Department of Epidemiology,Johns Hopkins University Bloomberg School of Public Health,Baltimore, Maryland.
Division of Medical Microbiology, Department of Pathology,Johns Hopkins University School of Medicine,Baltimore, Maryland.
Infect Control Hosp Epidemiol. 2019 May;40(5):541-550. doi: 10.1017/ice.2019.42. Epub 2019 Mar 27.
Targeted screening for carbapenem-resistant organisms (CROs), including carbapenem-resistant Enterobacteriaceae (CRE) and carbapenemase-producing organisms (CPOs), remains limited; recent data suggest that existing policies miss many carriers.
Our objective was to measure the prevalence of CRO and CPO perirectal colonization at hospital unit admission and to use machine learning methods to predict probability of CRO and/or CPO carriage.
We performed an observational cohort study of all patients admitted to the medical intensive care unit (MICU) or solid organ transplant (SOT) unit at The Johns Hopkins Hospital between July 1, 2016 and July 1, 2017. Admission perirectal swabs were screened for CROs and CPOs. More than 125 variables capturing preadmission clinical and demographic characteristics were collected from the electronic medical record (EMR) system. We developed models to predict colonization probabilities using decision tree learning.
Evaluating 2,878 admission swabs from 2,165 patients, we found that 7.5% and 1.3% of swabs were CRO and CPO positive, respectively. Organism and carbapenemase diversity among CPO isolates was high. Despite including many characteristics commonly associated with CRO/CPO carriage or infection, overall, decision tree models poorly predicted CRO and CPO colonization (C statistics, 0.57 and 0.58, respectively). In subgroup analyses, however, models did accurately identify patients with recent CRO-positive cultures who use proton-pump inhibitors as having a high likelihood of CRO colonization.
In this inpatient population, CRO carriage was infrequent but was higher than previously published estimates. Despite including many variables associated with CRO/CPO carriage, models poorly predicted colonization status, likely due to significant host and organism heterogeneity.
针对包括耐碳青霉烯肠杆菌科（CRE）和产碳青霉烯酶菌（CPO）在内的碳青霉烯类耐药菌（CRO）的靶向筛查仍然有限；最近的数据表明，现有的政策会遗漏许多携带者。
我们的目的是测量入院时患者直肠周围定植的 CRO 和 CPO 的流行率，并使用机器学习方法预测 CRO 和/或 CPO 定植的概率。
我们对 2016 年 7 月 1 日至 2017 年 7 月 1 日期间在约翰霍普金斯医院内科重症监护病房（MICU）或实体器官移植（SOT）病房住院的所有患者进行了一项观察性队列研究。入院时直肠拭子筛查 CRO 和 CPO。从电子病历（EMR）系统中收集了 125 多个以上的变量，这些变量捕获了入院前的临床和人口统计学特征。我们使用决策树学习来开发预测定植概率的模型。
在评估了来自 2165 名患者的 2878 份入院拭子后，我们发现 7.5%和 1.3%的拭子分别为 CRO 和 CPO 阳性。CPO 分离株的病原体和碳青霉烯酶多样性很高。尽管包括了许多与 CRO/CPO 定植或感染相关的特征，但总体而言，决策树模型对 CRO 和 CPO 定植的预测能力较差（C 统计量分别为 0.57 和 0.58）。然而，在亚组分析中，模型确实准确地识别了最近有 CRO 阳性培养史且使用质子泵抑制剂的患者，这些患者有很高的 CRO 定植可能性。
在该住院患者人群中，CRO 定植的发生率较低，但高于之前发表的估计值。尽管包括了许多与 CRO/CPO 定植相关的变量，但模型对定植状态的预测能力较差，这可能是由于宿主和病原体的异质性很大。
