{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T02:10:34Z","timestamp":1788315034471,"version":"build-2803163510"},"reference-count":22,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["226691\/Z\/22\/Z"],"award-info":[{"award-number":["226691\/Z\/22\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000272","name":"NIHR","doi-asserted-by":"publisher","award":["NIHR205131"],"award-info":[{"award-number":["NIHR205131"]}],"id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>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\u200a=\u200a276) and 72.7% (n\u200a=\u200a8) 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\u200a=\u200a336).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jac\/dkaf419","type":"journal-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T11:18:07Z","timestamp":1762946287000},"source":"Crossref","is-referenced-by-count":1,"title":["Machine learning for personalized antimicrobial susceptibility breakpoints"],"prefix":"10.1093","volume":"81","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8477-3956","authenticated-orcid":false,"given":"Yinzheng","family":"Zhong","sequence":"first","affiliation":[{"name":"Department of Clinical Pharmacology & Therapeutics, University of Liverpool , Liverpool ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6187-878X","authenticated-orcid":false,"given":"William","family":"Hope","sequence":"additional","affiliation":[{"name":"Department of Clinical Pharmacology & Therapeutics, University of Liverpool , Liverpool ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iain","family":"Buchan","sequence":"additional","affiliation":[{"name":"Department of Public Health, Policy & Systems, University of Liverpool , Liverpool ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anoop","family":"Velluva","sequence":"additional","affiliation":[{"name":"Department of Clinical Pharmacology & Therapeutics, University of Liverpool , Liverpool ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6743-4271","authenticated-orcid":false,"given":"Alessandro","family":"Gerada","sequence":"additional","affiliation":[{"name":"Department of Clinical Pharmacology & Therapeutics, University of Liverpool , Liverpool ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Conor","family":"Rosato","sequence":"additional","affiliation":[{"name":"Department of Clinical Pharmacology & Therapeutics, University of Liverpool , Liverpool ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter L","family":"Green","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Aerospace Engineering, School of Engineering, University of Liverpool , Liverpool ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Howard","sequence":"additional","affiliation":[{"name":"Department of Clinical Pharmacology & Therapeutics, University of Liverpool , Liverpool ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,11,12]]},"reference":[{"key":"2026011413265287800_dkaf419-B1","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1093\/jac\/dkab449","article-title":"Impact of rapid susceptibility testing on antimicrobial therapy and clinical outcomes in Gram-negative bloodstream infections","volume":"77","author":"Anton-Vazquez","year":"2022","journal-title":"J Antimicrob Chemother"},{"key":"2026011413265287800_dkaf419-B2","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1093\/jac\/48.suppl_1.5","article-title":"Determination of minimum inhibitory concentrations","volume":"48","author":"Andrews","year":"2001","journal-title":"J Antimicrob Chemother"},{"key":"2026011413265287800_dkaf419-B3","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/S0924-8579(02)00028-6","article-title":"Breakpoints: current practice and future perspectives","volume":"19","author":"Mouton","year":"2002","journal-title":"Int J Antimicrob Agents"},{"key":"2026011413265287800_dkaf419-B4","author":"The European Committee on Antimicrobial Susceptibility Testing"},{"key":"2026011413265287800_dkaf419-B5","doi-asserted-by":"publisher","first-page":"e02336-21","DOI":"10.1128\/jcm.02336-21","article-title":"The use of machine learning for image analysis artificial intelligence in clinical microbiology","volume":"61","author":"Burns","year":"2023","journal-title":"J Clin Microbiol"},{"key":"2026011413265287800_dkaf419-B6","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1038\/s41591-021-01619-9","article-title":"Direct antimicrobial resistance prediction from clinical MALDI-TOF mass spectra using machine learning","volume":"28","author":"Weis","year":"2022","journal-title":"Nat Med"},{"key":"2026011413265287800_dkaf419-B7","doi-asserted-by":"publisher","first-page":"1424","DOI":"10.1038\/s41587-023-01674-2","article-title":"High-throughput microbial culturomics using automation and machine learning","volume":"41","author":"Huang","year":"2023","journal-title":"Nat Biotechnol"},{"key":"2026011413265287800_dkaf419-B8","doi-asserted-by":"publisher","DOI":"10.1016\/S1473-3099(25)00313-5","article-title":"Artificial intelligence and infectious diseases: tackling antimicrobial resistance, from personalised care to antibiotic discovery","author":"Howard","year":"2025","journal-title":"Lancet Infect Dis"},{"key":"2026011413265287800_dkaf419-B9","doi-asserted-by":"crossref","unstructured":"Johnson AEW, Bulgarelli L, Shen L \u00a0et al \u00a0MIMIC-IV, a freely accessible electronic health record dataset. Sci Data \u00a02023; 10: 1. 10.1038\/s41597-022-01899-x","DOI":"10.1038\/s41597-022-01899-x"},{"key":"2026011413265287800_dkaf419-B10","unstructured":"Johnson A, Pollard T, Chahin A, et al \u00a0MIT-LCP\/Mimic-Code: V2.5.0. 2024. 10.5281\/ZENODO.821871."},{"key":"2026011413265287800_dkaf419-B11","doi-asserted-by":"publisher","first-page":"E215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for Complex physiologic signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"2026011413265287800_dkaf419-B12","doi-asserted-by":"publisher","first-page":"2317","DOI":"10.1093\/jac\/dkae230","article-title":"Bayesian estimation of the prevalence of antimicrobial resistance: a mathematical modelling study","volume":"79","author":"Howard","year":"2024","journal-title":"J Antimicrob Chemother"},{"key":"2026011413265287800_dkaf419-B13","author":"Chen"},{"key":"2026011413265287800_dkaf419-B14","volume-title":"Complicated Urinary Tract Infections","author":"Sabih","year":"2024"},{"key":"2026011413265287800_dkaf419-B15","first-page":"2021","article-title":"Performance analysis of XGBoost classifier with missing data","volume":"2","author":"Aydin","year":"2021","journal-title":"Manchester Journal of Artificial Intelligence and Applied Sciences (MJAIAS)"},{"key":"2026011413265287800_dkaf419-B16","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD\u200a+\u200aAI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"2026011413265287800_dkaf419-B17","author":"Sundararajan"},{"key":"2026011413265287800_dkaf419-B18","author":"Lundberg"},{"key":"2026011413265287800_dkaf419-B19","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1177\/0272989X10369005","article-title":"Dynamic microsimulation models for health outcomes: a review","volume":"31","author":"Rutter","year":"2011","journal-title":"Med Decis Making"},{"key":"2026011413265287800_dkaf419-B20","doi-asserted-by":"publisher","first-page":"2456","DOI":"10.1093\/jac\/dkv147","article-title":"Nitrofurantoin revisited: a systematic review and meta-analysis of controlled trials","volume":"70","author":"Huttner","year":"2015","journal-title":"J Antimicrob Chemother"},{"key":"2026011413265287800_dkaf419-B21","doi-asserted-by":"publisher","first-page":"e500","DOI":"10.1016\/S2666-5247(24)00003-X","article-title":"System-wide approaches to antimicrobial therapy and antimicrobial resistance in the UK: the AMR-X framework","volume":"5","author":"Abel","year":"2024","journal-title":"Lancet Microbe"},{"key":"2026011413265287800_dkaf419-B22","doi-asserted-by":"publisher","first-page":"e79","DOI":"10.1016\/S2589-7500(23)00221-2","article-title":"Antimicrobial learning systems: an implementation blueprint for artificial intelligence to tackle antimicrobial resistance","volume":"6","author":"Howard","year":"2024","journal-title":"Lancet Digit Health"}],"container-title":["Journal of Antimicrobial Chemotherapy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jac\/article-pdf\/81\/1\/dkaf419\/65274735\/dkaf419.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jac\/article-pdf\/81\/1\/dkaf419\/65274735\/dkaf419.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T18:27:03Z","timestamp":1768415223000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jac\/article\/doi\/10.1093\/jac\/dkaf419\/8321597"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,6]]}},"URL":"https:\/\/doi.org\/10.1093\/jac\/dkaf419","relation":{},"ISSN":["0305-7453","1460-2091"],"issn-type":[{"value":"0305-7453","type":"print"},{"value":"1460-2091","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,1]]},"published":{"date-parts":[[2025,11,12]]},"article-number":"dkaf419"}}