School of Physics, Mathematics and Computing, University of Western Australia, Perth, Australia.
Western Australian Country Health Service, Perth, Australia.
BMC Infect Dis. 2023 Aug 24;23(1):552. doi: 10.1186/s12879-023-08535-y.
Bloodstream infections (BSIs) are a significant burden on the global population and represent a key area of focus in the hospital environment. Blood culture (BC) testing is the standard diagnostic test utilised to confirm the presence of a BSI. However, current BC testing practices result in low positive yields and overuse of the diagnostic test. Diagnostic stewardship research regarding BC testing is increasing, and becoming more important to reduce unnecessary resource expenditure and antimicrobial use, especially as antimicrobial resistance continues to rise. This study aims to establish a machine learning (ML) pipeline for BC outcome prediction using data obtained from routinely analysed blood samples, including complete blood count (CBC), white blood cell differential (DIFF), and cell population data (CPD) produced by Sysmex XN-2000 analysers.
ML models were trained using retrospective data produced between 2018 and 2019, from patients at Sir Charles Gairdner hospital, Nedlands, Western Australia, and processed at Pathwest Laboratory Medicine, Nedlands. Trained ML models were evaluated using stratified 10-fold cross validation.
Two ML models, an XGBoost model using CBC/DIFF/CPD features with boruta feature selection (BFS) , and a random forest model trained using CBC/DIFF features with BFS were selected for further validation after obtaining AUC scores of [Formula: see text] and [Formula: see text] respectively using stratified 10-fold cross validation. The XGBoost model obtained an AUC score of 0.76 on a internal validation set. The random forest model obtained AUC scores of 0.82 and 0.76 on internal and external validation datasets respectively.
We have demonstrated the utility of using an ML pipeline combined with CBC/DIFF, and CBC/DIFF/CPD feature spaces for BC outcome prediction. This builds on the growing body of research in the area of BC outcome prediction, and provides opportunity for further research.
血流感染（BSI）给全球人口带来了沉重负担，是医院环境中重点关注的领域之一。血培养（BC）检测是用于确认 BSI 存在的标准诊断检测方法。然而，目前的 BC 检测实践导致阳性率低且诊断检测过度使用。关于 BC 检测的诊断管理研究正在增加，对于减少不必要的资源支出和抗菌药物的使用变得越来越重要，尤其是随着抗菌药物耐药性的不断上升。本研究旨在使用从常规分析的血液样本中获得的数据（包括 Sysmex XN-2000 分析仪生成的全血细胞计数（CBC）、白细胞分类（DIFF）和细胞群体数据（CPD））建立用于 BC 结果预测的机器学习（ML）管道。
使用 2018 年至 2019 年期间在西澳大利亚州尼德兰兹的查尔斯·盖尔德纳爵士医院就诊的患者产生的回顾性数据以及尼德兰兹的 Pathwest 实验室医学公司处理的数据来训练 ML 模型。使用分层 10 折交叉验证评估训练的 ML 模型。
在使用 CBC/DIFF/CPD 特征和 Boruta 特征选择（BFS）的 XGBoost 模型以及使用 CBC/DIFF 特征和 BFS 训练的随机森林模型分别获得 AUC 分数[Formula: see text]和[Formula: see text]后，选择这两个 ML 模型进行进一步验证。XGBoost 模型在内部验证集中获得 0.76 的 AUC 评分。随机森林模型在内部和外部验证数据集上分别获得 0.82 和 0.76 的 AUC 评分。
我们已经证明了使用 ML 管道结合 CBC/DIFF 和 CBC/DIFF/CPD 特征空间进行 BC 结果预测的实用性。这是对 BC 结果预测领域不断增加的研究的补充，并为进一步的研究提供了机会。
