Bonazzetti Cecilia, Rocchi Ettore, Toschi Alice, Derus Nicolas Riccardo, Sala Claudia, Pascale Renato, Rinaldi Matteo, Campoli Caterina, Pasquini Zeno Adrien Igor, Tazza Beatrice, Amicucci Armando, Gatti Milo, Ambretti Simone, Viale Pierluigi, Castellani Gastone, Giannella Maddalena
Department of Medical and Surgical Sciences, Alma Mater Studiorum, University of Bologna, Bologna, Italy.
Infectious Diseases Unit, Department of Integrated Infectious Risk Management, IRCCS Azienda Ospedaliero-Universitaria di Bologna, Bologna, Italy.
NPJ Digit Med. 2025 May 29;8(1):319. doi: 10.1038/s41746-025-01696-x.
Artificial intelligence (AI) models are promising tools for predicting antimicrobial susceptibility in gram-negative bloodstream infections (GN-BSI). Single-center study on hospitalized patients with GN-BSI, over 7-year period, aimed to predict resistance to fluoroquinolones (FQ-R), third generation cephalosporins (3GC-R), beta-lactam/beta-lactamase inhibitors (BL/BLI-R) and carbapenems (C-R) was performed. Analyses were carried out within a machine learning framework, developed using the scikit-learn Python package. Overall, 2552 patients were included. Enterobacterales accounted for 85.5% of isolates, with E. coli, Klebsiella spp, and Proteus spp being most common. Distribution of resistance was FQ-R 48.6%, 3GC-R 40.1%, BL/BLI-R 29.9%, and C-R 16.9%. Models' validation showed good performance predicting antibiotic resistance for all four resistance classes, with the best performance for C-R (AUC-ROC 0.921 ± 0.013). The developed pipeline has been made available ( https://github.com/EttoreRocchi/ResPredAI ), along with documentation for running the same workflow on a different dataset, to account for local epidemiology and clinical features.
人工智能(AI)模型是预测革兰氏阴性菌血流感染(GN-BSI)中抗菌药物敏感性的有前景的工具。对住院的GN-BSI患者进行了一项为期7年的单中心研究,旨在预测对氟喹诺酮类药物(FQ-R)、第三代头孢菌素(3GC-R)、β-内酰胺/β-内酰胺酶抑制剂(BL/BLI-R)和碳青霉烯类药物(C-R)的耐药性。分析是在一个使用scikit-learn Python包开发的机器学习框架内进行的。总共纳入了2552名患者。肠杆菌科占分离株的85.5%,其中大肠杆菌、克雷伯菌属和变形杆菌属最为常见。耐药性分布为FQ-R 48.6%、3GC-R 40.1%、BL/BLI-R 29.9%和C-R 16.9%。模型验证显示,对于所有四种耐药类别,预测抗生素耐药性的性能良好,其中对C-R的性能最佳(AUC-ROC 0.921±0.013)。已提供所开发的流程(https://github.com/EttoreRocchi/ResPredAI)以及在不同数据集上运行相同工作流程的文档,以考虑当地的流行病学和临床特征。