Background Easy identification of immunocompromised hosts (ICHs) would allow for stratification of culture results based on host type.

Methods We utilized antimicrobial stewardship program (ASP) team notes written during handshake stewardship rounds in the pediatric intensive care unit (PICU) as the gold standard for host status; clinical notes from the primary team, medication orders during the encounter, problem list, and billing diagnoses documented prior to the ASP documentation were extracted to develop models that predict host status. We calculated performance for three models based on diagnoses/medications, with and without natural language processing from clinical notes. The susceptibility of pathogens causing bacteremia to commonly used empiric antibiotic regimens was then stratified by host status.

Results We identified 844 antimicrobial episodes from 666 unique patients; 160 (18.9%) were identified as ICHs. We randomly selected 675 initiations (80%) for model training and 169 initiations (20%) for testing. A rule-based model using diagnoses and medications alone yielded a sensitivity of 0.87 (08.6–0.88), specificity of 0.93 (0.92–0.93), and positive predictive value (PPV) of 0.74 (0.73–0.75). Adding clinical notes into XGBoost model led to improved specificity of 0.98 (0.98–0.98) and PPV of 0.9 (0.88–0.91), but with decreased sensitivity 0.77 (0.76–0.79). There were 77 bacteremia episodes during the study period identified and a host-specific visualization was created.

Conclusions An electronic health record–based phenotype based on notes, diagnoses, and medications identifies ICH in the PICU with high specificity.

背景 易于识别免疫功能低下的宿主 (ICH) 将允许基于宿主类型对培养结果进行分层。

方法 我们利用儿科重症监护病房 (PICU) 握手管理轮次中编写的抗菌药物管理计划 (ASP) 团队笔记作为宿主状态的黄金标准；主要团队的临床记录、就诊期间的用药医嘱、问题清单和在 ASP 文档之前记录的计费诊断被提取出来，以开发预测宿主状态的模型。我们根据诊断/药物计算了三个模型的性能，有无来自临床记录的自然语言处理。然后根据宿主状态对导致菌血症的病原体对常用经验性抗生素方案的敏感性进行分层。

结果 我们从 666 名独特的患者中确定了 844 次抗菌药物发作；160 (18.9%) 人被确定为 ICH。我们随机选择了 675 个初始化（80%）用于模型训练和 169 个初始化（20%）用于测试。仅使用诊断和药物的基于规则的模型的敏感性为 0.87 (08.6-0.88)，特异性为 0.93 (0.92-0.93)，阳性预测值 (PPV) 为 0.74 (0.73-0.75)。在 XGBoost 模型中添加临床记录导致特异性提高 0.98 (0.98-0.98) 和 PPV 0.9 (0.88-0.91)，但敏感性降低 0.77 (0.76-0.79)。在研究期间确定了 77 次菌血症事件，并创建了特定于宿主的可视化。

结论 基于笔记、诊断和药物的基于电子健康记录的表型识别 PICU 中的 ICH 具有高特异性。