Han Hye-Ji, Kim Kyunghoon, Park June Dong
Department of Pediatrics, Seoul National University Bundang Hospital, Seongnam, Korea.
Departments of Pediatrics, Seoul National University College of Medicine, Seoul, Korea.
Acute Crit Care. 2024 Nov;39(4):611-620. doi: 10.4266/acc.2024.00752. Epub 2024 Nov 22.
Despite the high mortality associated with bloodstream infection (BSI), early detection of this condition is challenging in critical settings. The objective of this study was to create a machine learning tool for rapid recognition of BSI in critically ill children.
Data were extracted from a derivative cohort comprising patients who underwent at least one blood culture during hospitalization in the pediatric intensive care unit (PICU) of a tertiary hospital from January 2020 to June 2023 for model development. Data from another tertiary hospital were utilized for external validation. Variables selected for model development were age, white blood cell count with segmented neutrophil count, C-reactive protein, bilirubin, liver enzymes, glucose, body temperature, heart rate, and respiratory rate. Algorithms compared were extra trees, random forest, light gradient boosting, extreme gradient boosting, and CatBoost.
We gathered 1,806 measurements and recorded 290 hospitalizations from 263 patients in the derivative cohort. Median age on admission was 43 months, with an interquartile range of 10-118.75 months, and a male predominance was observed (n=160, 55.2%). Candida albicans was the most prevalent pathogen, and median duration to confirm BSI was 3 days (range, 3-4). Patients with BSI experienced significantly higher in-hospital mortality and prolonged stays in the PICU than patients without BSI. Random forest classifier achieved the highest area under the receiver operating characteristic curve of 0.874 (0.762 for the validation set).
We developed a machine learning model that predicts BSI with acceptable performance. Further research is necessary to validate its effectiveness.
尽管血流感染（BSI）相关死亡率很高，但在重症监护环境中早期发现这种情况具有挑战性。本研究的目的是创建一种机器学习工具，用于快速识别危重症儿童的BSI。
数据从一个衍生队列中提取，该队列包括2020年1月至2023年6月在一家三级医院的儿科重症监护病房（PICU）住院期间至少进行过一次血培养的患者，用于模型开发。另一家三级医院的数据用于外部验证。为模型开发选择的变量包括年龄、白细胞计数及分叶中性粒细胞计数、C反应蛋白、胆红素、肝酶、葡萄糖、体温、心率和呼吸频率。比较的算法有极端随机树、随机森林、轻梯度提升、极端梯度提升和CatBoost。
我们在衍生队列中收集了1806次测量数据，并记录了263例患者的290次住院情况。入院时的中位年龄为43个月，四分位间距为10 - 118.75个月，观察到男性占优势（n = 160，55.2%）。白色念珠菌是最常见的病原体，确诊BSI的中位时间为3天（范围为3 - 4天）。与无BSI的患者相比，BSI患者的院内死亡率显著更高，在PICU的住院时间更长。随机森林分类器在接收者操作特征曲线下的面积最高，为0.874（验证集为0.762）。
我们开发了一种性能可接受的预测BSI的机器学习模型。有必要进行进一步研究以验证其有效性。
