家庭医学中尿液培养分类算法的验证
Validation of an Algorithm to Classify Urine Cultures in Family Medicine.
作者信息
Zhang Jack, Morkem Rachael, Rajaram Akshay
机构信息
Section of Anesthesia, Northern Ontario School of Medicine University, Sudbury, Canada.
Department of Family Medicine, Queen's University, Kingston, Canada.
出版信息
Appl Clin Inform. 2025 Mar;16(2):357-361. doi: 10.1055/a-2499-4207. Epub 2025 Apr 23.
OBJECTIVES
Automation of test follow-up offers potential reductions in workload for clinicians. The primary objective of the study was to evaluate the performance of , a regular expression-based algorithm in classifying urine culture reports in primary care.
METHODS
A retrospective validation of was performed using urine culture reports abstracted from a single academic family health team. classifications were compared with labels assigned manually by a human reviewer. Measures of diagnostic performance were calculated.
RESULTS
achieved 95.3% accuracy, 88.6% sensitivity, and 100% specificity in classifying 1,999 urine culture reports.
CONCLUSION
The accuracy of was comparable to its performance in the original development and validation study by Eickelberg. Additional work is required to explore and improve the accuracy of and assess its performance across primary care settings and with more complex urine culture reports.
目的
检测随访自动化有望减轻临床医生的工作量。本研究的主要目的是评估一种基于正则表达式的算法在基层医疗中对尿培养报告进行分类的性能。
方法
使用从一个学术性家庭健康团队提取的尿培养报告对该算法进行回顾性验证。将该算法的分类结果与人工审核员手动分配的标签进行比较。计算诊断性能指标。
结果
在对1999份尿培养报告进行分类时，该算法的准确率达到95.3%，灵敏度达到88.6%，特异性达到100%。
结论
该算法的准确性与其在艾克尔贝格最初的开发和验证研究中的性能相当。需要开展更多工作来探索和提高该算法的准确性，并评估其在不同基层医疗环境以及面对更复杂尿培养报告时的性能。
Zotero 插件