Department of Family Medicine and Community Health, University of Kansas Medical Center, Kansas City, Kansas.
Department of Family Medicine and Community Health, University of Kansas Medical Center, Kansas City, Kansas
Ann Fam Med. 2023 Jan-Feb;21(1):11-18. doi: 10.1370/afm.2902.
Urinary tract infection (UTI) symptoms are common in primary care, but antibiotics are appropriate only when an infection is present. Urine culture is the reference standard test for infection, but results take >1 day. A machine learning predictor of urine cultures showed high accuracy for an emergency department (ED) population but required urine microscopy features that are not routinely available in primary care (the NeedMicro classifier).
We redesigned a classifier (NoMicro) that does not depend on urine microscopy and retrospectively validated it internally (ED data set) and externally (on a newly curated primary care [PC] data set) using a multicenter approach including 80,387 (ED) and 472 (PC) adults. We constructed machine learning models using extreme gradient boosting (XGBoost), artificial neural networks, and random forests (RFs). The primary outcome was pathogenic urine culture growing ≥100,000 colony forming units. Predictor variables included age; gender; dipstick urinalysis nitrites, leukocytes, clarity, glucose, protein, and blood; dysuria; abdominal pain; and history of UTI.
Removal of microscopy features did not severely compromise performance under internal validation: NoMicro/XGBoost receiver operating characteristic area under the curve (ROC-AUC) 0.86 (95% CI, 0.86-0.87) vs NeedMicro 0.88 (95% CI, 0.87-0.88). Excellent performance in external (PC) validation was also observed: NoMicro/RF ROC-AUC 0.85 (95% CI, 0.81-0.89). Retrospective simulation suggested that NoMicro/RF can be used to safely withhold antibiotics for low-risk patients, thereby avoiding antibiotic overuse.
The NoMicro classifier appears appropriate for PC. Prospective trials to adjudicate the balance of benefits and harms of using the NoMicro classifier are appropriate.
尿路感染 (UTI) 症状在初级保健中很常见，但只有在存在感染时才应使用抗生素。尿液培养是感染的参考标准测试，但结果需要 >1 天。一种用于急诊部 (ED) 人群的尿液培养预测器显示出很高的准确性，但需要在初级保健中常规使用的尿液显微镜特征（NeedMicro 分类器）。
我们重新设计了一种不需要尿液显微镜的分类器（NoMicro），并使用多中心方法对其进行了内部（ED 数据集）和外部（新整理的初级保健 [PC] 数据集）验证，该方法包括 80,387 名 ED 和 472 名 PC 成年人。我们使用极端梯度增强 (XGBoost)、人工神经网络和随机森林 (RF) 构建机器学习模型。主要结果是致病性尿液培养物生长≥100,000 个菌落形成单位。预测变量包括年龄；性别；尿沉渣分析亚硝酸盐、白细胞、透明度、葡萄糖、蛋白质和血液；尿痛；腹痛；和 UTI 病史。
在内部验证中，去除显微镜特征并未严重影响性能：NoMicro/XGBoost 接收器操作特征曲线 (ROC-AUC) 0.86（95%CI，0.86-0.87）与 NeedMicro 0.88（95%CI，0.87-0.88）。在外部（PC）验证中也观察到了出色的性能：NoMicro/RF ROC-AUC 0.85（95%CI，0.81-0.89）。回顾性模拟表明，NoMicro/RF 可用于安全地为低风险患者停用抗生素，从而避免抗生素过度使用。
NoMicro 分类器似乎适用于 PC。进行前瞻性试验以裁决使用 NoMicro 分类器的益处和危害的平衡是合适的。
