Section General and Acute Internal Medicine, Department of Internal Medicine, Amsterdam Public Health Research Institute, Amsterdam UMC Location VUmc, Amsterdam, The Netherlands.
Department of Clinical Chemistry, Amsterdam UMC Location VUmc, Amsterdam, The Netherlands.
BMJ Open. 2022 Jan 4;12(1):e053332. doi: 10.1136/bmjopen-2021-053332.
To develop predictive models for blood culture (BC) outcomes in an emergency department (ED) setting.
Retrospective observational study.
ED of a large teaching hospital in the Netherlands between 1 September 2018 and 24 June 2020.
Adult patients from whom BCs were collected in the ED. Data of demographic information, vital signs, administered medications in the ED and laboratory and radiology results were extracted from the electronic health record, if available at the end of the ED visits.
The primary outcome was the performance of two models (logistic regression and gradient boosted trees) to predict bacteraemia in ED patients, defined as at least one true positive BC collected at the ED.
In 4885 out of 51 399 ED visits (9.5%), BCs were collected. In 598/4885 (12.2%) visits, at least one of the BCs was true positive. Both a gradient boosted tree model and a logistic regression model showed good performance in predicting BC results with area under curve of the receiver operating characteristics of 0.77 (95% CI 0.73 to 0.82) and 0.78 (95% CI 0.73 to 0.82) in the test sets, respectively. In the gradient boosted tree model, the optimal threshold would predict 69% of BCs in the test set to be negative, with a negative predictive value of over 94%.
Both models can accurately identify patients with low risk of bacteraemia at the ED in this single-centre setting and may be useful to reduce unnecessary BCs and associated healthcare costs. Further studies are necessary for validation and to investigate the potential clinical benefits and possible risks after implementation.
在急诊科（ED）环境中建立预测血培养（BC）结果的模型。
回顾性观察性研究。
荷兰一家大型教学医院的 ED，时间为 2018 年 9 月 1 日至 2020 年 6 月 24 日。
从 ED 采集 BC 的成年患者。如果在 ED 就诊结束时可从电子健康记录中提取人口统计学信息、生命体征、ED 中给予的药物以及实验室和放射学结果等数据。
主要结局是评估两种模型（逻辑回归和梯度提升树）预测 ED 患者菌血症的表现，菌血症定义为至少在 ED 采集到一份真阳性 BC。
在 51399 次 ED 就诊中，有 4885 次（9.5%）采集了 BC。在 4885 次就诊中，有 598 次（12.2%）至少有一份 BC 为真阳性。梯度提升树模型和逻辑回归模型在预测 BC 结果方面均表现出良好的性能，测试集的受试者工作特征曲线下面积分别为 0.77（95%CI 0.73 至 0.82）和 0.78（95%CI 0.73 至 0.82）。在梯度提升树模型中，最佳阈值预测将有 69%的测试集 BC 为阴性，阴性预测值超过 94%。
在该单中心环境中，两种模型均能准确识别 ED 中低菌血症风险患者，可能有助于减少不必要的 BC 和相关医疗费用。需要进一步的研究来验证和探讨实施后的潜在临床获益和可能风险。
