Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea; Department of Emergency Medicine, Seoul National University Hospital, Seoul, Republic of Korea; Laboratory of Emergency Medical Services, Seoul National University Hospital Biomedical Research Institute, Seoul, Republic of Korea; Department of Biomedical Engineering, Seoul National University College of Medicine, Seoul, Republic of Korea.
Department of Emergency Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea; Department of Emergency Medicine, Seoul National University Hospital, Seoul, Republic of Korea; Laboratory of Emergency Medical Services, Seoul National University Hospital Biomedical Research Institute, Seoul, Republic of Korea.
Am J Emerg Med. 2022 Mar;53:86-93. doi: 10.1016/j.ajem.2021.12.065. Epub 2022 Jan 1.
Bacteremia is a common but critical condition with high mortality that requires timely and optimal treatment in the emergency department (ED). The prediction of bacteremia at the ED during triage and disposition stages could support the clinical decisions of ED physicians regarding the appropriate treatment course and safe ED disposition. This study developed and validated machine learning models to predict bacteremia in the emergency department during triage and disposition stages.
This study enrolled adult patients who visited a single tertiary hospital from 2016 to 2018 and had at least two sets of blood cultures during their ED stay. Demographic information, chief complaint, triage level, vital signs, and laboratory data were used as model predictors. We developed and validated prediction models using 10 variables at the time of ED triage and 42 variables at the time of disposition. The extreme gradient boosting (XGB) model was compared with the random forest and multivariable logistic regression models. We compared model performance by assessing the area under the receiver operating characteristic curve (AUC), test characteristics, and decision curve analysis.
A total of 24,768 patients were included: 16,197 cases were assigned to development, and 8571 cases were assigned to validation. The proportion of bacteremia was 10.9% and 10.4% in the development and validation datasets, respectively. The Triage XGB model (AUC, 0.718; 95% confidence interval (CI), 0.701-0.735) showed acceptable discrimination performance with a sensitivity over 97%. The Disposition XGB model (AUC, 0.853; 95% CI, 0.840-0.866) showed excellent performance and provided the greatest net benefit throughout the range of thresholds probabilities.
The Triage XGB model could be used to identify patients with a low risk of bacteremia immediately after initial ED triage. The Disposition XGB model showed excellent discriminative performance.
菌血症是一种常见但严重的疾病，死亡率高，需要在急诊科（ED）及时进行最佳治疗。在分诊和处置阶段预测 ED 中的菌血症可以支持 ED 医生对适当治疗过程和安全 ED 处置的临床决策。本研究开发和验证了机器学习模型，以预测分诊和处置阶段 ED 中的菌血症。
本研究纳入了 2016 年至 2018 年期间访问单一三级医院的成年患者，并且在 ED 住院期间至少有两套血培养。使用人口统计学信息、主要投诉、分诊级别、生命体征和实验室数据作为模型预测因子。我们使用 ED 分诊时的 10 个变量和处置时的 42 个变量开发和验证预测模型。比较极端梯度提升（XGB）模型与随机森林和多变量逻辑回归模型。通过评估接收者操作特征曲线下面积（AUC）、测试特征和决策曲线分析来比较模型性能。
共纳入 24768 例患者：16197 例分配至开发组，8571 例分配至验证组。开发组和验证组的菌血症比例分别为 10.9%和 10.4%。分诊 XGB 模型（AUC，0.718；95%置信区间[CI]，0.701-0.735）具有可接受的判别性能，敏感性超过 97%。处置 XGB 模型（AUC，0.853；95%CI，0.840-0.866）表现出色，在整个阈值概率范围内提供了最大的净收益。
分诊 XGB 模型可用于在初始 ED 分诊后立即识别出菌血症风险低的患者。处置 XGB 模型表现出出色的判别性能。
