机器学习预测急诊室的细菌性尿
Johnathan M Sheele1,2, Ronna L Campbell3,4, Derick D Jones3,4
1Department of Emergency Medicine (Sheele), Mayo Clinic, 4500 San Pablo Rd, Jacksonville, FL, 32224, USA. sheele.johnathan@mayo.edu.
Scientific reports
|August 24, 2025
概括
机器学习使用急诊室数据准确预测尿路感染. 在等待培养结果时,这可以帮助指导抗生素治疗决策.
科学领域:
- 医疗信息学
- 计算生物学
- 传染性疾病
背景情况:
- 尿路感染很常见,但往往被错误诊断和治疗.
- 准确及时诊断尿路感染对于有效治疗患者至关重要.
研究的目的:
- 评估机器学习模型,使用现有的急诊室 (ED) 数据来预测细菌性尿.
- 评估各种机器学习算法在尿液培养中的不同细菌生长值的预测性能.
主要方法:
- 对62,963例ED接触的回顾分析与尿液分析和尿液培养数据 (2017-2021年).
- 逻辑回归,k-最近邻居,随机森林,极端梯度增强 (XGBoost) 和深度神经网络的比较.
- 三种尿液培养结果的预测:任何微生物生长,≥10,000 CFU/mL和≥100,000 CFU/mL.
主要成果:
- XGBoost 的预测准确度最高,分别为 86. 1%, 89. 1% 和 93. 1%.
- 在被诊断为尿路感染前培养的病例中,XGBoost在预测没有生长或≥100,000 CFU/ ml时获得了91%的AUROC.
- 该模型仅使用ED遭遇期间可用的数据准确预测细菌性尿.
结论:
- 机器学习,特别是XGBoost,可以使用例行收集的ED数据准确预测细菌性尿.
- 这些算法为临床医生提供了有价值的工具来预测培养结果,并告知实证抗生素治疗决策.
- 将机器学习纳入临床工作流程可以改善疑似尿道感染的管理.
相关概念视频
Urinary Tract Infection III: Diagnostic Studies and Interprofessional Care
35
A healthcare provider can diagnose a urinary tract infection (UTI) through several methods:Medical History and Symptoms: The provider will take a detailed medical history and ask about symptoms such as frequent urination, burning sensation during urination, and lower abdominal pain.Urinalysis: A clean-catch urine sample is collected in a sterile container and tested for the presence of bacteria, white blood cells (leukocytes), nitrites, blood, and protein. The presence of leukocytes and...
35
Steps in Outbreak Investigation
199
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
199
Acute Pyelonephritis II: Diagnostic Studies and Management
40
Introduction:For diagnosing acute pyelonephritis, a comprehensive patient history is collected to identify symptoms such as dysuria, frequent or urgent urination, flank pain, or costovertebral angle (CVA) tenderness that may suggest a kidney infection.Physical ExaminationDuring the physical examination, CVA tenderness is assessed. This involves gentle percussion over the costovertebral angle, where tenderness often indicates a kidney infection.Diagnostic TestsUrinalysis: Used to identify white...
40
Urine Studies II: Urine Culture and Sensitivity Test
114
A urine culture and sensitivity test is a diagnostic procedure used to identify urinary tract bacterial infections and determine the most effective antibiotics for treatment. This test is generally preferred when a patient shows manifestations of a urinary tract infection, such as frequent or painful urination, cloudy or foul-smelling urine, or lower abdominal pain.Purpose of the TestThe primary goals of a urine culture and sensitivity test are to:Determine the specific bacteria causing the...
114
Urinary Tract Infection IV: Nursing Management
87
In managing urinary tract infections (UTIs) in nursing, a comprehensive assessment is essential. Begin by gathering subjective data, such as the patient’s complaints of dysuria (painful urination), urinary frequency, urgency, suprapubic pain, and any lower abdominal discomfort. This information can be complemented by questions regarding previous UTIs, sexual activity, and personal hygiene practices, which can provide insight into risk factors. Objective assessment should focus on signs...
87
Urinary Tract Infection II: Pathophysiology
43
The pathophysiology of urinary tract infections (UTIs) encompasses several progressive stages, beginning with bacterial colonization and culminating in potential systemic complications if untreated. UTIs are primarily initiated by bacteria, such as Escherichia coli, which often originate from the gastrointestinal tract and migrate to the urinary system through the periurethral area. This migration can occur via several routes, including improper hygiene practices, sexual activity, or...
43


