文献速递儿科与产科急症消化、代谢与肾脏急症

机器学习预测学术型儿科急诊就诊者的尿培养阳性

Machine learning prediction of positive urine cultures in an academic pediatric emergency department (ED).
PubMed 文献 · Am J Emerg Med · 2026-03-18
一句话结论在儿科急诊中,基于电子健康记录数据的XGBoost模型预测尿培养阳性的AUC-ROC为78.1%,可能辅助临床决策。

该横断面研究纳入2020年1月至2023年12月在一所四级学术医疗中心儿科急诊就诊且留取尿培养的3月龄至18岁患者,共3788次就诊,其中47.5%尿培养阳性。利用人口学、来诊方式、主诉、实验室检查、生命体征和就诊特征训练逻辑回归、K近邻、神经网络和梯度提升树(XGBoost)模型,按80%训练、20%测试。XGBoost模型表现最佳,准确率72.0%、精确率71.3%、召回率69.3%、AUC-ROC 78.1%,Brier评分0.194。作者认为该模型可能支持临床决策、减少不必要的抗生素使用并减少尿路感染治疗延迟。

要点

  • 在3788次儿科急诊就诊中,47.5%的尿培养为阳性。
  • XGBoost模型预测尿培养阳性的AUC-ROC为78.1%,准确率72.0%,精确率71.3%,召回率69.3%。
  • 模型校准良好,Brier评分为0.194。
  • 关键预测特征包括急诊尿路感染诊断、尿液采集方法、性别、体温、尿常规发现以及部分实验室和生命体征指标。
  • 作者认为该模型可能支持临床决策、减少不必要的抗生素使用并减少尿路感染治疗延迟。

适用人群与场景

  • 2020年1月至2023年12月期间在一所四级学术医疗中心儿科急诊就诊且留取尿培养的3月龄至18岁患者。

研究设计与关键结果

  • 研究类型为横断面研究,共纳入3788次就诊,其中47.5%尿培养阳性。
  • 逻辑回归、K近邻、神经网络和梯度提升树(XGBoost)模型在80%的就诊中训练,在20%中测试。
  • XGBoost模型表现最佳:准确率72.0%,精确率71.3%,召回率69.3%,AUC-ROC 78.1%。
  • 模型概率校准良好,Brier评分为0.194。
  • 关键预测特征包括急诊尿路感染诊断、尿液采集方法、性别、体温、尿常规发现以及部分实验室和生命体征指标。

证据类型、等级与局限

  • 证据类型为横断面研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为该机器学习模型可能支持临床决策、减少不必要的抗生素使用并减少尿路感染治疗延迟。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开

BACKGROUND: Urinary tract infections (UTIs) are among the most common pediatric infections, but urine culture, the diagnostic gold standard, requires 1-3 days for results. This delay may lead to unnecessary antibiotic use or treatment delays.

OBJECTIVE: To develop and validate a machine learning (ML) model that predicts urine culture positivity in pediatric emergency department (ED) encounters using electronic health record (EHR) data.

METHODS: We conducted a cross-sectional study of patients aged 3 months-18 years who had urine cultures obtained during ED visits at a quaternary academic medical center between January 2020 and December 2023. Demographics, arrival mode, chief complaint, labs, vitals, and encounter characteristics were extracted from the EHR. Logistic regression, K-nearest neighbors, neural networks, and gradient-boosted trees (XGBoost) were trained on 80% of encounters and tested on 20%. Model performance was assessed using accuracy, precision, recall, F1-score, and AUC-ROC. Feature importance was evaluated with Shapley Additive Explanations (SHAP).

RESULTS: Among 3788 encounters with urine cultures, 47.5% were positive. The XGBoost model achieved the best performance (accuracy 72.0%, precision 71.3%, recall 69.3%, AUC-ROC 78.1%). The model demonstrated appropriate probability calibration with a Brier score of 0.194. Key predictive features included ED diagnosis of UTI, urine collection method, sex, temperature, urinalysis findings, and select laboratory and vital sign measures.

CONCLUSION: A machine learning model applied to routinely collected EHR data accurately predicted urine culture positivity in pediatric ED patients. Such models may support clinician decision-making, reduce unnecessary antibiotic use, and minimize delays in UTI treatment.

来源:Am J Emerg Med,查看原文。版权归原作者所有。

参考来源

  1. Shen T, Homme JJ, Sheele J, et al. Machine learning prediction of positive urine cultures in an academic pediatric emergency department (ED). Am J Emerg Med. 2026. PMID: 41903287. doi:10.1016/j.ajem.2026.02.036

供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。