文献速递泌尿系感染

尿液培养抗生素敏感性预测模型的外部验证

External validation of predictive models for antibiotic susceptibility of urine culture.
PubMed 文献 · BJU Int · 2024-12-22

该研究开发并外部验证了机器学习算法,可在标准尿培养药敏结果可用前最多3天预测抗生素敏感性。算法在11种测试抗生素中表现准确(AUC 0.71-0.94),在远距离医院队列外部验证中仍保持准确(AUC 0.69-0.87),且算法推荐的药物较临床医生经验性处方更常实现充分覆盖。

要点

  • 机器学习算法可基于大数据在尿培养药敏结果前最多3天预测敏感性。
  • 外部验证中算法对11种抗生素保持准确(AUC 0.69-0.87)。
  • 算法推荐的口服抗生素较临床医生经验性处方更常实现充分覆盖。

核心结论

  • 基于大型数据集训练的机器学习算法可在尿培养药敏结果可用前最多3天准确预测尿液培养的敏感与耐药。
  • 此类算法的临床实施可能改善临床诊疗与抗菌药物管理。

研究设计与样本

  • 算法在距训练队列设施约1931公里(约1200英里)的同一时期地理远距离医院系统队列中进行外部验证。
  • 算法在当代队列中进行临床验证,并与临床医生开具的经验性治疗进行比较。

主要发现

  • 临床验证中算法对所有11种测试抗生素均准确(AUC 0.71-0.94)。
  • 随着病原体被识别,算法准确性提高(AUC 0.79-0.97)。
  • 在地理远距离队列的外部验证中,即使未对该组额外训练,算法仍保持准确(AUC 0.69-0.87)。
  • 当算法在地理远距离医院的抗菌谱上训练时,准确性提高(AUC 0.70-0.93)。
  • 在当代队列中针对口服抗生素经验性处方与临床医生比较时,算法建议的药物更常实现充分的经验性覆盖。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVE: To develop, externally validate, and test a series of computer algorithms to accurately predict antibiotic susceptibility test (AST) results at the time of clinical diagnosis, up to 3 days before standard urine culture results become available, with the goal of improving antibiotic stewardship and patient outcomes. PATIENTS AND METHODS: Machine learning algorithms were developed and trained to predict susceptibility or resistance using over 4.7 million discrete AST classifications from urine cultures in a cohort of adult patients from outpatient and inpatient settings from 2012 to 2022. The algorithms were validated on a cohort from a geographically-distant hospital system, ~1931 km (~1200 miles) from the training cohort facilities, from the same time period. Finally, algorithms were clinically validated in a contemporary cohort and compared to the empiric therapy prescribed by clinicians. Appropriateness of the antibiotics selected by clinicians and the algorithm during the clinical validation was compared. RESULTS: Algorithms were accurate during clinical validation (area under the receiver operating characteristic curve [AUC] 0.71-0.94) for all 11 tested antibiotics. The algorithms' accuracy improved as the organism was identified (AUC 0.79-0.97). In external validation in a geographically-distant cohort, the algorithms remained accurate even without additional training on this group (AUC 0.69-0.87). When the algorithms were trained on the antibiogram from the geographically-distant hospital, the accuracy improved (AUC 0.70-0.93). When algorithms' performances were tested against clinicians in a contemporary cohort for the empiric prescription of oral antibiotics, the drug agent suggested by the algorithms more frequently resulted in adequate empiric coverage. CONCLUSIONS: Machine learning algorithms trained on a large dataset are accurate in prediction of urine culture susceptibility vs resistance up to 3 days prior to urine AST availability. Clinical implementation of such an algorithm could improve both clinical care and antimicrobial stewardship.

来源:BJU Int,查看原文。版权归原作者所有。

引用

  1. Werneburg GT, Rhoads DD, Milinovich A, et al. External validation of predictive models for antibiotic susceptibility of urine culture. BJU Int. 2024. PMID: 39710428. doi:10.1111/bju.16626

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。