Artificial intelligence automation of urine culture reading with BD Kiestra Urine Culture Application: measurement of performance and potential efficiency gains.

IF 3.6 3区医学 Q1 PATHOLOGY

Pathology Pub Date : 2025-04-19 DOI:10.1016/j.pathol.2025.02.011

Maryza Graham, Leanne Tilson, Tony M Korman, Denise Liow, Harshini Wickremasinghe, Richard Streitberg, John Hamblin

{"title":"Artificial intelligence automation of urine culture reading with BD Kiestra Urine Culture Application: measurement of performance and potential efficiency gains.","authors":"Maryza Graham, Leanne Tilson, Tony M Korman, Denise Liow, Harshini Wickremasinghe, Richard Streitberg, John Hamblin","doi":"10.1016/j.pathol.2025.02.011","DOIUrl":null,"url":null,"abstract":"Automation of microbiology sample inoculation and incubation has recently been shown to improve microbiological and clinical endpoints (such as turnaround time) as well as improve efficiency. However, instruments for automation of microbiology sample culture reading and interpretation have only recently become available for clinical evaluation. We evaluated the BD Kiestra Urine Culture Application (UCA) for culture interpretation of clinical urine samples and compared the results to the reading of Kiestra image by scientific staff. Of the 1021 urine samples processed by both UCA and scientist culture reading, 1003 (98%) yielded concordant results at 18-h incubation. The number of samples with ≥104 colony-forming units (CFU)/mL (≥107 CFU/L) which were correctly recognised by the UCA using the early growth detection algorithm was 424/424 (100%). We found the UCA to be an accurate artificial intelligence solution, and we describe the potential for large workload efficiency gains in addition to more rapid report turnaround times.","PeriodicalId":19915,"journal":{"name":"Pathology","volume":" ","pages":""},"PeriodicalIF":3.6000,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Pathology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.pathol.2025.02.011","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PATHOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Automation of microbiology sample inoculation and incubation has recently been shown to improve microbiological and clinical endpoints (such as turnaround time) as well as improve efficiency. However, instruments for automation of microbiology sample culture reading and interpretation have only recently become available for clinical evaluation. We evaluated the BD Kiestra Urine Culture Application (UCA) for culture interpretation of clinical urine samples and compared the results to the reading of Kiestra image by scientific staff. Of the 1021 urine samples processed by both UCA and scientist culture reading, 1003 (98%) yielded concordant results at 18-h incubation. The number of samples with ≥10⁴ colony-forming units (CFU)/mL (≥10⁷ CFU/L) which were correctly recognised by the UCA using the early growth detection algorithm was 424/424 (100%). We found the UCA to be an accurate artificial intelligence solution, and we describe the potential for large workload efficiency gains in addition to more rapid report turnaround times.

查看原文本刊更多论文

人工智能自动化尿液培养阅读与BD Kiestra尿液培养应用：测量性能和潜在的效率收益。

微生物样品接种和孵育自动化最近已被证明可以改善微生物学和临床终点（如周转时间）以及提高效率。然而，用于微生物样品培养阅读和解释的自动化仪器直到最近才可用于临床评估。我们评估了BD Kiestra尿液培养应用程序（UCA）对临床尿液样本的培养解释，并将结果与科学人员对Kiestra图像的读取进行了比较。在UCA和科学家培养读数处理的1021份尿液样本中，1003份（98%）在18小时的孵育中获得了一致的结果。使用早期生长检测算法，UCA正确识别≥104个菌落形成单位(CFU)/mL（≥107个CFU/L）的样本数为424/424（100%）。我们发现UCA是一种精确的人工智能解决方案，并且我们描述了除了更快的报告周转时间之外，还可以获得大量工作负载效率的潜力。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Pathology 医学-病理学

CiteScore

6.50

自引率

2.20%

发文量

459

审稿时长

54 days

期刊介绍： Published by Elsevier from 2016 Pathology is the official journal of the Royal College of Pathologists of Australasia (RCPA). It is committed to publishing peer-reviewed, original articles related to the science of pathology in its broadest sense, including anatomical pathology, chemical pathology and biochemistry, cytopathology, experimental pathology, forensic pathology and morbid anatomy, genetics, haematology, immunology and immunopathology, microbiology and molecular pathology.