Machine learning for personalized antimicrobial susceptibility breakpoints.

Zhong, Yinzheng ORCID: 0000-0001-8477-3956, Hope, William ORCID: 0000-0001-6187-878X, Buchan, Iain, Velluva, Anoop, Gerada, Alessandro ORCID: 0000-0002-6743-4271, Rosato, Conor ORCID: 0000-0001-8394-7344, Green, Peter L and Howard, Alex (2025) Machine learning for personalized antimicrobial susceptibility breakpoints. The Journal of antimicrobial chemotherapy. dkaf419-. ISSN 0305-7453, 1460-2091

Access the full-text of this item by clicking on the Open Access link.

Abstract

<h4>Objectives</h4>Infection diagnoses are critical to the personalized interpretation of EUCAST aminopenicillin breakpoints for Enterobacterales, but microbiology laboratories cannot predict diagnosis when specimens are received. Here, we assess whether machine learning could facilitate personalized antimicrobial susceptibility breakpoint reporting by predicting urinary tract infection (UTI) diagnoses.<h4>Methods</h4>XGBoost models were trained using open-source electronic healthcare record data to predict complicated UTI in patients with Enterobacterales bacteriuria and to predict UTI in patients with Enterobacterales bacteraemia. These models were validated and used to provide simulated aminopenicillin dosing/regimen recommendations based on antimicrobial susceptibility results for patients with bacteriuria and bacteraemia in a holdout dataset. The main outcomes were the proportions of patients recommended appropriate aminopenicillin dosages/regimens according to EUCAST guidelines based on their diagnosis.<h4>Results</h4>The area under the receiver operating characteristic curve was 0.62 for predicting both complicated UTI in patients with bacteriuria and UTI in patients with bacteraemia. In the simulation study, 79.3% (n = 276) and 72.7% (n = 8) of patients with ampicillin-susceptible Enterobacterales bacteriuria and bacteraemia, respectively, were recommended appropriate aminopenicillin dosages/regimens for their infection diagnosis according to EUCAST guidelines. Adjusting the probability threshold for predicting complicated UTI increased the proportion of appropriate recommendations in bacteriuria to 96.6% (n = 336).<h4>Conclusions</h4>Using machine learning models to predict the probability of complicated UTI in patients with bacteriuria and the probability of UTI in patients with bacteraemia resulted in appropriate aminopenicillin dosages/regimens being recommended in most cases. These results provide proof-of-concept for how machine learning could facilitate the personalized implementation of EUCAST aminopenicillin breakpoints.

Item Type:	Article
Uncontrolled Keywords:	3207 Medical Microbiology, 32 Biomedical and Clinical Sciences, 3202 Clinical Sciences, 3211 Oncology and Carcinogenesis, Women's Health, Machine Learning and Artificial Intelligence, Urologic Diseases, Networking and Information Technology R&D (NITRD), Infectious Diseases, Precision Medicine, Infection, 3 Good Health and Well Being
Divisions:	Faculty of Health & Life Sciences Faculty of Science & Engineering Faculty of Science & Engineering > School of Engineering Faculty of Health & Life Sciences > Inst. Systems, Molec & Integrative Biology Faculty of Health & Life Sciences > Inst. Systems, Molec & Integrative Biology > Inst. Systems, Molec & Integrative Biology (T&R Staff) Faculty of Health & Life Sciences > Inst. Systems, Molec & Integrative Biology > Pharmacology & Therapeutics Faculty of Science & Engineering > School of Engineering > Mechanical and Aerospace Engineering
Depositing User:	Symplectic Admin
Date Deposited:	20 Nov 2025 15:41
Last Modified:	06 Dec 2025 02:52
DOI:	10.1093/jac/dkaf419
Open Access URL:	https://doi.org/10.1093/jac/dkaf419
Related Websites:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3195543
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.